yao-meta-skill/reports/review-studio.json

{
  "schema_version": "2.0",
  "ok": true,
  "skill_dir": ".",
  "summary": {
    "decision": "review",
    "world_class_score": 91,
    "gate_count": 16,
    "blocker_count": 0,
    "warning_count": 3,
    "action_count": 3,
    "annotation_count": 0,
    "open_annotation_count": 0,
    "open_annotation_blocker_count": 0,
    "open_annotation_warning_count": 0
  },
  "gates": [
    {
      "key": "intent-canvas",
      "label": "意图画布",
      "status": "pass",
      "detail": "intent confidence 100/100; Intent is clear enough to package the first routeable version.",
      "evidence": "reports/intent-confidence.json",
      "link": "intent-confidence.md"
    },
    {
      "key": "trigger-lab",
      "label": "触发实验",
      "status": "pass",
      "detail": "13 trigger cases; 0 misroutes; 0 ambiguous",
      "evidence": "reports/route_scorecard.json",
      "link": "route_scorecard.md"
    },
    {
      "key": "output-lab",
      "label": "输出实验",
      "status": "warn",
      "detail": "5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5",
      "evidence": "reports/output_quality_scorecard.json",
      "link": "output_quality_scorecard.md"
    },
    {
      "key": "context-budget",
      "label": "上下文",
      "status": "pass",
      "detail": "initial load 960/1000; deferred 416415/120000; top deferred scripts 367825; resource governance governed; quality density 135.4",
      "evidence": "reports/context_budget.json",
      "link": "context_budget.md"
    },
    {
      "key": "runtime-matrix",
      "label": "运行矩阵",
      "status": "pass",
      "detail": "5 / 5 targets pass",
      "evidence": "reports/conformance_matrix.json",
      "link": "conformance_matrix.md"
    },
    {
      "key": "trust-report",
      "label": "信任报告",
      "status": "pass",
      "detail": "0 secrets; 106 scripts; 3 network-capable scripts; 0 help smoke failures",
      "evidence": "reports/security_trust_report.json",
      "link": "security_trust_report.md"
    },
    {
      "key": "python-compat",
      "label": "Python 兼容",
      "status": "pass",
      "detail": "Python 3.11; 171 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards",
      "evidence": "reports/python_compatibility.json",
      "link": "python_compatibility.md"
    },
    {
      "key": "architecture-maintainability",
      "label": "架构维护",
      "status": "pass",
      "detail": "168 Python files; 0 hotspots; 0 blockers; largest 886 lines; 34 CLI handlers",
      "evidence": "reports/architecture_maintainability.json",
      "link": "architecture_maintainability.md"
    },
    {
      "key": "permission-gates",
      "label": "权限批准",
      "status": "pass",
      "detail": "3/3 permissions approved; gaps 0; required file_write, network, subprocess",
      "evidence": "reports/security_trust_report.json + security/permission_policy.json",
      "link": "../security/permission_policy.md"
    },
    {
      "key": "permission-runtime",
      "label": "权限探针",
      "status": "pass",
      "detail": "4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4",
      "evidence": "reports/runtime_permission_probes.json",
      "link": "runtime_permission_probes.md"
    },
    {
      "key": "skill-atlas",
      "label": "组合治理",
      "status": "pass",
      "detail": "12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues",
      "evidence": "reports/skill_atlas.json",
      "link": "skill_atlas.html"
    },
    {
      "key": "operations-loop",
      "label": "运营回路",
      "status": "pass",
      "detail": "1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low",
      "evidence": "reports/adoption_drift_report.json",
      "link": "adoption_drift_report.md"
    },
    {
      "key": "review-waivers",
      "label": "人工批准",
      "status": "warn",
      "detail": "0 active waivers; 1 warning gates still need reviewer decision",
      "evidence": "reports/review_waivers.json",
      "link": "review_waivers.md"
    },
    {
      "key": "world-class-evidence",
      "label": "世界证据",
      "status": "warn",
      "detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 7/13 pass; 6 blocked; overclaim guard true",
      "evidence": "reports/world_class_evidence_ledger.json",
      "link": "world_class_evidence_ledger.md"
    },
    {
      "key": "registry-audit",
      "label": "注册审计",
      "status": "pass",
      "detail": "yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures",
      "evidence": "reports/registry_audit.json + reports/install_simulation.json",
      "link": "registry_audit.md"
    },
    {
      "key": "release-notes",
      "label": "发布路线",
      "status": "pass",
      "detail": "0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended",
      "evidence": "reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md",
      "link": "promotion_decisions.md"
    }
  ],
  "blockers": [],
  "warnings": [
    {
      "key": "output-lab",
      "label": "输出实验",
      "status": "warn",
      "detail": "5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5",
      "evidence": "reports/output_quality_scorecard.json",
      "link": "output_quality_scorecard.md"
    },
    {
      "key": "review-waivers",
      "label": "人工批准",
      "status": "warn",
      "detail": "0 active waivers; 1 warning gates still need reviewer decision",
      "evidence": "reports/review_waivers.json",
      "link": "review_waivers.md"
    },
    {
      "key": "world-class-evidence",
      "label": "世界证据",
      "status": "warn",
      "detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 7/13 pass; 6 blocked; overclaim guard true",
      "evidence": "reports/world_class_evidence_ledger.json",
      "link": "world_class_evidence_ledger.md"
    }
  ],
  "review_actions": [
    {
      "gate_key": "output-lab",
      "label": "输出实验",
      "status": "warn",
      "priority": "warning",
      "summary": "补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。",
      "why": "没有输出质量和人工盲评证据时，Skill 只能证明会触发，不能证明输出真的更好且经得起审查。",
      "source_fix": "evals/output/cases.jsonl + reports/output_quality_scorecard.md + reports/output_review_kit.html + reports/output_review_adjudication.md",
      "source_refs": [
        {
          "path": "evals/output/cases.jsonl",
          "label": "output eval cases",
          "kind": "eval",
          "line": 1,
          "exists": true,
          "link": "../evals/output/cases.jsonl"
        },
        {
          "path": "reports/output_quality_scorecard.md",
          "label": "output scorecard",
          "kind": "report",
          "line": 1,
          "exists": true,
          "link": "output_quality_scorecard.md"
        },
        {
          "path": "reports/output_execution_runs.md",
          "label": "output execution runs",
          "kind": "report",
          "line": 1,
          "exists": true,
          "link": "output_execution_runs.md"
        },
        {
          "path": "reports/output_blind_review_pack.md",
          "label": "blind A/B review pack",
          "kind": "report",
          "line": 1,
          "exists": true,
          "link": "output_blind_review_pack.md"
        },
        {
          "path": "reports/output_review_kit.html",
          "label": "reviewer cockpit",
          "kind": "report",
          "line": 6,
          "exists": true,
          "link": "output_review_kit.html"
        },
        {
          "path": "reports/output_review_adjudication.md",
          "label": "review adjudication",
          "kind": "report",
          "line": 1,
          "exists": true,
          "link": "output_review_adjudication.md"
        }
      ],
      "evidence": "reports/output_quality_scorecard.json",
      "evidence_link": "output_quality_scorecard.md",
      "verification_command": "python3 scripts/adjudicate_output_review.py --write-template && python3 scripts/yao.py output-review",
      "evidence_steps": []
    },
    {
      "gate_key": "review-waivers",
      "label": "人工批准",
      "status": "warn",
      "priority": "warning",
      "summary": "对保留的 warning 写入 reviewer、理由、范围和到期时间，或修掉 warning。",
      "why": "warning 可以被接受，但必须可审计、会过期，并且不能掩盖 blocker。",
      "source_fix": "reports/review_waivers.md",
      "source_refs": [
        {
          "path": "reports/review_waivers.md",
          "label": "waiver ledger",
          "kind": "report",
          "line": 1,
          "exists": true,
          "link": "review_waivers.md"
        },
        {
          "path": "references/review-waiver-method.md",
          "label": "waiver method",
          "kind": "method",
          "line": 1,
          "exists": true,
          "link": "../references/review-waiver-method.md"
        }
      ],
      "evidence": "reports/review_waivers.json",
      "evidence_link": "review_waivers.md",
      "verification_command": "python3 scripts/render_review_waivers.py .",
      "evidence_steps": []
    },
    {
      "gate_key": "world-class-evidence",
      "label": "世界证据",
      "status": "warn",
      "priority": "warning",
      "summary": "补齐 provider、真人盲评、原生权限执行和真实客户端遥测证据，或明确本次发布不声明 world-class 完成。",
      "why": "世界级结论必须来自已接受的外部/人工证据；计划、metadata fallback、待评审和本地命令都不能替代完成证据。",
      "source_fix": "reports/world_class_operator_runbook.html + reports/world_class_evidence_ledger.md + reports/world_class_evidence_intake.md + reports/world_class_submission_review.md",
      "source_refs": [
        {
          "path": "reports/world_class_evidence_ledger.md",
          "label": "world-class evidence ledger",
          "kind": "report",
          "line": 1,
          "exists": true,
          "link": "world_class_evidence_ledger.md"
        },
        {
          "path": "reports/world_class_evidence_plan.md",
          "label": "world-class evidence plan",
          "kind": "report",
          "line": 1,
          "exists": true,
          "link": "world_class_evidence_plan.md"
        },
        {
          "path": "reports/world_class_evidence_intake.md",
          "label": "world-class evidence intake",
          "kind": "report",
          "line": 1,
          "exists": true,
          "link": "world_class_evidence_intake.md"
        },
        {
          "path": "reports/world_class_submission_review.md",
          "label": "world-class submission review",
          "kind": "report",
          "line": 1,
          "exists": true,
          "link": "world_class_submission_review.md"
        },
        {
          "path": "reports/world_class_claim_guard.md",
          "label": "world-class claim guard",
          "kind": "report",
          "line": 1,
          "exists": true,
          "link": "world_class_claim_guard.md"
        },
        {
          "path": "evidence/world_class/intake.schema.json",
          "label": "evidence intake schema",
          "kind": "schema",
          "line": 4,
          "exists": true,
          "link": "../evidence/world_class/intake.schema.json"
        },
        {
          "path": "evidence/world_class/templates/provider-holdout.intake.json",
          "label": "provider intake template",
          "kind": "template",
          "line": 3,
          "exists": true,
          "link": "../evidence/world_class/templates/provider-holdout.intake.json"
        },
        {
          "path": "evidence/world_class/templates/human-adjudication.intake.json",
          "label": "human intake template",
          "kind": "template",
          "line": 3,
          "exists": true,
          "link": "../evidence/world_class/templates/human-adjudication.intake.json"
        },
        {
          "path": "evidence/world_class/templates/native-permission-enforcement.intake.json",
          "label": "permission intake template",
          "kind": "template",
          "line": 3,
          "exists": true,
          "link": "../evidence/world_class/templates/native-permission-enforcement.intake.json"
        },
        {
          "path": "evidence/world_class/templates/native-client-telemetry.intake.json",
          "label": "telemetry intake template",
          "kind": "template",
          "line": 3,
          "exists": true,
          "link": "../evidence/world_class/templates/native-client-telemetry.intake.json"
        },
        {
          "path": "reports/skill_os2_audit.md",
          "label": "Skill OS 2.0 audit",
          "kind": "report",
          "line": 1,
          "exists": true,
          "link": "skill_os2_audit.md"
        },
        {
          "path": "reports/output_review_decisions.json",
          "label": "human review decisions",
          "kind": "report",
          "line": 6,
          "exists": true,
          "link": "output_review_decisions.json"
        },
        {
          "path": "reports/runtime_permission_probes.md",
          "label": "runtime permission probes",
          "kind": "report",
          "line": 1,
          "exists": true,
          "link": "runtime_permission_probes.md"
        },
        {
          "path": "reports/adoption_drift_report.md",
          "label": "adoption drift",
          "kind": "report",
          "line": 1,
          "exists": true,
          "link": "adoption_drift_report.md"
        }
      ],
      "evidence": "reports/world_class_evidence_ledger.json",
      "evidence_link": "world_class_evidence_ledger.md",
      "verification_command": "python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py review-studio .",
      "evidence_steps": [
        {
          "key": "provider-holdout",
          "label": "Provider Holdout",
          "category": "external",
          "status": "pending",
          "readiness": "awaiting-submission",
          "current": "model-executed 0; token-observed 0",
          "next_action": "Run provider-backed holdout cases with real credentials and commit only aggregate evidence.",
          "submission_path": "evidence/world_class/submissions/provider-holdout.json",
          "template_path": "evidence/world_class/templates/provider-holdout.intake.json",
          "source_pass_count": 1,
          "source_blocked_count": 2,
          "blocked_checks": [
            {
              "label": "Provider model run",
              "field": "model_executed_count",
              "actual": 0,
              "expected": ">0",
              "status": "blocked",
              "next_action": "Run provider-backed output-exec with real credentials."
            },
            {
              "label": "Token usage observed",
              "field": "token_observed_count",
              "actual": 0,
              "expected": ">0",
              "status": "blocked",
              "next_action": "Provider execution should return non-estimated token usage."
            }
          ],
          "commands": [
            {
              "key": "prepare_submission",
              "label": "准备提交",
              "command": "python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions"
            },
            {
              "key": "validate_intake",
              "label": "校验入口",
              "command": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
            },
            {
              "key": "submission_review",
              "label": "审查提交",
              "command": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions"
            },
            {
              "key": "refresh_ledger",
              "label": "刷新台账",
              "command": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions"
            },
            {
              "key": "guard_claim",
              "label": "声明守卫",
              "command": "python3 scripts/yao.py world-class-claim-guard ."
            }
          ],
          "runbook": [
            "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
            "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
            "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields."
          ]
        },
        {
          "key": "human-adjudication",
          "label": "Human Adjudication",
          "category": "human",
          "status": "pending",
          "readiness": "awaiting-submission",
          "current": "0/5 decisions; pending 5",
          "next_action": "Record real A/B choices in the decision template, then regenerate adjudication.",
          "submission_path": "evidence/world_class/submissions/human-adjudication.json",
          "template_path": "evidence/world_class/templates/human-adjudication.intake.json",
          "source_pass_count": 2,
          "source_blocked_count": 2,
          "blocked_checks": [
            {
              "label": "No pending decisions",
              "field": "pending_count",
              "actual": 5,
              "expected": "==0",
              "status": "blocked",
              "next_action": "Record a reviewer choice for every pair."
            },
            {
              "label": "Judgments complete",
              "field": "judgment_count",
              "actual": 0,
              "expected": "==pair_count",
              "status": "blocked",
              "next_action": "Every pair needs one valid human judgment."
            }
          ],
          "commands": [
            {
              "key": "prepare_submission",
              "label": "准备提交",
              "command": "python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions"
            },
            {
              "key": "validate_intake",
              "label": "校验入口",
              "command": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
            },
            {
              "key": "submission_review",
              "label": "审查提交",
              "command": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions"
            },
            {
              "key": "refresh_ledger",
              "label": "刷新台账",
              "command": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions"
            },
            {
              "key": "guard_claim",
              "label": "声明守卫",
              "command": "python3 scripts/yao.py world-class-claim-guard ."
            }
          ],
          "runbook": [
            "python3 scripts/yao.py output-review-kit --write-template",
            "Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.",
            "python3 scripts/adjudicate_output_review.py --write-template"
          ]
        },
        {
          "key": "native-permission-enforcement",
          "label": "Native Permission Enforcement",
          "category": "external",
          "status": "pending",
          "readiness": "awaiting-submission",
          "current": "native-enforced targets 0; installer-enforced targets 4",
          "next_action": "Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.",
          "submission_path": "evidence/world_class/submissions/native-permission-enforcement.json",
          "template_path": "evidence/world_class/templates/native-permission-enforcement.intake.json",
          "source_pass_count": 2,
          "source_blocked_count": 1,
          "blocked_checks": [
            {
              "label": "Native enforcement",
              "field": "native_enforcement_count",
              "actual": 0,
              "expected": ">0",
              "status": "blocked",
              "next_action": "Collect real target-client or external runtime guard proof."
            }
          ],
          "commands": [
            {
              "key": "prepare_submission",
              "label": "准备提交",
              "command": "python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions"
            },
            {
              "key": "validate_intake",
              "label": "校验入口",
              "command": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
            },
            {
              "key": "submission_review",
              "label": "审查提交",
              "command": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions"
            },
            {
              "key": "refresh_ledger",
              "label": "刷新台账",
              "command": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions"
            },
            {
              "key": "guard_claim",
              "label": "声明守卫",
              "command": "python3 scripts/yao.py world-class-claim-guard ."
            }
          ],
          "runbook": [
            "Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.",
            "Update the generated target adapter only when the guard is actually enforced by that target.",
            "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip"
          ]
        },
        {
          "key": "native-client-telemetry",
          "label": "Native Client Telemetry",
          "category": "external",
          "status": "pending",
          "readiness": "awaiting-submission",
          "current": "external source events 0; adoption samples 1",
          "next_action": "Install a real client against the native host and import production metadata-only events.",
          "submission_path": "evidence/world_class/submissions/native-client-telemetry.json",
          "template_path": "evidence/world_class/templates/native-client-telemetry.intake.json",
          "source_pass_count": 2,
          "source_blocked_count": 1,
          "blocked_checks": [
            {
              "label": "External events",
              "field": "external_source_events",
              "actual": 0,
              "expected": ">0",
              "status": "blocked",
              "next_action": "Import at least one metadata-only event from a real client."
            }
          ],
          "commands": [
            {
              "key": "prepare_submission",
              "label": "准备提交",
              "command": "python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions"
            },
            {
              "key": "validate_intake",
              "label": "校验入口",
              "command": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
            },
            {
              "key": "submission_review",
              "label": "审查提交",
              "command": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions"
            },
            {
              "key": "refresh_ledger",
              "label": "刷新台账",
              "command": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions"
            },
            {
              "key": "guard_claim",
              "label": "声明守卫",
              "command": "python3 scripts/yao.py world-class-claim-guard ."
            }
          ],
          "runbook": [
            "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
            "Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.",
            "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl"
          ]
        }
      ]
    }
  ],
  "evidence_paths": {
    "skill_overview": "reports/skill-overview.html",
    "review_viewer": "reports/review-viewer.html",
    "output_eval": "reports/output_quality_scorecard.md",
    "output_execution": "reports/output_execution_runs.md",
    "output_blind_review": "reports/output_blind_review_pack.md",
    "output_review_kit": "reports/output_review_kit.md",
    "output_review_kit_html": "reports/output_review_kit.html",
    "output_review_decisions": "reports/output_review_decisions.json",
    "output_review_adjudication": "reports/output_review_adjudication.md",
    "benchmark_reproducibility": "reports/benchmark_reproducibility.md",
    "skill_os2_coverage": "reports/skill_os2_coverage.md",
    "runtime_conformance": "reports/conformance_matrix.md",
    "trust_report": "reports/security_trust_report.md",
    "python_compatibility": "reports/python_compatibility.md",
    "architecture_maintainability": "reports/architecture_maintainability.md",
    "permission_policy": "security/permission_policy.md",
    "runtime_permissions": "reports/runtime_permission_probes.md",
    "skill_atlas": "reports/skill_atlas.html",
    "compiled_targets": "reports/compiled_targets.md",
    "adoption_drift": "reports/adoption_drift_report.md",
    "review_waivers": "reports/review_waivers.md",
    "review_annotations": "reports/review_annotations.md",
    "world_class_evidence_plan": "reports/world_class_evidence_plan.md",
    "world_class_evidence_ledger": "reports/world_class_evidence_ledger.md",
    "world_class_evidence_intake": "reports/world_class_evidence_intake.md",
    "world_class_submission_review": "reports/world_class_submission_review.md",
    "world_class_operator_runbook": "reports/world_class_operator_runbook.md",
    "world_class_operator_runbook_html": "reports/world_class_operator_runbook.html",
    "world_class_claim_guard": "reports/world_class_claim_guard.md",
    "registry_audit": "reports/registry_audit.md",
    "package_verification": "reports/package_verification.md",
    "install_simulation": "reports/install_simulation.md",
    "upgrade_check": "reports/upgrade_check.md",
    "migration": "docs/migration-v2.md"
  },
  "data": {
    "overview": {
      "skill_summary": {
        "name": "yao-meta-skill",
        "title": "Yao Meta Skill",
        "display_name": "Yao Meta Skill",
        "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
        "maturity": "governed",
        "updated_at": "2026-03-31",
        "core_value": "把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。",
        "audience": "Skill 作者、复用团队和后续 reviewer。",
        "deliverables": [
          "SKILL.md",
          "agents/interface.yaml",
          "reports/skill-ir.json",
          "reports/compiled_targets.md",
          "reports/output_quality_scorecard.md",
          "reports/output_execution_runs.md",
          "reports/output_blind_review_pack.md",
          "reports/output_review_kit.md",
          "reports/output_review_adjudication.md",
          "reports/benchmark_reproducibility.md",
          "reports/output_blind_answer_key.json",
          "reports/conformance_matrix.md",
          "reports/security_trust_report.md",
          "reports/runtime_permission_probes.md",
          "reports/skill_atlas.html",
          "reports/registry_audit.md",
          "reports/package_verification.md",
          "reports/install_simulation.md",
          "reports/upgrade_check.md",
          "reports/adoption_drift_report.md",
          "reports/review_waivers.md",
          "reports/world_class_evidence_plan.md",
          "reports/world_class_evidence_ledger.md",
          "reports/review_annotations.md",
          "reports/review-studio.html",
          "reports/skill-overview.html"
        ],
        "flow": [
          "输入材料",
          "Skill 包体",
          "可复用能力"
        ]
      },
      "scorecard": {
        "completeness_score": {
          "label": "完整度",
          "score": 100,
          "reasons": [
            "SKILL.md 已存在，是 Skill 的入口。",
            "README.md 已存在，便于人工阅读。",
            "agents/interface.yaml 已存在，便于跨平台适配。",
            "manifest.json 已存在，生命周期信息可追踪。",
            "reports/ 已存在，生成证据可以随包体迁移。"
          ]
        },
        "trigger_score": {
          "label": "触发清晰",
          "score": 100,
          "reasons": [
            "frontmatter description 已存在，具备基础路由面。",
            "description 有足够长度说明任务边界。",
            "description 已包含使用场景或排除边界信号。",
            "evals/ 已存在，可承载触发样例或质量检查。",
            "intent-confidence 报告已生成，可辅助判断触发稳定性。"
          ]
        },
        "evidence_score": {
          "label": "证据充分",
          "score": 100,
          "reasons": [
            "已生成 20 / 20 类报告证据。",
            "skill-ir.json 已存在。",
            "compiled_targets.json 已存在。",
            "intent-dialogue.json 已存在。"
          ]
        },
        "maintainability_score": {
          "label": "可维护性",
          "score": 100,
          "reasons": [
            "SKILL.md 约 356 个词/字。",
            "入口文件保持克制，可维护性较好。",
            "references/ 已承载扩展指导。",
            "scripts/ 已承载确定性逻辑。",
            "evals/ 已承载可迁移检查。"
          ]
        },
        "portability_score": {
          "label": "可迁移性",
          "score": 100,
          "reasons": [
            "agents/interface.yaml 已存在。",
            "manifest.json 已存在。",
            "目标平台或 adapter target 已声明。",
            "入口文件未发现明显私有绝对路径。"
          ]
        },
        "context_cost": {
          "label": "上下文成本",
          "score": 42,
          "reasons": [
            "入口约 356 个词/字，references 约 16045 个词/字。",
            "分数越高代表上下文成本越低。",
            "上下文成本偏高，建议压缩入口或拆分 references。"
          ]
        }
      },
      "capability_profile": {
        "archetype": "governed",
        "task_family": "Execution operation",
        "maturity": "governed",
        "trigger_strength": "手动触发 + description 路由",
        "reuse_scope": "跨平台",
        "matrix": {
          "execution_certainty": 72,
          "knowledge_density": 80
        }
      },
      "principle_model": {
        "nodes": [
          {
            "title": "意图澄清",
            "body": "Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse."
          },
          {
            "title": "边界路由",
            "body": "用 frontmatter description 决定是否触发，并写明相邻非目标。"
          },
          {
            "title": "资产分层",
            "body": "把入口、参考、脚本、评估和报告拆到各自目录，避免 SKILL.md 膨胀。"
          },
          {
            "title": "证据回路",
            "body": "Ask only the highest-leverage clarification before adding package weight."
          },
          {
            "title": "漂移观察",
            "body": "Add near-neighbor exclusions and route evals before expanding workflow steps."
          },
          {
            "title": "杠杆升级",
            "body": "Name the recurring job, expected input, output, and strongest non-goal in compact language."
          }
        ],
        "layers": [
          "入口层",
          "参考层",
          "脚本层",
          "评估层",
          "报告层"
        ]
      },
      "contract_boundary": {
        "trigger": {
          "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
          "activation": "manual",
          "execution": "inline",
          "shell": "bash"
        },
        "inputs": [
          "rough workflow notes, SOPs, runbooks, prompts, transcripts, documents, or repeated task descriptions",
          "an existing skill directory that needs refactor, evaluation, packaging, or governance hardening",
          "target platform requirements such as OpenAI, Claude, generic Agent Skills, or team distribution",
          "benchmark references, local constraints, desired maturity tier, and review standards"
        ],
        "outputs": [
          "A working skill package with lean SKILL.md, aligned agents/interface.yaml, justified references, scripts only when useful, eval evidence, reports, packaging metadata, and clear next iteration recommendations.",
          "结构化 Skill 目录，共 8 类关键资产。"
        ],
        "should_trigger": [
          "把重复流程沉淀为可复用的 agent skill。",
          "把分散提示词、对话记录或操作规范整理为稳定能力。",
          "团队复用前，需要明确触发边界、质量证据和维护责任。"
        ],
        "should_not_trigger": [
          "只需要一次性回答、没有复用价值的临时请求。",
          "要求直接执行相邻任务，而不是沉淀或使用这个 Skill。",
          "缺少必要事实且用户不允许澄清的场景。"
        ],
        "boundary_cards": [
          {
            "label": "Owned",
            "body": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse."
          },
          {
            "label": "Adjacent",
            "body": "相邻任务需要先确认是否应转为独立 Skill。"
          },
          {
            "label": "Excluded",
            "body": "不替代人工事实核查，也不静默扩大职责。"
          }
        ]
      },
      "quality_review": {
        "strengths": [
          "触发面保持精简，并锚定在 frontmatter description。",
          "已生成 Skill IR，核心语义可先于平台打包被审查和迁移。",
          "已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。",
          "已生成 Output Eval Lab scorecard，可比较 with-skill 与 baseline 输出质量。",
          "已生成 Output Execution Runs，可区分记录样本、命令执行和模型执行证据。",
          "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。"
        ],
        "gaps": [
          "上下文成本需要补强：入口约 356 个词/字，references 约 16045 个词/字。"
        ],
        "recommendations": [
          "先改触发边界，再扩展工作流。",
          "只把重复且稳定的步骤沉淀为脚本。",
          "每次升级后重新生成报告并检查分数原因。"
        ],
        "artifact_design": {
          "design_system": "metric editorial",
          "highlights": [
            "Execution-focused technical artifact with environment assumptions, copyable commands, expected outputs, and side effects made explicit.",
            "Name the working directory and required inputs for commands.",
            "Mark destructive, networked, or external side-effect operations.",
            "Prefer the smallest runnable snippet over broad framework scaffolding."
          ]
        },
        "prompt_quality": {
          "overall_quality_score": 89.0,
          "highlights": [
            "Primary prompt task family: Execution operation.",
            "Complexity: expert — multiple task families plus governance, evaluation, or expert-level constraints",
            "Completeness: 100/100.",
            "Clarity: 85/100."
          ]
        },
        "system_model": {
          "stability": {
            "score": 100,
            "band": "system-ready"
          },
          "highlights": [
            "Stability: system-ready (100/100).",
            "Owned job: Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse.",
            "Leverage: Tune the frontmatter description — Name the recurring job, expected input, output, and strongest non-goal in compact language.",
            "Leverage: Install output self-repair checks — Add only the checks that prevent recurring output mistakes."
          ]
        }
      },
      "risk_governance": {
        "risks": [
          {
            "name": "误触发风险",
            "impact": 3,
            "probability": 1,
            "signal": "frontmatter description 已存在，具备基础路由面。",
            "response": "先补证据和边界，再增加包体复杂度。"
          },
          {
            "name": "输出漂移风险",
            "impact": 2,
            "probability": 1,
            "signal": "已生成 20 / 20 类报告证据。",
            "response": "先补证据和边界，再增加包体复杂度。"
          },
          {
            "name": "证据不足风险",
            "impact": 3,
            "probability": 1,
            "signal": "已生成 20 / 20 类报告证据。",
            "response": "先补证据和边界，再增加包体复杂度。"
          },
          {
            "name": "包体膨胀风险",
            "impact": 2,
            "probability": 1,
            "signal": "SKILL.md 约 356 个词/字。",
            "response": "先补证据和边界，再增加包体复杂度。"
          },
          {
            "name": "跨平台迁移风险",
            "impact": 3,
            "probability": 1,
            "signal": "agents/interface.yaml 已存在。",
            "response": "先补证据和边界，再增加包体复杂度。"
          }
        ],
        "risk_families": [
          {
            "key": "markdown_readability",
            "label": "Markdown readability",
            "matched_keywords": [
              "md",
              "report",
              "doc"
            ],
            "score": 3,
            "risks": [
              "Tables can render as dense grids with weak hierarchy or poor mobile readability.",
              "Long bullets can make the output look complete while hiding the actual decision logic.",
              "Mixed heading levels can reduce scanability."
            ],
            "constraints": [
              "Use tables only when comparison is the main job; otherwise prefer compact cards or grouped bullets.",
              "Keep table cells short and move explanations below the table.",
              "Use heading levels consistently and keep each section anchored to a user-facing outcome."
            ],
            "self_repair": [
              "Preview whether each table still reads well when columns are narrow.",
              "Convert any table with paragraph-length cells into bullets or cards."
            ]
          },
          {
            "key": "citation_clutter",
            "label": "Citation and footnote clutter",
            "matched_keywords": [
              "source",
              "reference"
            ],
            "score": 2,
            "risks": [
              "Footnote markers or dense citation notes can interrupt the reading flow.",
              "Evidence can be over-attached to obvious statements and under-attached to risky claims.",
              "Source notes may become more prominent than the tutorial itself."
            ],
            "constraints": [
              "Attach citations only to claims that need evidence, not to every sentence.",
              "Group source notes at the end of a section when inline markers would hurt readability.",
              "Keep the main sentence readable without requiring the reader to chase a footnote."
            ],
            "self_repair": [
              "Remove decorative citations that do not support a material claim.",
              "Move repeated source explanations into one compact source note."
            ]
          },
          {
            "key": "visual_capture",
            "label": "Screenshot and visual capture",
            "matched_keywords": [
              "capture"
            ],
            "score": 1,
            "risks": [
              "Screenshots can be captured from the wrong state, wrong viewport, or wrong crop.",
              "Missing screenshots can cause the skill to invent visual references instead of declaring the gap.",
              "Image descriptions can omit the action-relevant region."
            ],
            "constraints": [
              "Never invent a screenshot; state when visual evidence is missing.",
              "Record the source, viewport, and crop intent for any screenshot-dependent output.",
              "Describe what the reader should inspect in the image, not just that an image exists."
            ],
            "self_repair": [
              "Check that every screenshot reference points to a real provided or generated asset.",
              "Reword any visual instruction that depends on an unseen screen state."
            ]
          },
          {
            "key": "code_or_command_safety",
            "label": "Code and command safety",
            "matched_keywords": [
              "script"
            ],
            "score": 1,
            "risks": [
              "Commands can omit environment assumptions, working directory, or rollback notes.",
              "Code snippets can look runnable while missing required inputs.",
              "Error handling can be either absent or over-engineered."
            ],
            "constraints": [
              "Name the working directory, required inputs, and expected output for each command.",
              "Mark destructive or external side-effect operations explicitly.",
              "Prefer the smallest runnable snippet over broad framework code."
            ],
            "self_repair": [
              "Scan each command for cwd, input, output, and side-effect assumptions.",
              "Remove speculative error handling that is not tied to a real failure mode."
            ]
          },
          {
            "key": "tone_and_specificity",
            "label": "Tone and specificity",
            "matched_keywords": [
              "summary"
            ],
            "score": 1,
            "risks": [
              "Headings and summaries can drift into generic, interchangeable language.",
              "The output can sound polished but lose the user's actual taste, audience, or scenario.",
              "Strong claims can appear without examples or constraints."
            ],
            "constraints": [
              "Anchor titles and summaries in the user's audience, object, and concrete outcome.",
              "Avoid placeholder phrases such as comprehensive guide, ultimate solution, or key insights unless the source demands them.",
              "Preserve one distinctive phrase, constraint, or standard from the user's input."
            ],
            "self_repair": [
              "Replace generic title candidates with scenario-specific alternatives.",
              "Delete any polished sentence that could fit almost any project unchanged."
            ]
          }
        ],
        "human_judgment_boundary": [
          "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.",
          "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.",
          "Do not silently broaden the skill into adjacent jobs just because the examples are nearby."
        ]
      },
      "world_class_readiness": {
        "ready": false,
        "decision": "evidence-pending",
        "entry_count": 4,
        "pending_count": 4,
        "accepted_count": 0,
        "external_pending_count": 3,
        "human_pending_count": 1,
        "source_check_count": 13,
        "source_pass_count": 6,
        "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
        "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
        "entries": [
          {
            "key": "provider-holdout",
            "label_zh": "提供商留出",
            "label_en": "Provider Holdout",
            "category": "external",
            "category_zh": "外部证据",
            "category_en": "External evidence",
            "status": "pending",
            "summary_zh": "缺少真实 provider 模型运行和 token metadata。",
            "summary_en": "Missing a real provider model run and token metadata.",
            "blocked_checks": [
              "Provider model run",
              "Token usage observed"
            ]
          },
          {
            "key": "human-adjudication",
            "label_zh": "人工盲评",
            "label_en": "Human Adjudication",
            "category": "human",
            "category_zh": "人工证据",
            "category_en": "Human evidence",
            "status": "pending",
            "summary_zh": "盲评 pair 仍待真实 reviewer 决策。",
            "summary_en": "Blind-review pairs still need real reviewer decisions.",
            "blocked_checks": [
              "No pending decisions",
              "Judgments complete"
            ]
          },
          {
            "key": "native-permission-enforcement",
            "label_zh": "原生权限",
            "label_en": "Native Permission",
            "category": "external",
            "category_zh": "外部证据",
            "category_en": "External evidence",
            "status": "pending",
            "summary_zh": "原生 runtime enforcement 仍待目标客户端或外部安装器证明。",
            "summary_en": "Native runtime enforcement still needs target-client or external-installer proof.",
            "blocked_checks": [
              "Native enforcement"
            ]
          },
          {
            "key": "native-client-telemetry",
            "label_zh": "原生遥测",
            "label_en": "Native Telemetry",
            "category": "external",
            "category_zh": "外部证据",
            "category_en": "External evidence",
            "status": "pending",
            "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
            "summary_en": "Real external-client metadata-only events have not been imported yet.",
            "blocked_checks": [
              "External events",
              "Adoption sample"
            ]
          }
        ]
      },
      "package_assets": {
        "entries": [
          {
            "path": "SKILL.md",
            "label": "Skill entrypoint",
            "kind": "file",
            "file_count": 1
          },
          {
            "path": "README.md",
            "label": "Human-readable usage guide",
            "kind": "file",
            "file_count": 1
          },
          {
            "path": "agents/interface.yaml",
            "label": "Neutral interface metadata",
            "kind": "file",
            "file_count": 1
          },
          {
            "path": "manifest.json",
            "label": "Lifecycle and portability metadata",
            "kind": "file",
            "file_count": 1
          },
          {
            "path": "references",
            "label": "Extended guidance and reusable notes",
            "kind": "folder",
            "file_count": 34
          },
          {
            "path": "scripts",
            "label": "Deterministic helpers or local tooling",
            "kind": "folder",
            "file_count": 106
          },
          {
            "path": "evals",
            "label": "Trigger and quality checks",
            "kind": "folder",
            "file_count": 29
          },
          {
            "path": "reports",
            "label": "Generated evidence and overview artifacts",
            "kind": "folder",
            "file_count": 211
          }
        ],
        "file_count": 384,
        "folder_count": 4,
        "distribution": [
          {
            "label": "SKILL.md",
            "value": 1
          },
          {
            "label": "README.md",
            "value": 1
          },
          {
            "label": "agents/interface.yaml",
            "value": 1
          },
          {
            "label": "manifest.json",
            "value": 1
          },
          {
            "label": "references",
            "value": 34
          },
          {
            "label": "scripts",
            "value": 106
          },
          {
            "label": "evals",
            "value": 29
          },
          {
            "label": "reports",
            "value": 211
          }
        ]
      },
      "iteration_roadmap": {
        "items": [
          {
            "title": "补齐世界证据",
            "why": "世界级证据仍有 4 项待补；公开完成态 claim 必须继续保持阻塞。",
            "actions": [
              "补齐提供商留出证据：缺少真实 provider 模型运行和 token metadata。",
              "补齐人工盲评证据：盲评 pair 仍待真实 reviewer 决策。",
              "继续补齐剩余 2 项外部/人工证据，并保持 claim guard 为 pending 状态。"
            ],
            "unlocks": "全部外部/人工证据被 ledger 接受后，才能进入公开 world-class claim 复核。",
            "source": "world_class_evidence_ledger"
          },
          {
            "title": "Borrow one proven pattern on purpose",
            "why": "You already have public benchmark objects. The next gain is to choose one pattern intentionally instead of absorbing everything loosely.",
            "actions": [
              "Read the strongest pattern from obra/superpowers.",
              "Decide whether to borrow method, structure, execution, or portability, but only one of them first.",
              "Record what you will not borrow so the package stays light."
            ],
            "unlocks": "A cleaner package shape with less accidental over-design."
          },
          {
            "title": "Harden portability semantics",
            "why": "The skill already signals reuse across environments, so contract clarity matters early.",
            "actions": [
              "Confirm activation mode, execution context, and trust assumptions.",
              "Add or review degradation strategy for non-native targets.",
              "Package the skill once to verify adapter expectations."
            ],
            "unlocks": "Safer cross-environment reuse with less target drift."
          }
        ]
      },
      "report_contract": {
        "schema_version": "2.0",
        "html_report": "reports/skill-overview.html",
        "language": "zh-CN",
        "default_language": "zh-CN",
        "languages": [
          "zh-CN",
          "en"
        ],
        "layout": "kami-white-audit-v2",
        "nav_labels": [
          "技能概述",
          "总览指标",
          "能力画像",
          "原理结构",
          "契约边界",
          "质量评估",
          "风险治理",
          "包体资产",
          "迭代路线"
        ],
        "nav_labels_en": [
          "Overview",
          "Metrics",
          "Profile",
          "Principle",
          "Contract",
          "Quality",
          "Risk",
          "Assets",
          "Roadmap"
        ]
      },
      "name": "yao-meta-skill",
      "title": "Yao Meta Skill",
      "display_name": "Yao Meta Skill",
      "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
      "logic_steps": [
        "Decide whether the request should become a skill and choose the lightest fit.",
        "Capture job, output, exclusions, constraints, and standards.",
        "Run reference scan: external benchmarks first, user references second, local fit third; surface only uncertainty or conflict.",
        "Write the `description` early and test route quality before expanding the package.",
        "Add output-risk, artifact-design, prompt-quality, and system-model reports only when they matter."
      ],
      "usage_steps": [
        "Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals.",
        "Use this skill when the request matches: Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse."
      ],
      "package_map": [
        {
          "path": "SKILL.md",
          "label": "Skill entrypoint",
          "kind": "file",
          "file_count": 1
        },
        {
          "path": "README.md",
          "label": "Human-readable usage guide",
          "kind": "file",
          "file_count": 1
        },
        {
          "path": "agents/interface.yaml",
          "label": "Neutral interface metadata",
          "kind": "file",
          "file_count": 1
        },
        {
          "path": "manifest.json",
          "label": "Lifecycle and portability metadata",
          "kind": "file",
          "file_count": 1
        },
        {
          "path": "references",
          "label": "Extended guidance and reusable notes",
          "kind": "folder",
          "file_count": 34
        },
        {
          "path": "scripts",
          "label": "Deterministic helpers or local tooling",
          "kind": "folder",
          "file_count": 106
        },
        {
          "path": "evals",
          "label": "Trigger and quality checks",
          "kind": "folder",
          "file_count": 29
        },
        {
          "path": "reports",
          "label": "Generated evidence and overview artifacts",
          "kind": "folder",
          "file_count": 211
        }
      ],
      "strengths": [
        "触发面保持精简，并锚定在 frontmatter description。",
        "已生成 Skill IR，核心语义可先于平台打包被审查和迁移。",
        "已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。",
        "已生成 Output Eval Lab scorecard，可比较 with-skill 与 baseline 输出质量。",
        "已生成 Output Execution Runs，可区分记录样本、命令执行和模型执行证据。",
        "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。"
      ],
      "scenarios": [
        "把重复流程沉淀为可复用的 agent skill。",
        "把分散提示词、对话记录或操作规范整理为稳定能力。",
        "团队复用前，需要明确触发边界、质量证据和维护责任。",
        "用户说出类似需求时：Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals."
      ],
      "trigger_contract": {
        "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
        "activation": "manual",
        "execution": "inline",
        "shell": "bash"
      },
      "io_contract": {
        "inputs": [
          "rough workflow notes, SOPs, runbooks, prompts, transcripts, documents, or repeated task descriptions",
          "an existing skill directory that needs refactor, evaluation, packaging, or governance hardening",
          "target platform requirements such as OpenAI, Claude, generic Agent Skills, or team distribution",
          "benchmark references, local constraints, desired maturity tier, and review standards"
        ],
        "outputs": [
          "A working skill package with lean SKILL.md, aligned agents/interface.yaml, justified references, scripts only when useful, eval evidence, reports, packaging metadata, and clear next iteration recommendations.",
          "结构化 Skill 目录，共 8 类关键资产。"
        ]
      },
      "principles": [
        {
          "title": "意图澄清",
          "body": "Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse."
        },
        {
          "title": "边界路由",
          "body": "用 frontmatter description 决定是否触发，并写明相邻非目标。"
        },
        {
          "title": "资产分层",
          "body": "把入口、参考、脚本、评估和报告拆到各自目录，避免 SKILL.md 膨胀。"
        },
        {
          "title": "证据回路",
          "body": "Ask only the highest-leverage clarification before adding package weight."
        },
        {
          "title": "漂移观察",
          "body": "Add near-neighbor exclusions and route evals before expanding workflow steps."
        },
        {
          "title": "杠杆升级",
          "body": "Name the recurring job, expected input, output, and strongest non-goal in compact language."
        }
      ],
      "roadmap": [
        {
          "title": "补齐世界证据",
          "why": "世界级证据仍有 4 项待补；公开完成态 claim 必须继续保持阻塞。",
          "actions": [
            "补齐提供商留出证据：缺少真实 provider 模型运行和 token metadata。",
            "补齐人工盲评证据：盲评 pair 仍待真实 reviewer 决策。",
            "继续补齐剩余 2 项外部/人工证据，并保持 claim guard 为 pending 状态。"
          ],
          "unlocks": "全部外部/人工证据被 ledger 接受后，才能进入公开 world-class claim 复核。",
          "source": "world_class_evidence_ledger"
        },
        {
          "title": "Borrow one proven pattern on purpose",
          "why": "You already have public benchmark objects. The next gain is to choose one pattern intentionally instead of absorbing everything loosely.",
          "actions": [
            "Read the strongest pattern from obra/superpowers.",
            "Decide whether to borrow method, structure, execution, or portability, but only one of them first.",
            "Record what you will not borrow so the package stays light."
          ],
          "unlocks": "A cleaner package shape with less accidental over-design."
        },
        {
          "title": "Harden portability semantics",
          "why": "The skill already signals reuse across environments, so contract clarity matters early.",
          "actions": [
            "Confirm activation mode, execution context, and trust assumptions.",
            "Add or review degradation strategy for non-native targets.",
            "Package the skill once to verify adapter expectations."
          ],
          "unlocks": "Safer cross-environment reuse with less target drift."
        }
      ],
      "cards": [],
      "introduction": [
        "这份报告用于快速理解新生成 Skill 的定位、原理、触发边界和交付内容。",
        "先确认重复任务、真实输入形态和可交付输出，再决定是否继续加 references、scripts 或 evals。",
        "如果需求仍然模糊，优先回到 intent dialogue 收紧边界，再扩展包体结构。"
      ],
      "benchmark_highlights": [],
      "skill_ir": {
        "schema_version": "2.0.0",
        "target_count": 5,
        "trigger_samples": 8,
        "output_eval_cases": 3
      },
      "compiled_targets": {
        "ok": true,
        "schema_version": "1.0",
        "summary": {
          "target_count": 5,
          "pass_count": 5,
          "warn_count": 0,
          "block_count": 0,
          "failure_count": 0,
          "warning_count": 0
        },
        "targets": [
          {
            "target": "openai",
            "status": "pass",
            "adapter_mode": "metadata-adapter",
            "degradation_strategy": "metadata-adapter",
            "native_surface": "OpenAI-style interface metadata plus neutral Agent Skills source",
            "permission_enforcement": "metadata-only",
            "generated_files": [
              "targets/openai/adapter.json",
              "targets/openai/agents/openai.yaml"
            ],
            "unsupported_features": [
              "client-native script permission prompts are represented as permission contract metadata"
            ],
            "warnings": []
          },
          {
            "target": "claude",
            "status": "pass",
            "adapter_mode": "neutral-source-plus-adapter",
            "degradation_strategy": "neutral-source-plus-adapter",
            "native_surface": "Claude-compatible neutral source folder with adapter notes",
            "permission_enforcement": "metadata-fallback",
            "generated_files": [
              "targets/claude/adapter.json",
              "targets/claude/README.md"
            ],
            "unsupported_features": [
              "vendor-native metadata fields are carried as adapter JSON and README notes"
            ],
            "warnings": []
          },
          {
            "target": "generic",
            "status": "pass",
            "adapter_mode": "agent-skills-compatible",
            "degradation_strategy": "neutral-source",
            "native_surface": "Agent Skills compatible neutral package",
            "permission_enforcement": "consumer-enforced-or-metadata-only",
            "generated_files": [
              "targets/generic/adapter.json"
            ],
            "unsupported_features": [],
            "warnings": []
          },
          {
            "target": "agent-skills-compatible",
            "status": "pass",
            "adapter_mode": "neutral-agent-skills-source",
            "degradation_strategy": "neutral-source",
            "native_surface": "Agent Skills standard source tree",
            "permission_enforcement": "consumer-enforced-or-metadata-only",
            "generated_files": [
              "SKILL.md",
              "agents/interface.yaml"
            ],
            "unsupported_features": [],
            "warnings": []
          },
          {
            "target": "vscode",
            "status": "pass",
            "adapter_mode": "vscode-agent-skills-adapter",
            "degradation_strategy": "agent-skills-source-with-vscode-notes",
            "native_surface": "VS Code/Copilot Agent Skills project or user scope",
            "permission_enforcement": "client-or-workspace-trust",
            "generated_files": [
              "targets/vscode/adapter.json",
              "targets/vscode/README.md"
            ],
            "unsupported_features": [
              "VS Code installation scope is documented but not installed by this compiler"
            ],
            "warnings": []
          }
        ],
        "failures": [],
        "warnings": []
      },
      "output_quality": {
        "case_count": 5,
        "file_backed_case_count": 1,
        "near_neighbor_case_count": 1,
        "boundary_case_count": 1,
        "baseline_pass_rate": 0.0,
        "with_skill_pass_rate": 100.0,
        "delta": 100.0,
        "regression_count": 0,
        "gate_pass": true,
        "failure_taxonomy": [],
        "blind_pair_count": 5
      },
      "output_execution": {
        "ok": true,
        "summary": {
          "case_count": 5,
          "variant_run_count": 10,
          "command_executed_count": 10,
          "model_executed_count": 0,
          "recorded_fixture_count": 0,
          "timing_observed_count": 10,
          "token_observed_count": 0,
          "token_estimated_count": 10,
          "baseline_pass_rate": 0.0,
          "with_skill_pass_rate": 100.0,
          "delta": 100.0,
          "regression_count": 0,
          "failure_count": 0,
          "gate_pass": true
        },
        "runner": {
          "mode": "command",
          "command": [
            "python3",
            "scripts/local_output_eval_runner.py"
          ],
          "timeout_seconds": 30.0
        },
        "failures": []
      },
      "output_blind_review": {
        "summary": {
          "pair_count": 5,
          "answer_key_separate": true,
          "with_skill_hidden_count": 5
        },
        "seed": "yao-output-eval-blind-v1",
        "pair_count": 5,
        "answer_key_separate": true
      },
      "output_review_kit": {
        "ok": true,
        "summary": {
          "case_count": 5,
          "ready_for_adjudication_count": 0,
          "pending_decision_count": 5,
          "invalid_decision_count": 0,
          "reviewer_metadata_present": false,
          "answer_key_hidden": true,
          "answer_key_path_exposed": false,
          "ready_to_run_adjudication": false,
          "failure_count": 0
        },
        "artifacts": {
          "reviewer_kit_json": "reports/output_review_kit.json",
          "reviewer_kit_markdown": "reports/output_review_kit.md",
          "reviewer_kit_html": "reports/output_review_kit.html",
          "blind_pack_json": "reports/output_blind_review_pack.json",
          "blind_pack_markdown": "reports/output_blind_review_pack.md",
          "decisions": "reports/output_review_decisions.json",
          "adjudication_json": "reports/output_review_adjudication.json",
          "adjudication_markdown": "reports/output_review_adjudication.md"
        },
        "failures": []
      },
      "output_review_adjudication": {
        "ok": true,
        "summary": {
          "pair_count": 5,
          "judgment_count": 0,
          "pending_count": 5,
          "agreement_count": 0,
          "disagreement_count": 0,
          "invalid_decision_count": 0,
          "answer_revealed_count": 0,
          "pending_answer_hidden_count": 5,
          "agreement_rate": null,
          "needs_review": true,
          "failure_count": 0,
          "reviewer_checklist_count": 5,
          "reviewer_checklist_pending_count": 5,
          "reviewer_checklist_invalid_count": 0,
          "reviewer_checklist_ready_count": 0
        },
        "reviewer": "",
        "reviewed_at": "",
        "failures": []
      },
      "benchmark_reproducibility": {
        "ok": true,
        "summary": {
          "reproducibility_ready": true,
          "release_lock_ready": false,
          "methodology_complete": true,
          "required_artifact_count": 24,
          "missing_artifact_count": 0,
          "evidence_bundle_sha256": "119f209f1d4665b38a489cc372140ec9f01c663c4d2637048e82b924cfadb6c5",
          "source_contract_sha256": "ecb6c742c79077b26d1f9e61ede1b1c4c078b485fc57467b969d9c1744bc91b6",
          "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
          "output_case_count": 5,
          "failure_disclosure_count": 3,
          "command_count": 21,
          "command_executed_count": 10,
          "timing_observed_count": 10,
          "model_executed_count": 0,
          "token_observed_count": 0,
          "human_review_complete": false,
          "provider_evidence_complete": false,
          "world_class_ready": false,
          "world_class_open_gap_count": 4,
          "world_class_task_count": 4,
          "world_class_ledger_pending_count": 4,
          "world_class_source_check_count": 13,
          "world_class_source_pass_count": 6,
          "world_class_source_blocked_count": 7,
          "public_claim_ready": false,
          "public_claim_blocker_count": 5,
          "working_tree_dirty": true,
          "changed_file_count": 61
        },
        "commit": "5495734e7e33b19b84a932626112d783a3edf271",
        "missing_artifacts": [],
        "limitations": [
          "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
          "Local command-runner evidence is reproducible but does not replace provider-backed model holdout evidence.",
          "Pending blind-review decisions are visible but do not count as human adjudication.",
          "World-class readiness remains false until external and human evidence gaps close."
        ]
      },
      "runtime_conformance": {
        "target_count": 5,
        "pass_count": 5,
        "fail_count": 0
      },
      "runtime_permissions": {
        "ok": true,
        "summary": {
          "target_count": 4,
          "pass_count": 4,
          "fail_count": 0,
          "native_enforcement_count": 0,
          "metadata_fallback_count": 4,
          "residual_risk_count": 4,
          "required_capability_count": 3,
          "failure_count": 0,
          "installer_enforcement_source_status": "present",
          "installer_enforcement_target_count": 4,
          "installer_enforcement_pass_count": 4,
          "installer_permission_enforced_count": 12,
          "installer_permission_failure_count": 0,
          "installer_permission_capability_count": 3,
          "world_class_native_evidence_ready": false,
          "installer_enforcement_ready": true
        },
        "expected_capabilities": [
          "file_write",
          "network",
          "subprocess"
        ],
        "targets": [
          {
            "target": "openai",
            "status": "pass",
            "assurance": "metadata-fallback-explicit",
            "native_enforcement": false,
            "metadata_fallback_explicit": true,
            "residual_risks": [
              "Client-native permission enforcement is not provided by this target; installer or operator must honor metadata."
            ]
          },
          {
            "target": "claude",
            "status": "pass",
            "assurance": "metadata-fallback-explicit",
            "native_enforcement": false,
            "metadata_fallback_explicit": true,
            "residual_risks": [
              "Client-native permission enforcement is not provided by this target; installer or operator must honor metadata."
            ]
          },
          {
            "target": "generic",
            "status": "pass",
            "assurance": "metadata-fallback-explicit",
            "native_enforcement": false,
            "metadata_fallback_explicit": true,
            "residual_risks": [
              "Client-native permission enforcement is not provided by this target; installer or operator must honor metadata."
            ]
          },
          {
            "target": "vscode",
            "status": "pass",
            "assurance": "metadata-fallback-explicit",
            "native_enforcement": false,
            "metadata_fallback_explicit": true,
            "residual_risks": [
              "Client-native permission enforcement is not provided by this target; installer or operator must honor metadata."
            ]
          }
        ],
        "failures": []
      },
      "trust_security": {
        "scanned_files": 193,
        "script_count": 106,
        "internal_module_count": 26,
        "secret_findings": 0,
        "dependency_files": [
          "requirements-ci.txt"
        ],
        "network_script_count": 3,
        "network_policy_covered_count": 3,
        "network_policy_missing_count": 0,
        "file_write_script_count": 67,
        "permission_required_count": 3,
        "permission_approved_count": 3,
        "permission_missing_count": 0,
        "permission_invalid_count": 0,
        "permission_expired_count": 0,
        "help_smoke_checked_count": 80,
        "help_smoke_failed_count": 0,
        "interactive_script_count": 0,
        "package_hash_scope": "source-contract-without-generated-reports",
        "package_hash_file_count": 193,
        "package_sha256": "ecb6c742c79077b26d1f9e61ede1b1c4c078b485fc57467b969d9c1744bc91b6"
      },
      "skill_atlas": {
        "skill_count": 12,
        "actionable_skill_count": 1,
        "route_collision_count": 5,
        "actionable_route_collision_count": 0,
        "owner_gap_count": 9,
        "actionable_owner_gap_count": 0,
        "stale_count": 10,
        "actionable_stale_count": 0,
        "shared_resource_count": 0,
        "no_route_opportunity_count": 0,
        "telemetry_report_count": 1,
        "drift_signal_count": 0,
        "actionable_drift_signal_count": 0,
        "non_actionable_issue_count": 24
      },
      "registry_distribution": {
        "ok": true,
        "package": {
          "schema_version": "2.0",
          "name": "yao-meta-skill",
          "version": "1.1.0",
          "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
          "targets": [
            "openai",
            "claude",
            "generic",
            "agent-skills-compatible",
            "vscode"
          ],
          "maturity": "governed",
          "owner": "Yao Team",
          "review_cadence": "quarterly",
          "trust_level": "local",
          "license": "MIT",
          "checksums": {
            "package_sha256": "37a1ec0f35323886bdae64523b4113f5dc4ba3153117ee4980b8e5cd54b49aba",
            "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc"
          },
          "compatibility": {
            "openai": "pass",
            "claude": "pass",
            "agent-skills": "pass",
            "vscode": "pass",
            "generic": "pass",
            "agent-skills-compatible": "pass"
          },
          "source": {
            "skill_dir": ".",
            "skill_ir": "skill-ir/examples/yao-meta-skill.json",
            "ir_schema_version": "2.0.0",
            "canonical_metadata": "agents/interface.yaml"
          },
          "artifacts": {
            "overview_html": "reports/skill-overview.html",
            "review_studio_html": "reports/review-studio.html",
            "trust_report": "reports/security_trust_report.md",
            "conformance_matrix": "reports/conformance_matrix.md",
            "compiled_targets": "reports/compiled_targets.md",
            "package_verification": "reports/package_verification.md",
            "install_simulation": "reports/install_simulation.md",
            "adoption_drift": "reports/adoption_drift_report.md",
            "review_waivers": "reports/review_waivers.md",
            "review_annotations": "reports/review_annotations.md",
            "package_metadata": "registry/packages/yao-meta-skill.json"
          },
          "distribution": {
            "archive_verified": true,
            "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
            "package_verification": "reports/package_verification.json",
            "install_simulated": true,
            "install_simulation": "reports/install_simulation.json"
          },
          "generated_at": "2026-06-13"
        },
        "failures": [],
        "warnings": []
      },
      "package_verification": {
        "ok": true,
        "summary": {
          "target_count": 4,
          "adapter_count": 4,
          "archive_present": true,
          "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
          "archive_entry_count": 586,
          "failure_count": 0,
          "warning_count": 0
        },
        "failures": [],
        "warnings": []
      },
      "install_simulation": {
        "ok": true,
        "summary": {
          "archive_present": true,
          "archive_entry_count": 601,
          "archive_extracted": true,
          "entrypoint_loaded": true,
          "manifest_loaded": true,
          "interface_loaded": true,
          "adapter_count": 4,
          "installer_permission_enforced_count": 12,
          "installer_permission_failure_count": 0,
          "permission_target_count": 4,
          "permission_capability_count": 3,
          "install_root_is_temp": false,
          "failure_count": 0,
          "warning_count": 0
        },
        "failures": [],
        "warnings": []
      },
      "upgrade_check": {
        "ok": true,
        "summary": {
          "declared_bump": "minor",
          "recommended_bump": "minor",
          "breaking_change_count": 0,
          "added_target_count": 2,
          "metadata_change_count": 1,
          "checksum_change_count": 2,
          "failure_count": 0,
          "warning_count": 0
        },
        "upgrade_diff": {
          "name_changed": false,
          "added_targets": [
            "agent-skills-compatible",
            "vscode"
          ],
          "removed_targets": [],
          "compatibility_changes": [
            {
              "target": "agent-skills",
              "from": "missing",
              "to": "pass",
              "direction": "improved"
            },
            {
              "target": "agent-skills-compatible",
              "from": "missing",
              "to": "pass",
              "direction": "improved"
            },
            {
              "target": "vscode",
              "from": "missing",
              "to": "pass",
              "direction": "improved"
            }
          ],
          "metadata_changes": [
            {
              "field": "description",
              "from": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes.",
              "to": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse."
            }
          ],
          "checksum_changes": [
            {
              "field": "archive_sha256",
              "from": "",
              "to": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc"
            },
            {
              "field": "package_sha256",
              "from": "0000000000000000000000000000000000000000000000000000000000000000",
              "to": "37a1ec0f35323886bdae64523b4113f5dc4ba3153117ee4980b8e5cd54b49aba"
            }
          ]
        },
        "release_notes": [
          "Recommended version bump: minor.",
          "Added targets: agent-skills-compatible, vscode.",
          "Package or archive checksum changed; reviewers should verify package artifacts before release.",
          "Package verification evidence: reports/package_verification.md."
        ],
        "failures": [],
        "warnings": []
      },
      "adoption_drift": {
        "ok": true,
        "summary": {
          "event_count": 1,
          "adoption_sample_count": 0,
          "activation_count": 0,
          "accepted_count": 0,
          "edited_count": 0,
          "rejected_count": 0,
          "missed_count": 0,
          "failed_count": 0,
          "adoption_rate": 0,
          "missed_trigger_count": 0,
          "wrong_trigger_count": 0,
          "bad_output_count": 0,
          "script_error_count": 0,
          "missing_resource_count": 0,
          "review_overdue_count": 0,
          "risk_band": "low",
          "event_types": {
            "review_event": 1
          },
          "failure_types": {},
          "source_types": {
            "manual": 1
          },
          "command_counts": {}
        },
        "next_iteration_candidates": [],
        "privacy_contract": {
          "storage": "local-first",
          "event_scope": "metadata-only",
          "raw_content_allowed": false,
          "raw_event_log_packaged": false,
          "blocked_fields": [
            "content",
            "input",
            "inputs",
            "message",
            "messages",
            "note",
            "output",
            "outputs",
            "prompt",
            "raw",
            "text",
            "transcript"
          ]
        },
        "failures": []
      },
      "review_waivers": {
        "ok": true,
        "summary": {
          "waiver_count": 0,
          "active_count": 0,
          "expired_count": 0,
          "invalid_count": 0,
          "covered_gate_count": 0,
          "covered_gate_keys": [],
          "waiver_candidate_count": 2,
          "waiverable_open_count": 1,
          "non_waivable_count": 1
        },
        "policy": {
          "blocker_waivers_allowed": false,
          "minimum_reason_chars": 20,
          "expires_required": true,
          "known_gate_keys": [
            "context-budget",
            "intent-canvas",
            "operations-loop",
            "output-lab",
            "permission-gates",
            "permission-runtime",
            "registry-audit",
            "release-notes",
            "runtime-matrix",
            "skill-atlas",
            "trigger-lab",
            "trust-report"
          ]
        },
        "failures": [],
        "warnings": []
      },
      "review_annotations": {
        "ok": true,
        "summary": {
          "annotation_count": 0,
          "open_count": 0,
          "resolved_count": 0,
          "deferred_count": 0,
          "open_blocker_count": 0,
          "open_warning_count": 0,
          "linked_gate_count": 0,
          "target_missing_count": 0,
          "failure_count": 0
        },
        "annotations": [],
        "failures": []
      },
      "world_class_evidence_plan": {
        "ok": true,
        "summary": {
          "audit_decision": "continue-iteration",
          "world_class_ready": false,
          "audit_world_class_ready": false,
          "ready_to_claim_world_class": false,
          "ledger_completion_required": true,
          "evidence_requirement_count": 4,
          "task_count": 4,
          "human_task_count": 1,
          "external_task_count": 3,
          "review_task_count": 0,
          "decision": "collect-external-evidence"
        },
        "tasks": [
          {
            "key": "provider-holdout",
            "label": "Provider Holdout",
            "status": "external_required",
            "category": "external",
            "owner": "operator with provider credentials",
            "current": "model-executed 0; token-observed 0",
            "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
            "runbook": [
              "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
              "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
              "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
              "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
            ],
            "success_checks": [
              "reports/output_execution_runs.json summary.model_executed_count > 0",
              "reports/output_execution_runs.json summary.timing_observed_count > 0",
              "reports/output_execution_runs.json summary.token_observed_count > 0",
              "reports/skill_os2_audit.json item provider-holdout status becomes pass"
            ],
            "evidence_artifacts": [
              "reports/output_execution_runs.json",
              "reports/output_execution_runs.md",
              "reports/skill_os2_audit.json",
              "evidence/world_class/intake.schema.json",
              "evidence/world_class/templates/provider-holdout.intake.json",
              "reports/world_class_evidence_intake.json",
              "reports/world_class_evidence_intake.md"
            ],
            "privacy_contract": [
              "Do not commit provider credentials or environment dumps.",
              "The output execution report records output hashes and aggregate run metadata, not raw provider prompts."
            ],
            "audit_next_action": "Run provider-backed holdout cases with real credentials and commit only aggregate evidence."
          },
          {
            "key": "human-adjudication",
            "label": "Human Adjudication",
            "status": "human_required",
            "category": "human",
            "owner": "human reviewer",
            "current": "0/5 decisions; pending 5",
            "objective": "Record real blind A/B reviewer decisions before claiming human output review completion.",
            "runbook": [
              "python3 scripts/yao.py output-review-kit --write-template",
              "Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.",
              "python3 scripts/adjudicate_output_review.py --write-template",
              "Edit reports/output_review_decisions.json with winner_variant values and reviewer metadata.",
              "python3 scripts/yao.py output-review",
              "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
              "Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.",
              "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
            ],
            "success_checks": [
              "reports/output_review_adjudication.json summary.pending_count == 0",
              "reports/output_review_adjudication.json summary.judgment_count == summary.pair_count",
              "reports/output_review_adjudication.json summary.invalid_decision_count == 0",
              "reports/skill_os2_audit.json item human-adjudication status becomes pass"
            ],
            "evidence_artifacts": [
              "reports/output_blind_review_pack.md",
              "reports/output_review_kit.md",
              "reports/output_review_decisions.json",
              "reports/output_review_adjudication.json",
              "reports/output_review_adjudication.md",
              "evidence/world_class/intake.schema.json",
              "evidence/world_class/templates/human-adjudication.intake.json",
              "reports/world_class_evidence_intake.json",
              "reports/world_class_evidence_intake.md"
            ],
            "privacy_contract": [
              "Reviewer decisions should not include raw user data or private customer detail.",
              "Keep the answer key separate until after decisions are recorded."
            ],
            "audit_next_action": "Record real A/B choices in the decision template, then regenerate adjudication."
          },
          {
            "key": "native-permission-enforcement",
            "label": "Native Permission Enforcement",
            "status": "external_required",
            "category": "external",
            "owner": "target client or installer integrator",
            "current": "native-enforced targets 0; installer-enforced targets 4",
            "objective": "Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.",
            "runbook": [
              "Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.",
              "Update the generated target adapter only when the guard is actually enforced by that target.",
              "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip",
              "python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation",
              "python3 scripts/yao.py runtime-permissions . --package-dir dist",
              "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
              "Copy evidence/world_class/templates/native-permission-enforcement.intake.json to evidence/world_class/submissions/native-permission-enforcement.json and fill only real evidence fields.",
              "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
            ],
            "success_checks": [
              "reports/runtime_permission_probes.json summary.native_enforcement_count > 0",
              "reports/runtime_permission_probes.json summary.failure_count == 0",
              "reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence",
              "reports/skill_os2_audit.json item native-permission-enforcement status becomes pass"
            ],
            "evidence_artifacts": [
              "dist/targets/*/adapter.json",
              "reports/runtime_permission_probes.json",
              "reports/runtime_permission_probes.md",
              "reports/install_simulation.json",
              "reports/install_simulation.md",
              "security/permission_policy.json",
              "evidence/world_class/intake.schema.json",
              "evidence/world_class/templates/native-permission-enforcement.intake.json",
              "reports/world_class_evidence_intake.json",
              "reports/world_class_evidence_intake.md"
            ],
            "privacy_contract": [
              "Do not mark native_enforcement true for metadata-only fallbacks.",
              "Keep residual risks visible for targets that still rely on operator enforcement."
            ],
            "audit_next_action": "Integrate a real target-client or external installer runtime guard before claiming native permission enforcement."
          },
          {
            "key": "native-client-telemetry",
            "label": "Native Client Telemetry",
            "status": "external_required",
            "category": "external",
            "owner": "Browser/Chrome/IDE/provider client integrator",
            "current": "external source events 0; adoption samples 0",
            "objective": "Import production metadata-only events from a real external client into the local drift loop.",
            "runbook": [
              "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
              "Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.",
              "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl",
              "python3 scripts/yao.py skill-atlas --workspace-root .",
              "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
              "Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.",
              "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
            ],
            "success_checks": [
              "reports/adoption_drift_report.json summary.source_types.external > 0",
              "reports/adoption_drift_report.json summary.adoption_sample_count > 0",
              "reports/skill_os2_audit.json item native-client-telemetry status becomes pass"
            ],
            "evidence_artifacts": [
              "reports/adoption_drift_report.json",
              "reports/adoption_drift_report.md",
              "reports/telemetry_hook_recipes.json",
              "scripts/telemetry_native_host.py",
              "evidence/world_class/intake.schema.json",
              "evidence/world_class/templates/native-client-telemetry.intake.json",
              "reports/world_class_evidence_intake.json",
              "reports/world_class_evidence_intake.md"
            ],
            "privacy_contract": [
              "Telemetry must remain metadata-only and local-first.",
              "Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field."
            ],
            "audit_next_action": "Install a real client against the native host and import production metadata-only events."
          }
        ],
        "source_audit": {
          "json": "reports/skill_os2_audit.json",
          "markdown": "reports/skill_os2_audit.md",
          "open_gap_count": 4
        }
      },
      "world_class_evidence_ledger": {
        "ok": true,
        "summary": {
          "ledger_entry_count": 4,
          "source_accepted_count": 0,
          "accepted_count": 0,
          "pending_count": 4,
          "human_pending_count": 1,
          "external_pending_count": 3,
          "submitted_entry_count": 0,
          "missing_submission_count": 4,
          "invalid_submission_count": 0,
          "source_check_count": 13,
          "source_pass_count": 6,
          "source_blocked_count": 7,
          "submitted_but_pending_count": 0,
          "source_accepted_without_valid_submission_count": 0,
          "overclaim_guard_active": true,
          "ready_to_claim_world_class": false,
          "decision": "evidence-pending"
        },
        "entries": [
          {
            "key": "provider-holdout",
            "label": "Provider Holdout",
            "category": "external",
            "owner": "operator with provider credentials",
            "status": "pending",
            "source_status": "external_required",
            "source_accepted": false,
            "current": "model-executed 0; token-observed 0",
            "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
            "runbook": [
              "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
              "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
              "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
              "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
            ],
            "provenance_requirements": [
              "provider-backed model run",
              "observed timing",
              "observed token metadata"
            ],
            "success_checks": [
              "reports/output_execution_runs.json summary.model_executed_count > 0",
              "reports/output_execution_runs.json summary.timing_observed_count > 0",
              "reports/output_execution_runs.json summary.token_observed_count > 0",
              "reports/skill_os2_audit.json item provider-holdout status becomes pass"
            ],
            "evidence_artifacts": [
              "reports/output_execution_runs.json",
              "reports/output_execution_runs.md",
              "reports/skill_os2_audit.json",
              "evidence/world_class/intake.schema.json",
              "evidence/world_class/templates/provider-holdout.intake.json",
              "reports/world_class_evidence_intake.json",
              "reports/world_class_evidence_intake.md"
            ],
            "privacy_contract": [
              "Do not commit provider credentials or environment dumps.",
              "The output execution report records output hashes and aggregate run metadata, not raw provider prompts."
            ],
            "observed_state": {
              "model_executed_count": 0,
              "timing_observed_count": 10,
              "token_observed_count": 0,
              "accepted": false
            },
            "source_checklist": [
              {
                "evidence_key": "provider-holdout",
                "label": "Provider model run",
                "field": "model_executed_count",
                "expected": ">0",
                "actual": 0,
                "status": "blocked",
                "source_accepted": false,
                "next_action": "Run provider-backed output-exec with real credentials."
              },
              {
                "evidence_key": "provider-holdout",
                "label": "Timing observed",
                "field": "timing_observed_count",
                "expected": ">0",
                "actual": 10,
                "status": "pass",
                "source_accepted": false,
                "next_action": "Provider execution should record timing metadata."
              },
              {
                "evidence_key": "provider-holdout",
                "label": "Token usage observed",
                "field": "token_observed_count",
                "expected": ">0",
                "actual": 0,
                "status": "blocked",
                "source_accepted": false,
                "next_action": "Provider execution should return non-estimated token usage."
              }
            ],
            "source_check_count": 3,
            "source_pass_count": 1,
            "source_blocked_count": 2,
            "submission_state": {
              "status": "missing",
              "path": "evidence/world_class/submissions/provider-holdout.json",
              "artifact_ref_count": 0,
              "attested_real_evidence": false,
              "privacy_contract_satisfied": false,
              "ledger_counts_as_completion": false
            },
            "anti_overclaim": {
              "planned_work_counts_as_evidence": false,
              "metadata_fallback_counts_as_native_enforcement": false,
              "pending_review_counts_as_human_decision": false,
              "local_command_runner_counts_as_provider_model": false
            },
            "next_action": "Run provider-backed holdout cases with real credentials and commit only aggregate evidence."
          },
          {
            "key": "human-adjudication",
            "label": "Human Adjudication",
            "category": "human",
            "owner": "human reviewer",
            "status": "pending",
            "source_status": "human_required",
            "source_accepted": false,
            "current": "0/5 decisions; pending 5",
            "objective": "Record real blind A/B reviewer decisions before claiming human output review completion.",
            "runbook": [
              "python3 scripts/yao.py output-review-kit --write-template",
              "Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.",
              "python3 scripts/adjudicate_output_review.py --write-template",
              "Edit reports/output_review_decisions.json with winner_variant values and reviewer metadata.",
              "python3 scripts/yao.py output-review",
              "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
              "Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.",
              "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
            ],
            "provenance_requirements": [
              "real reviewer identity",
              "blind A/B decisions",
              "answer key unopened until decisions exist"
            ],
            "success_checks": [
              "reports/output_review_adjudication.json summary.pending_count == 0",
              "reports/output_review_adjudication.json summary.judgment_count == summary.pair_count",
              "reports/output_review_adjudication.json summary.invalid_decision_count == 0",
              "reports/skill_os2_audit.json item human-adjudication status becomes pass"
            ],
            "evidence_artifacts": [
              "reports/output_blind_review_pack.md",
              "reports/output_review_kit.md",
              "reports/output_review_decisions.json",
              "reports/output_review_adjudication.json",
              "reports/output_review_adjudication.md",
              "evidence/world_class/intake.schema.json",
              "evidence/world_class/templates/human-adjudication.intake.json",
              "reports/world_class_evidence_intake.json",
              "reports/world_class_evidence_intake.md"
            ],
            "privacy_contract": [
              "Reviewer decisions should not include raw user data or private customer detail.",
              "Keep the answer key separate until after decisions are recorded."
            ],
            "observed_state": {
              "pair_count": 5,
              "judgment_count": 0,
              "pending_count": 5,
              "invalid_decision_count": 0,
              "answer_revealed_count": 0,
              "accepted": false
            },
            "source_checklist": [
              {
                "evidence_key": "human-adjudication",
                "label": "Review pairs exist",
                "field": "pair_count",
                "expected": ">0",
                "actual": 5,
                "status": "pass",
                "source_accepted": false,
                "next_action": "Generate the blind A/B review pack."
              },
              {
                "evidence_key": "human-adjudication",
                "label": "No pending decisions",
                "field": "pending_count",
                "expected": "==0",
                "actual": 5,
                "status": "blocked",
                "source_accepted": false,
                "next_action": "Record a reviewer choice for every pair."
              },
              {
                "evidence_key": "human-adjudication",
                "label": "Judgments complete",
                "field": "judgment_count",
                "expected": "==pair_count",
                "actual": 0,
                "status": "blocked",
                "source_accepted": false,
                "next_action": "Every pair needs one valid human judgment."
              },
              {
                "evidence_key": "human-adjudication",
                "label": "No invalid decisions",
                "field": "invalid_decision_count",
                "expected": "==0",
                "actual": 0,
                "status": "pass",
                "source_accepted": false,
                "next_action": "Fix malformed winner/confidence entries."
              }
            ],
            "source_check_count": 4,
            "source_pass_count": 2,
            "source_blocked_count": 2,
            "submission_state": {
              "status": "missing",
              "path": "evidence/world_class/submissions/human-adjudication.json",
              "artifact_ref_count": 0,
              "attested_real_evidence": false,
              "privacy_contract_satisfied": false,
              "ledger_counts_as_completion": false
            },
            "anti_overclaim": {
              "planned_work_counts_as_evidence": false,
              "metadata_fallback_counts_as_native_enforcement": false,
              "pending_review_counts_as_human_decision": false,
              "local_command_runner_counts_as_provider_model": false
            },
            "next_action": "Record real A/B choices in the decision template, then regenerate adjudication."
          },
          {
            "key": "native-permission-enforcement",
            "label": "Native Permission Enforcement",
            "category": "external",
            "owner": "target client or installer integrator",
            "status": "pending",
            "source_status": "external_required",
            "source_accepted": false,
            "current": "native-enforced targets 0; installer-enforced targets 4",
            "objective": "Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.",
            "runbook": [
              "Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.",
              "Update the generated target adapter only when the guard is actually enforced by that target.",
              "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip",
              "python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation",
              "python3 scripts/yao.py runtime-permissions . --package-dir dist",
              "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
              "Copy evidence/world_class/templates/native-permission-enforcement.intake.json to evidence/world_class/submissions/native-permission-enforcement.json and fill only real evidence fields.",
              "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
            ],
            "provenance_requirements": [
              "real target client or external installer runtime guard",
              "native enforcement flag or externally accepted guard proof",
              "residual risk retained for fallback targets"
            ],
            "success_checks": [
              "reports/runtime_permission_probes.json summary.native_enforcement_count > 0",
              "reports/runtime_permission_probes.json summary.failure_count == 0",
              "reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence",
              "reports/skill_os2_audit.json item native-permission-enforcement status becomes pass"
            ],
            "evidence_artifacts": [
              "dist/targets/*/adapter.json",
              "reports/runtime_permission_probes.json",
              "reports/runtime_permission_probes.md",
              "reports/install_simulation.json",
              "reports/install_simulation.md",
              "security/permission_policy.json",
              "evidence/world_class/intake.schema.json",
              "evidence/world_class/templates/native-permission-enforcement.intake.json",
              "reports/world_class_evidence_intake.json",
              "reports/world_class_evidence_intake.md"
            ],
            "privacy_contract": [
              "Do not mark native_enforcement true for metadata-only fallbacks.",
              "Keep residual risks visible for targets that still rely on operator enforcement."
            ],
            "observed_state": {
              "native_enforcement_count": 0,
              "metadata_fallback_count": 4,
              "installer_enforcement_pass_count": 4,
              "installer_permission_failure_count": 0,
              "installer_enforcement_ready": true,
              "residual_risk_count": 4,
              "failure_count": 0,
              "accepted": false
            },
            "source_checklist": [
              {
                "evidence_key": "native-permission-enforcement",
                "label": "Native enforcement",
                "field": "native_enforcement_count",
                "expected": ">0",
                "actual": 0,
                "status": "blocked",
                "source_accepted": false,
                "next_action": "Collect real target-client or external runtime guard proof."
              },
              {
                "evidence_key": "native-permission-enforcement",
                "label": "Probe failures",
                "field": "failure_count",
                "expected": "==0",
                "actual": 0,
                "status": "pass",
                "source_accepted": false,
                "next_action": "Runtime permission probes must stay clean."
              },
              {
                "evidence_key": "native-permission-enforcement",
                "label": "Installer support",
                "field": "installer_enforcement_ready",
                "expected": "true",
                "actual": true,
                "status": "pass",
                "source_accepted": false,
                "next_action": "Installer enforcement is supporting evidence, not native proof."
              }
            ],
            "source_check_count": 3,
            "source_pass_count": 2,
            "source_blocked_count": 1,
            "submission_state": {
              "status": "missing",
              "path": "evidence/world_class/submissions/native-permission-enforcement.json",
              "artifact_ref_count": 0,
              "attested_real_evidence": false,
              "privacy_contract_satisfied": false,
              "ledger_counts_as_completion": false
            },
            "anti_overclaim": {
              "planned_work_counts_as_evidence": false,
              "metadata_fallback_counts_as_native_enforcement": false,
              "pending_review_counts_as_human_decision": false,
              "local_command_runner_counts_as_provider_model": false
            },
            "next_action": "Integrate a real target-client or external installer runtime guard before claiming native permission enforcement."
          },
          {
            "key": "native-client-telemetry",
            "label": "Native Client Telemetry",
            "category": "external",
            "owner": "Browser/Chrome/IDE/provider client integrator",
            "status": "pending",
            "source_status": "external_required",
            "source_accepted": false,
            "current": "external source events 0; adoption samples 0",
            "objective": "Import production metadata-only events from a real external client into the local drift loop.",
            "runbook": [
              "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
              "Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.",
              "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl",
              "python3 scripts/yao.py skill-atlas --workspace-root .",
              "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
              "Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.",
              "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
            ],
            "provenance_requirements": [
              "real external client source",
              "metadata-only event",
              "local-first import path"
            ],
            "success_checks": [
              "reports/adoption_drift_report.json summary.source_types.external > 0",
              "reports/adoption_drift_report.json summary.adoption_sample_count > 0",
              "reports/skill_os2_audit.json item native-client-telemetry status becomes pass"
            ],
            "evidence_artifacts": [
              "reports/adoption_drift_report.json",
              "reports/adoption_drift_report.md",
              "reports/telemetry_hook_recipes.json",
              "scripts/telemetry_native_host.py",
              "evidence/world_class/intake.schema.json",
              "evidence/world_class/templates/native-client-telemetry.intake.json",
              "reports/world_class_evidence_intake.json",
              "reports/world_class_evidence_intake.md"
            ],
            "privacy_contract": [
              "Telemetry must remain metadata-only and local-first.",
              "Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field."
            ],
            "observed_state": {
              "external_source_events": 0,
              "adoption_sample_count": 0,
              "raw_content_allowed": false,
              "risk_band": "low",
              "accepted": false
            },
            "source_checklist": [
              {
                "evidence_key": "native-client-telemetry",
                "label": "External events",
                "field": "external_source_events",
                "expected": ">0",
                "actual": 0,
                "status": "blocked",
                "source_accepted": false,
                "next_action": "Import at least one metadata-only event from a real client."
              },
              {
                "evidence_key": "native-client-telemetry",
                "label": "Adoption sample",
                "field": "adoption_sample_count",
                "expected": ">0",
                "actual": 0,
                "status": "blocked",
                "source_accepted": false,
                "next_action": "Telemetry must include adoption outcome evidence."
              },
              {
                "evidence_key": "native-client-telemetry",
                "label": "Raw content blocked",
                "field": "raw_content_allowed",
                "expected": "false",
                "actual": false,
                "status": "pass",
                "source_accepted": false,
                "next_action": "Telemetry must stay metadata-only."
              }
            ],
            "source_check_count": 3,
            "source_pass_count": 1,
            "source_blocked_count": 2,
            "submission_state": {
              "status": "missing",
              "path": "evidence/world_class/submissions/native-client-telemetry.json",
              "artifact_ref_count": 0,
              "attested_real_evidence": false,
              "privacy_contract_satisfied": false,
              "ledger_counts_as_completion": false
            },
            "anti_overclaim": {
              "planned_work_counts_as_evidence": false,
              "metadata_fallback_counts_as_native_enforcement": false,
              "pending_review_counts_as_human_decision": false,
              "local_command_runner_counts_as_provider_model": false
            },
            "next_action": "Install a real client against the native host and import production metadata-only events."
          }
        ],
        "source_plan": {
          "json": "reports/world_class_evidence_plan.json",
          "markdown": "reports/world_class_evidence_plan.md",
          "task_count": 4,
          "evidence_requirement_count": 4
        }
      },
      "synthesis_highlights": [
        "Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts.",
        "Borrow a review checkpoint wherever trust matters more than raw speed.",
        "Borrow the discipline of defining what the skill should not own before growing the package."
      ],
      "artifact_design": {
        "design_system": "metric editorial",
        "highlights": [
          "Execution-focused technical artifact with environment assumptions, copyable commands, expected outputs, and side effects made explicit.",
          "Name the working directory and required inputs for commands.",
          "Mark destructive, networked, or external side-effect operations.",
          "Prefer the smallest runnable snippet over broad framework scaffolding."
        ]
      },
      "prompt_quality": {
        "overall_quality_score": 89.0,
        "highlights": [
          "Primary prompt task family: Execution operation.",
          "Complexity: expert — multiple task families plus governance, evaluation, or expert-level constraints",
          "Completeness: 100/100.",
          "Clarity: 85/100."
        ]
      },
      "system_model": {
        "stability": {
          "score": 100,
          "band": "system-ready"
        },
        "highlights": [
          "Stability: system-ready (100/100).",
          "Owned job: Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse.",
          "Leverage: Tune the frontmatter description — Name the recurring job, expected input, output, and strongest non-goal in compact language.",
          "Leverage: Install output self-repair checks — Add only the checks that prevent recurring output mistakes."
        ]
      },
      "metadata": {
        "canonical_format": "agent-skills",
        "targets": [
          "openai",
          "claude",
          "generic",
          "vscode"
        ],
        "maturity_tier": "governed",
        "skill_archetype": "governed",
        "updated_at": "2026-03-31"
      }
    },
    "intent_confidence": {
      "score": 100,
      "band": "high",
      "gate_passed": true,
      "strengths": [
        "The recurring job is concrete enough to anchor the package.",
        "Real input shape is explicit.",
        "The hand-back output is concrete.",
        "Boundary exclusions are already explicit.",
        "Operational constraints are visible."
      ],
      "gaps": [],
      "follow_up_questions": [],
      "anchor_sentence": "Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse. Primary output: A working skill package with lean SKILL.md, aligned agents/interface.yaml, justified references, scripts only when useful, eval evidence, reports, packaging metadata, and clear next iteration recommendations.. Exclusions: one-off writing, translation, explanation, or brainstorming requests that do not need a reusable skill, general code review or debugging unless the user is packaging that workflow as a skill, raw private material that was not intentionally supplied as skill evidence, platform-specific plugin creation when the request is not about an agent skill package.",
      "recommended_action": "Intent is clear enough to package the first routeable version.",
      "context": {
        "job": "Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse.",
        "real_inputs": [
          "rough workflow notes, SOPs, runbooks, prompts, transcripts, documents, or repeated task descriptions",
          "an existing skill directory that needs refactor, evaluation, packaging, or governance hardening",
          "target platform requirements such as OpenAI, Claude, generic Agent Skills, or team distribution",
          "benchmark references, local constraints, desired maturity tier, and review standards"
        ],
        "primary_output": "A working skill package with lean SKILL.md, aligned agents/interface.yaml, justified references, scripts only when useful, eval evidence, reports, packaging metadata, and clear next iteration recommendations.",
        "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
        "exclusions": [
          "one-off writing, translation, explanation, or brainstorming requests that do not need a reusable skill",
          "general code review or debugging unless the user is packaging that workflow as a skill",
          "raw private material that was not intentionally supplied as skill evidence",
          "platform-specific plugin creation when the request is not about an agent skill package"
        ],
        "constraints": [
          "keep SKILL.md lean and route primarily through frontmatter description",
          "put durable guidance in references, executable logic in scripts, and evidence in reports",
          "default to the lightest reliable mode before adding governance weight",
          "preserve portability across OpenAI, Claude, generic, and Agent Skills compatible targets",
          "avoid raw prompt, output, transcript, or private content in telemetry"
        ],
        "standards": [
          "trigger boundaries must be tested with should-trigger and should-not-trigger cases",
          "production and higher maturity work needs output eval, trust, runtime conformance, and Review Studio evidence",
          "governed work needs owner, review cadence, permission approvals, registry metadata, package verification, and install simulation",
          "generated reports should be bilingual or reviewer-friendly when they are user-facing",
          "each new asset must earn its place by reducing ambiguity, risk, or repeated work"
        ],
        "correction": "The 2.0 direction reframes this package from a Meta Skill factory into a Skill OS with Skill IR, compiler contracts, output eval, runtime conformance, trust, registry, Review Studio, Skill Atlas, and telemetry loops.",
        "user_references": [
          "Yao Meta Skill 2.0 upgrade plan",
          "Kami-style white report layout requirements for generated skill reports",
          "local Waza engineering habits for review, design, diagnosis, and implementation discipline"
        ]
      }
    },
    "intent_dialogue": {
      "skill_name": "yao-meta-skill",
      "title": "Yao Meta Skill",
      "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
      "focus": "portability-and-contract",
      "opening_frame": "Let's start from the real work, the result you care about, and the standards that matter here. We can make the structure clearer after that.",
      "reference_note": "If you already have examples you admire, bring them in. We will learn the pattern, not copy the source.",
      "conversation_path": [
        "Start with the user's own words, not package vocabulary.",
        "Reflect the job, output, and non-goals back in one clean sentence.",
        "Only then offer a tiny scaffold if it would help the user move faster."
      ],
      "opening_styles": [
        {
          "label": "温柔陪伴型",
          "best_when": "用户想法还散、还在试探，或者需要先被接住。",
          "message": "我们先不急着把它说成一个很完整的 skill。你就像跟我聊天一样，先说说你最想让它以后稳稳接住哪类重复工作；如果它做得很理想，最后应该交回你一个什么结果。"
        },
        {
          "label": "专业教练型",
          "best_when": "用户目标比较明确，希望被高效带着走。",
          "message": "我们先把这件事讲清楚，再决定 skill 怎么设计。你先告诉我三件事：它要接住的重复任务是什么，别人通常会给它什么材料，最后你希望它交付什么结果。"
        },
        {
          "label": "共创伙伴型",
          "best_when": "用户已经有一些想法，希望一起打磨，不想被填表。",
          "message": "我们把这次当成一次共创。你先给我一个粗糙版本就行，我先帮你看它真正的核心任务是什么，再一起决定边界、结构和接下来最值的一步。"
        }
      ],
      "optional_scaffold": [
        "The repeated job it should reliably handle",
        "The real inputs people will hand to it",
        "The useful output it should hand back",
        "What it should clearly refuse"
      ],
      "questions": [
        {
          "question": "If this skill worked beautifully, what recurring job would it reliably handle for the user every time?",
          "why": "This reveals the real job-to-be-done and gives the package a humane center instead of a guessed prompt shape."
        },
        {
          "question": "When someone reaches for this skill in the real world, what materials will they actually hand to it?",
          "why": "Input shape decides whether references, scripts, or templates are needed."
        },
        {
          "question": "What finished output should it hand back so the user can immediately keep moving?",
          "why": "Outputs should drive the package structure before extra guidance is added."
        },
        {
          "question": "Which nearby requests should this skill politely refuse so the boundary stays clean?",
          "why": "The exclusion list is the fastest route to better trigger quality."
        },
        {
          "question": "What matters most here: speed, consistency, auditability, portability, governance, or tone/style fit?",
          "why": "Constraints decide how much structure, packaging, and review the skill actually needs."
        },
        {
          "question": "Do you already have any references you want this skill to learn from, such as a repo, product, page, workflow, or prompt example?",
          "why": "A good reference can raise the quality bar quickly, but the skill should only borrow patterns and standards, never copy wording or confidential material."
        },
        {
          "question": "Which environments or clients must be able to consume this skill?",
          "why": "This sets the minimum metadata and degradation strategy."
        }
      ],
      "output": {
        "capability_sentence": "Yao Meta Skill should turn a recurring request into a reliable reusable output without widening the boundary unnecessarily.",
        "required_capture": [
          "recurring job",
          "real inputs",
          "required outputs",
          "exclusions",
          "constraints",
          "reference preferences",
          "first evaluation target"
        ],
        "recommended_first_gate": "portability and contract"
      }
    },
    "route_scorecard": {
      "summary": {
        "total_cases": 13,
        "correct_cases": 13,
        "accuracy": 1.0,
        "ambiguous_case_count": 0,
        "margin_warning_threshold": 0.08,
        "misroute_count": 0,
        "no_route_accuracy": 1.0
      },
      "route_stats": {
        "yao-meta-skill": {
          "expected_count": 3,
          "predicted_count": 3,
          "correct_count": 3,
          "precision": 1.0,
          "recall": 1.0,
          "average_margin": 0.611
        },
        "team-frontend-review": {
          "expected_count": 3,
          "predicted_count": 3,
          "correct_count": 3,
          "precision": 1.0,
          "recall": 1.0,
          "average_margin": 0.805
        },
        "governed-incident-command": {
          "expected_count": 3,
          "predicted_count": 3,
          "correct_count": 3,
          "precision": 1.0,
          "recall": 1.0,
          "average_margin": 0.659
        },
        "no_route": {
          "expected_count": 4,
          "predicted_count": 4,
          "correct_count": 4,
          "precision": 1.0,
          "recall": 1.0,
          "average_margin": null
        }
      },
      "confusion_matrix": {
        "yao-meta-skill": {
          "yao-meta-skill": 3,
          "team-frontend-review": 0,
          "governed-incident-command": 0,
          "no_route": 0
        },
        "team-frontend-review": {
          "yao-meta-skill": 0,
          "team-frontend-review": 3,
          "governed-incident-command": 0,
          "no_route": 0
        },
        "governed-incident-command": {
          "yao-meta-skill": 0,
          "team-frontend-review": 0,
          "governed-incident-command": 3,
          "no_route": 0
        },
        "no_route": {
          "yao-meta-skill": 0,
          "team-frontend-review": 0,
          "governed-incident-command": 0,
          "no_route": 4
        }
      },
      "ambiguous_cases": [],
      "misroutes": [],
      "cases": [
        {
          "family": "meta_create",
          "prompt": "Create a reusable skill from this workflow and add evals before sharing it with the team.",
          "expected_route": "yao-meta-skill",
          "predicted_route": "yao-meta-skill",
          "correct": true,
          "margin": 0.741,
          "ambiguous": false,
          "ranked_routes": [
            {
              "name": "yao-meta-skill",
              "score": 0.741,
              "passed_threshold": true,
              "threshold": 0.33,
              "matched_desired_concepts": [
                "eval_optimize",
                "iterate_existing_skill",
                "reuse_package",
                "team_operationalize",
                "transform_workflow"
              ],
              "matched_negative_concepts": []
            },
            {
              "name": "team-frontend-review",
              "score": 0.01,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            },
            {
              "name": "governed-incident-command",
              "score": 0.01,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            }
          ]
        },
        {
          "family": "meta_iterate",
          "prompt": "Refactor this existing skill description, tighten the trigger boundary, and package it for reuse.",
          "expected_route": "yao-meta-skill",
          "predicted_route": "yao-meta-skill",
          "correct": true,
          "margin": 0.535,
          "ambiguous": false,
          "ranked_routes": [
            {
              "name": "yao-meta-skill",
              "score": 0.535,
              "passed_threshold": true,
              "threshold": 0.33,
              "matched_desired_concepts": [
                "eval_optimize",
                "iterate_existing_skill",
                "reuse_package"
              ],
              "matched_negative_concepts": []
            },
            {
              "name": "team-frontend-review",
              "score": 0.011,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            },
            {
              "name": "governed-incident-command",
              "score": 0.01,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            }
          ]
        },
        {
          "family": "meta_operationalize",
          "prompt": "Turn these prompts, notes, and transcripts into a maintained skill package with references and scripts.",
          "expected_route": "yao-meta-skill",
          "predicted_route": "yao-meta-skill",
          "correct": true,
          "margin": 0.558,
          "ambiguous": false,
          "ranked_routes": [
            {
              "name": "yao-meta-skill",
              "score": 0.558,
              "passed_threshold": true,
              "threshold": 0.33,
              "matched_desired_concepts": [
                "build_skill",
                "reuse_package"
              ],
              "matched_negative_concepts": []
            },
            {
              "name": "governed-incident-command",
              "score": 0.269,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [
                "governed_workflow"
              ],
              "matched_negative_concepts": []
            },
            {
              "name": "team-frontend-review",
              "score": 0.011,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            }
          ]
        },
        {
          "family": "frontend_premerge",
          "prompt": "Run a pre-merge frontend review for keyboard navigation issues and unsafe rendering.",
          "expected_route": "team-frontend-review",
          "predicted_route": "team-frontend-review",
          "correct": true,
          "margin": 0.893,
          "ambiguous": false,
          "ranked_routes": [
            {
              "name": "team-frontend-review",
              "score": 0.893,
              "passed_threshold": true,
              "threshold": 0.48,
              "matched_desired_concepts": [
                "accessibility",
                "frontend_scope",
                "review_frontend",
                "ui_security",
                "ux_regression"
              ],
              "matched_negative_concepts": []
            },
            {
              "name": "yao-meta-skill",
              "score": 0.018,
              "passed_threshold": false,
              "threshold": 0.33,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            },
            {
              "name": "governed-incident-command",
              "score": 0.012,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            }
          ]
        },
        {
          "family": "frontend_states",
          "prompt": "Run a pre-merge frontend review on this React diff for missing empty states, form handling, and UX regressions.",
          "expected_route": "team-frontend-review",
          "predicted_route": "team-frontend-review",
          "correct": true,
          "margin": 0.704,
          "ambiguous": false,
          "ranked_routes": [
            {
              "name": "team-frontend-review",
              "score": 0.704,
              "passed_threshold": true,
              "threshold": 0.48,
              "matched_desired_concepts": [
                "frontend_scope",
                "review_frontend",
                "ui_security",
                "ux_regression"
              ],
              "matched_negative_concepts": []
            },
            {
              "name": "yao-meta-skill",
              "score": 0.013,
              "passed_threshold": false,
              "threshold": 0.33,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            },
            {
              "name": "governed-incident-command",
              "score": 0.008,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            }
          ]
        },
        {
          "family": "frontend_a11y",
          "prompt": "Review React components for a11y regressions, unsafe rendering, and UI behavior before merge.",
          "expected_route": "team-frontend-review",
          "predicted_route": "team-frontend-review",
          "correct": true,
          "margin": 0.819,
          "ambiguous": false,
          "ranked_routes": [
            {
              "name": "team-frontend-review",
              "score": 0.819,
              "passed_threshold": true,
              "threshold": 0.48,
              "matched_desired_concepts": [
                "accessibility",
                "frontend_scope",
                "review_frontend",
                "ui_security"
              ],
              "matched_negative_concepts": []
            },
            {
              "name": "yao-meta-skill",
              "score": 0.012,
              "passed_threshold": false,
              "threshold": 0.33,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            },
            {
              "name": "governed-incident-command",
              "score": 0.006,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            }
          ]
        },
        {
          "family": "incident_packet",
          "prompt": "Build a governed incident command packet from alerts, responder notes, incident communication needs, and severity findings.",
          "expected_route": "governed-incident-command",
          "predicted_route": "governed-incident-command",
          "correct": true,
          "margin": 1.0,
          "ambiguous": false,
          "ranked_routes": [
            {
              "name": "governed-incident-command",
              "score": 1.0,
              "passed_threshold": true,
              "threshold": 0.48,
              "matched_desired_concepts": [
                "comms_and_owners",
                "governed_workflow",
                "severity_assessment"
              ],
              "matched_negative_concepts": []
            },
            {
              "name": "yao-meta-skill",
              "score": 0.021,
              "passed_threshold": false,
              "threshold": 0.33,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            },
            {
              "name": "team-frontend-review",
              "score": 0.011,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            }
          ]
        },
        {
          "family": "incident_severity",
          "prompt": "Run severity assessment and package incident communication from this outage review.",
          "expected_route": "governed-incident-command",
          "predicted_route": "governed-incident-command",
          "correct": true,
          "margin": 0.805,
          "ambiguous": false,
          "ranked_routes": [
            {
              "name": "governed-incident-command",
              "score": 0.805,
              "passed_threshold": true,
              "threshold": 0.48,
              "matched_desired_concepts": [
                "comms_and_owners",
                "severity_assessment"
              ],
              "matched_negative_concepts": []
            },
            {
              "name": "yao-meta-skill",
              "score": 0.189,
              "passed_threshold": false,
              "threshold": 0.33,
              "matched_desired_concepts": [
                "reuse_package"
              ],
              "matched_negative_concepts": []
            },
            {
              "name": "team-frontend-review",
              "score": 0.022,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            }
          ]
        },
        {
          "family": "incident_governed_workflow",
          "prompt": "Standardize this incident review into a reusable governed workflow with owner actions.",
          "expected_route": "governed-incident-command",
          "predicted_route": "governed-incident-command",
          "correct": true,
          "margin": 0.172,
          "ambiguous": false,
          "ranked_routes": [
            {
              "name": "governed-incident-command",
              "score": 0.62,
              "passed_threshold": true,
              "threshold": 0.48,
              "matched_desired_concepts": [
                "comms_and_owners",
                "governed_workflow"
              ],
              "matched_negative_concepts": []
            },
            {
              "name": "yao-meta-skill",
              "score": 0.448,
              "passed_threshold": true,
              "threshold": 0.33,
              "matched_desired_concepts": [
                "reuse_package",
                "team_operationalize",
                "transform_workflow"
              ],
              "matched_negative_concepts": []
            },
            {
              "name": "team-frontend-review",
              "score": 0.013,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            }
          ]
        },
        {
          "family": "no_route_explain",
          "prompt": "Explain keyboard accessibility basics in plain English.",
          "expected_route": "no_route",
          "predicted_route": "no_route",
          "correct": true,
          "margin": null,
          "ambiguous": false,
          "ranked_routes": [
            {
              "name": "team-frontend-review",
              "score": 0.195,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [
                "accessibility"
              ],
              "matched_negative_concepts": []
            },
            {
              "name": "yao-meta-skill",
              "score": 0.0,
              "passed_threshold": false,
              "threshold": 0.33,
              "matched_desired_concepts": [],
              "matched_negative_concepts": [
                "explain_only"
              ]
            },
            {
              "name": "governed-incident-command",
              "score": 0.0,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            }
          ]
        },
        {
          "family": "no_route_build",
          "prompt": "Build a React form page with loading and empty states.",
          "expected_route": "no_route",
          "predicted_route": "no_route",
          "correct": true,
          "margin": null,
          "ambiguous": false,
          "ranked_routes": [
            {
              "name": "yao-meta-skill",
              "score": 0.016,
              "passed_threshold": false,
              "threshold": 0.33,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            },
            {
              "name": "governed-incident-command",
              "score": 0.008,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            },
            {
              "name": "team-frontend-review",
              "score": 0.0,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [
                "frontend_scope"
              ],
              "matched_negative_concepts": [
                "build_ui"
              ]
            }
          ]
        },
        {
          "family": "no_route_single_update",
          "prompt": "Write one short outage update for customers from these notes.",
          "expected_route": "no_route",
          "predicted_route": "no_route",
          "correct": true,
          "margin": null,
          "ambiguous": false,
          "ranked_routes": [
            {
              "name": "yao-meta-skill",
              "score": 0.024,
              "passed_threshold": false,
              "threshold": 0.33,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            },
            {
              "name": "team-frontend-review",
              "score": 0.008,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            },
            {
              "name": "governed-incident-command",
              "score": 0.0,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            }
          ]
        },
        {
          "family": "no_route_document_only",
          "prompt": "Summarize this workflow and keep it as documentation only.",
          "expected_route": "no_route",
          "predicted_route": "no_route",
          "correct": true,
          "margin": null,
          "ambiguous": false,
          "ranked_routes": [
            {
              "name": "governed-incident-command",
              "score": 0.01,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            },
            {
              "name": "team-frontend-review",
              "score": 0.009,
              "passed_threshold": false,
              "threshold": 0.48,
              "matched_desired_concepts": [],
              "matched_negative_concepts": []
            },
            {
              "name": "yao-meta-skill",
              "score": 0.0,
              "passed_threshold": false,
              "threshold": 0.33,
              "matched_desired_concepts": [
                "transform_workflow"
              ],
              "matched_negative_concepts": [
                "no_build_directive",
                "summarize_only"
              ]
            }
          ]
        }
      ]
    },
    "output_quality": {
      "ok": true,
      "cases": "evals/output/cases.jsonl",
      "summary": {
        "case_count": 5,
        "file_backed_case_count": 1,
        "near_neighbor_case_count": 1,
        "boundary_case_count": 1,
        "baseline_pass_rate": 0.0,
        "with_skill_pass_rate": 100.0,
        "delta": 100.0,
        "regression_count": 0,
        "gate_pass": true,
        "failure_taxonomy": [],
        "blind_pair_count": 5
      },
      "results": [
        {
          "id": "skill-package-contract",
          "prompt": "Turn this repeated workflow into a reusable team skill package.",
          "input_files": [],
          "metadata": {},
          "baseline": {
            "score": 0.0,
            "passed_count": 0,
            "failed_count": 4,
            "checks": [
              {
                "id": "has-entrypoint",
                "description": "Output names the routeable Skill entrypoint.",
                "weight": 1.0,
                "failure_type": "missing_entrypoint",
                "passed": false,
                "missing": [
                  "SKILL.md"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-interface",
                "description": "Output includes neutral interface metadata.",
                "weight": 1.0,
                "failure_type": "missing_interface",
                "passed": false,
                "missing": [
                  "agents/interface.yaml"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-report",
                "description": "Output points reviewer to generated overview report.",
                "weight": 1.0,
                "failure_type": "missing_review_artifact",
                "passed": false,
                "missing": [
                  "reports/skill-overview.html"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-resource-boundary",
                "description": "Output preserves entrypoint/resource separation.",
                "weight": 1.0,
                "failure_type": "resource_boundary",
                "passed": false,
                "missing": [
                  "references/",
                  "scripts/",
                  "reports/"
                ],
                "present_forbidden": []
              }
            ],
            "failed": [
              {
                "id": "has-entrypoint",
                "description": "Output names the routeable Skill entrypoint.",
                "weight": 1.0,
                "failure_type": "missing_entrypoint",
                "passed": false,
                "missing": [
                  "SKILL.md"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-interface",
                "description": "Output includes neutral interface metadata.",
                "weight": 1.0,
                "failure_type": "missing_interface",
                "passed": false,
                "missing": [
                  "agents/interface.yaml"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-report",
                "description": "Output points reviewer to generated overview report.",
                "weight": 1.0,
                "failure_type": "missing_review_artifact",
                "passed": false,
                "missing": [
                  "reports/skill-overview.html"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-resource-boundary",
                "description": "Output preserves entrypoint/resource separation.",
                "weight": 1.0,
                "failure_type": "resource_boundary",
                "passed": false,
                "missing": [
                  "references/",
                  "scripts/",
                  "reports/"
                ],
                "present_forbidden": []
              }
            ]
          },
          "with_skill": {
            "score": 100.0,
            "passed_count": 4,
            "failed_count": 0,
            "checks": [
              {
                "id": "has-entrypoint",
                "description": "Output names the routeable Skill entrypoint.",
                "weight": 1.0,
                "failure_type": "missing_entrypoint",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              },
              {
                "id": "has-interface",
                "description": "Output includes neutral interface metadata.",
                "weight": 1.0,
                "failure_type": "missing_interface",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              },
              {
                "id": "has-report",
                "description": "Output points reviewer to generated overview report.",
                "weight": 1.0,
                "failure_type": "missing_review_artifact",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              },
              {
                "id": "has-resource-boundary",
                "description": "Output preserves entrypoint/resource separation.",
                "weight": 1.0,
                "failure_type": "resource_boundary",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              }
            ],
            "failed": []
          },
          "delta": 100.0,
          "winner": "with_skill",
          "failure_taxonomy": []
        },
        {
          "id": "output-eval-expectation",
          "prompt": "Upgrade this production skill so we know whether the generated output is better than baseline.",
          "input_files": [],
          "metadata": {},
          "baseline": {
            "score": 0.0,
            "passed_count": 0,
            "failed_count": 4,
            "checks": [
              {
                "id": "has-baseline-comparison",
                "description": "Output explicitly compares with-skill and baseline outputs.",
                "weight": 1.0,
                "failure_type": "missing_baseline_delta",
                "passed": false,
                "missing": [
                  "with-skill",
                  "baseline"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-assertion-grading",
                "description": "Output includes objective assertion grading.",
                "weight": 1.0,
                "failure_type": "missing_assertions",
                "passed": false,
                "missing": [
                  "assertion grading"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-scorecard",
                "description": "Output produces a scorecard report path.",
                "weight": 1.0,
                "failure_type": "missing_scorecard",
                "passed": false,
                "missing": [
                  "reports/output_quality_scorecard.md"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-failure-taxonomy",
                "description": "Output records failure taxonomy.",
                "weight": 1.0,
                "failure_type": "missing_failure_taxonomy",
                "passed": false,
                "missing": [
                  "failure taxonomy"
                ],
                "present_forbidden": []
              }
            ],
            "failed": [
              {
                "id": "has-baseline-comparison",
                "description": "Output explicitly compares with-skill and baseline outputs.",
                "weight": 1.0,
                "failure_type": "missing_baseline_delta",
                "passed": false,
                "missing": [
                  "with-skill",
                  "baseline"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-assertion-grading",
                "description": "Output includes objective assertion grading.",
                "weight": 1.0,
                "failure_type": "missing_assertions",
                "passed": false,
                "missing": [
                  "assertion grading"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-scorecard",
                "description": "Output produces a scorecard report path.",
                "weight": 1.0,
                "failure_type": "missing_scorecard",
                "passed": false,
                "missing": [
                  "reports/output_quality_scorecard.md"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-failure-taxonomy",
                "description": "Output records failure taxonomy.",
                "weight": 1.0,
                "failure_type": "missing_failure_taxonomy",
                "passed": false,
                "missing": [
                  "failure taxonomy"
                ],
                "present_forbidden": []
              }
            ]
          },
          "with_skill": {
            "score": 100.0,
            "passed_count": 4,
            "failed_count": 0,
            "checks": [
              {
                "id": "has-baseline-comparison",
                "description": "Output explicitly compares with-skill and baseline outputs.",
                "weight": 1.0,
                "failure_type": "missing_baseline_delta",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              },
              {
                "id": "has-assertion-grading",
                "description": "Output includes objective assertion grading.",
                "weight": 1.0,
                "failure_type": "missing_assertions",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              },
              {
                "id": "has-scorecard",
                "description": "Output produces a scorecard report path.",
                "weight": 1.0,
                "failure_type": "missing_scorecard",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              },
              {
                "id": "has-failure-taxonomy",
                "description": "Output records failure taxonomy.",
                "weight": 1.0,
                "failure_type": "missing_failure_taxonomy",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              }
            ],
            "failed": []
          },
          "delta": 100.0,
          "winner": "with_skill",
          "failure_taxonomy": []
        },
        {
          "id": "ir-before-packaging",
          "prompt": "Package this skill for OpenAI, Claude, Agent Skills, and generic targets.",
          "input_files": [],
          "metadata": {},
          "baseline": {
            "score": 0.0,
            "passed_count": 0,
            "failed_count": 4,
            "checks": [
              {
                "id": "has-ir-first",
                "description": "Output requires Skill IR before packaging.",
                "weight": 1.0,
                "failure_type": "missing_ir",
                "passed": false,
                "missing": [
                  "Skill IR first"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-core-ir-fields",
                "description": "Output lists core IR contract fields.",
                "weight": 1.0,
                "failure_type": "incomplete_ir_contract",
                "passed": false,
                "missing": [
                  "job_to_be_done",
                  "trigger_surface",
                  "eval_plan",
                  "governance"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-targets",
                "description": "Output names requested runtime targets.",
                "weight": 1.0,
                "failure_type": "missing_targets",
                "passed": false,
                "missing": [
                  "OpenAI",
                  "Claude",
                  "Agent Skills",
                  "generic"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-semantic-preservation",
                "description": "Output says targets must preserve the capability contract.",
                "weight": 1.0,
                "failure_type": "semantic_drift",
                "passed": false,
                "missing": [
                  "preserve the same capability contract"
                ],
                "present_forbidden": []
              }
            ],
            "failed": [
              {
                "id": "has-ir-first",
                "description": "Output requires Skill IR before packaging.",
                "weight": 1.0,
                "failure_type": "missing_ir",
                "passed": false,
                "missing": [
                  "Skill IR first"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-core-ir-fields",
                "description": "Output lists core IR contract fields.",
                "weight": 1.0,
                "failure_type": "incomplete_ir_contract",
                "passed": false,
                "missing": [
                  "job_to_be_done",
                  "trigger_surface",
                  "eval_plan",
                  "governance"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-targets",
                "description": "Output names requested runtime targets.",
                "weight": 1.0,
                "failure_type": "missing_targets",
                "passed": false,
                "missing": [
                  "OpenAI",
                  "Claude",
                  "Agent Skills",
                  "generic"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-semantic-preservation",
                "description": "Output says targets must preserve the capability contract.",
                "weight": 1.0,
                "failure_type": "semantic_drift",
                "passed": false,
                "missing": [
                  "preserve the same capability contract"
                ],
                "present_forbidden": []
              }
            ]
          },
          "with_skill": {
            "score": 100.0,
            "passed_count": 4,
            "failed_count": 0,
            "checks": [
              {
                "id": "has-ir-first",
                "description": "Output requires Skill IR before packaging.",
                "weight": 1.0,
                "failure_type": "missing_ir",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              },
              {
                "id": "has-core-ir-fields",
                "description": "Output lists core IR contract fields.",
                "weight": 1.0,
                "failure_type": "incomplete_ir_contract",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              },
              {
                "id": "has-targets",
                "description": "Output names requested runtime targets.",
                "weight": 1.0,
                "failure_type": "missing_targets",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              },
              {
                "id": "has-semantic-preservation",
                "description": "Output says targets must preserve the capability contract.",
                "weight": 1.0,
                "failure_type": "semantic_drift",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              }
            ],
            "failed": []
          },
          "delta": 100.0,
          "winner": "with_skill",
          "failure_taxonomy": []
        },
        {
          "id": "near-neighbor-boundary",
          "prompt": "I only need a one-off summary of these notes, not a reusable process.",
          "input_files": [],
          "metadata": {
            "case_type": "near_neighbor",
            "tier": "production"
          },
          "baseline": {
            "score": 0.0,
            "passed_count": 0,
            "failed_count": 3,
            "checks": [
              {
                "id": "declines-skill",
                "description": "Output refuses unnecessary skill creation for one-off work.",
                "weight": 1.0,
                "failure_type": "over_trigger",
                "passed": false,
                "missing": [
                  "Do not create a skill"
                ],
                "present_forbidden": []
              },
              {
                "id": "names-near-neighbor",
                "description": "Output labels the request as near-neighbor instead of owned work.",
                "weight": 1.0,
                "failure_type": "missing_boundary_language",
                "passed": false,
                "missing": [
                  "near-neighbor"
                ],
                "present_forbidden": []
              },
              {
                "id": "requires-reuse-signal",
                "description": "Output asks for repeat-use evidence before packaging.",
                "weight": 1.0,
                "failure_type": "missing_reuse_gate",
                "passed": false,
                "missing": [
                  "repeated use",
                  "reusable output contract"
                ],
                "present_forbidden": []
              }
            ],
            "failed": [
              {
                "id": "declines-skill",
                "description": "Output refuses unnecessary skill creation for one-off work.",
                "weight": 1.0,
                "failure_type": "over_trigger",
                "passed": false,
                "missing": [
                  "Do not create a skill"
                ],
                "present_forbidden": []
              },
              {
                "id": "names-near-neighbor",
                "description": "Output labels the request as near-neighbor instead of owned work.",
                "weight": 1.0,
                "failure_type": "missing_boundary_language",
                "passed": false,
                "missing": [
                  "near-neighbor"
                ],
                "present_forbidden": []
              },
              {
                "id": "requires-reuse-signal",
                "description": "Output asks for repeat-use evidence before packaging.",
                "weight": 1.0,
                "failure_type": "missing_reuse_gate",
                "passed": false,
                "missing": [
                  "repeated use",
                  "reusable output contract"
                ],
                "present_forbidden": []
              }
            ]
          },
          "with_skill": {
            "score": 100.0,
            "passed_count": 3,
            "failed_count": 0,
            "checks": [
              {
                "id": "declines-skill",
                "description": "Output refuses unnecessary skill creation for one-off work.",
                "weight": 1.0,
                "failure_type": "over_trigger",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              },
              {
                "id": "names-near-neighbor",
                "description": "Output labels the request as near-neighbor instead of owned work.",
                "weight": 1.0,
                "failure_type": "missing_boundary_language",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              },
              {
                "id": "requires-reuse-signal",
                "description": "Output asks for repeat-use evidence before packaging.",
                "weight": 1.0,
                "failure_type": "missing_reuse_gate",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              }
            ],
            "failed": []
          },
          "delta": 100.0,
          "winner": "with_skill",
          "failure_taxonomy": []
        },
        {
          "id": "file-backed-governed-package",
          "prompt": "Turn the attached release brief source into a governed skill package.",
          "input_files": [
            "fixtures/release-brief-source.md"
          ],
          "metadata": {
            "case_type": "boundary",
            "tier": "governed"
          },
          "baseline": {
            "score": 0.0,
            "passed_count": 0,
            "failed_count": 5,
            "checks": [
              {
                "id": "uses-file-backed-evidence",
                "description": "Output names file-backed source evidence.",
                "weight": 1.0,
                "failure_type": "missing_file_fixture",
                "passed": false,
                "missing": [
                  "file-backed fixture",
                  "input_files"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-governance",
                "description": "Output preserves governed ownership metadata.",
                "weight": 1.0,
                "failure_type": "missing_governance",
                "passed": false,
                "missing": [
                  "review cadence"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-output-contract",
                "description": "Output preserves output and rollback boundaries.",
                "weight": 1.0,
                "failure_type": "missing_contract_boundary",
                "passed": false,
                "missing": [
                  "output contract",
                  "rollback boundary"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-trust-and-scorecard",
                "description": "Output requires trust and output scorecard artifacts.",
                "weight": 1.0,
                "failure_type": "missing_release_evidence",
                "passed": false,
                "missing": [
                  "trust report",
                  "reports/output_quality_scorecard.md"
                ],
                "present_forbidden": []
              },
              {
                "id": "does-not-invent-evidence",
                "description": "Output forbids invented launch evidence.",
                "weight": 1.0,
                "failure_type": "invented_evidence",
                "passed": false,
                "missing": [
                  "missing evidence"
                ],
                "present_forbidden": []
              }
            ],
            "failed": [
              {
                "id": "uses-file-backed-evidence",
                "description": "Output names file-backed source evidence.",
                "weight": 1.0,
                "failure_type": "missing_file_fixture",
                "passed": false,
                "missing": [
                  "file-backed fixture",
                  "input_files"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-governance",
                "description": "Output preserves governed ownership metadata.",
                "weight": 1.0,
                "failure_type": "missing_governance",
                "passed": false,
                "missing": [
                  "review cadence"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-output-contract",
                "description": "Output preserves output and rollback boundaries.",
                "weight": 1.0,
                "failure_type": "missing_contract_boundary",
                "passed": false,
                "missing": [
                  "output contract",
                  "rollback boundary"
                ],
                "present_forbidden": []
              },
              {
                "id": "has-trust-and-scorecard",
                "description": "Output requires trust and output scorecard artifacts.",
                "weight": 1.0,
                "failure_type": "missing_release_evidence",
                "passed": false,
                "missing": [
                  "trust report",
                  "reports/output_quality_scorecard.md"
                ],
                "present_forbidden": []
              },
              {
                "id": "does-not-invent-evidence",
                "description": "Output forbids invented launch evidence.",
                "weight": 1.0,
                "failure_type": "invented_evidence",
                "passed": false,
                "missing": [
                  "missing evidence"
                ],
                "present_forbidden": []
              }
            ]
          },
          "with_skill": {
            "score": 100.0,
            "passed_count": 5,
            "failed_count": 0,
            "checks": [
              {
                "id": "uses-file-backed-evidence",
                "description": "Output names file-backed source evidence.",
                "weight": 1.0,
                "failure_type": "missing_file_fixture",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              },
              {
                "id": "has-governance",
                "description": "Output preserves governed ownership metadata.",
                "weight": 1.0,
                "failure_type": "missing_governance",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              },
              {
                "id": "has-output-contract",
                "description": "Output preserves output and rollback boundaries.",
                "weight": 1.0,
                "failure_type": "missing_contract_boundary",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              },
              {
                "id": "has-trust-and-scorecard",
                "description": "Output requires trust and output scorecard artifacts.",
                "weight": 1.0,
                "failure_type": "missing_release_evidence",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              },
              {
                "id": "does-not-invent-evidence",
                "description": "Output forbids invented launch evidence.",
                "weight": 1.0,
                "failure_type": "invented_evidence",
                "passed": true,
                "missing": [],
                "present_forbidden": []
              }
            ],
            "failed": []
          },
          "delta": 100.0,
          "winner": "with_skill",
          "failure_taxonomy": []
        }
      ],
      "failures": [],
      "blind_review": {
        "pack": "reports/output_blind_review_pack.json",
        "answer_key": "reports/output_blind_answer_key.json",
        "pair_count": 5
      },
      "artifacts": {
        "json": "reports/output_quality_scorecard.json",
        "markdown": "reports/output_quality_scorecard.md",
        "blind_review_pack_json": "reports/output_blind_review_pack.json",
        "blind_review_pack_md": "reports/output_blind_review_pack.md",
        "blind_answer_key_json": "reports/output_blind_answer_key.json"
      }
    },
    "output_execution": {
      "schema_version": "1.0",
      "ok": true,
      "cases": "evals/output/cases.jsonl",
      "runner": {
        "mode": "command",
        "command": [
          "python3",
          "scripts/local_output_eval_runner.py"
        ],
        "timeout_seconds": 30.0
      },
      "summary": {
        "case_count": 5,
        "variant_run_count": 10,
        "command_executed_count": 10,
        "model_executed_count": 0,
        "recorded_fixture_count": 0,
        "timing_observed_count": 10,
        "token_observed_count": 0,
        "token_estimated_count": 10,
        "baseline_pass_rate": 0.0,
        "with_skill_pass_rate": 100.0,
        "delta": 100.0,
        "regression_count": 0,
        "failure_count": 0,
        "gate_pass": true
      },
      "runs": [
        {
          "case_id": "skill-package-contract",
          "variant": "baseline",
          "status": "pass",
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
          "duration_ms": 42.05,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
            "input_tokens": 16,
            "output_tokens": 17,
            "total_tokens": 33,
            "estimated": true
          },
          "score": 0.0,
          "passed_count": 0,
          "failed_count": 4,
          "failed_assertions": [
            "has-entrypoint",
            "has-interface",
            "has-report",
            "has-resource-boundary"
          ],
          "output_sha256": "ece26a6edbbbea86a93faaf9f0eadf88efbae12f1c3ad81da9376cf2a889d101",
          "failure": ""
        },
        {
          "case_id": "skill-package-contract",
          "variant": "with_skill",
          "status": "pass",
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
          "duration_ms": 36.82,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
            "input_tokens": 16,
            "output_tokens": 57,
            "total_tokens": 73,
            "estimated": true
          },
          "score": 100.0,
          "passed_count": 4,
          "failed_count": 0,
          "failed_assertions": [],
          "output_sha256": "8bee0131e17fdbe87e48457130ac6aeaa55ea30c919a45e77109852609f33eba",
          "failure": ""
        },
        {
          "case_id": "output-eval-expectation",
          "variant": "baseline",
          "status": "pass",
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
          "duration_ms": 38.87,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
            "input_tokens": 24,
            "output_tokens": 12,
            "total_tokens": 36,
            "estimated": true
          },
          "score": 0.0,
          "passed_count": 0,
          "failed_count": 4,
          "failed_assertions": [
            "has-baseline-comparison",
            "has-assertion-grading",
            "has-scorecard",
            "has-failure-taxonomy"
          ],
          "output_sha256": "98fa332fb493b5dc14656a9d65a6c0a9c25ff61a14b71b647aad89cbdbd3ab35",
          "failure": ""
        },
        {
          "case_id": "output-eval-expectation",
          "variant": "with_skill",
          "status": "pass",
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
          "duration_ms": 35.73,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
            "input_tokens": 24,
            "output_tokens": 56,
            "total_tokens": 80,
            "estimated": true
          },
          "score": 100.0,
          "passed_count": 4,
          "failed_count": 0,
          "failed_assertions": [],
          "output_sha256": "8efdbfefa6a36603682b7063b1753f9f939b3810c082d29686e297906d9f51c8",
          "failure": ""
        },
        {
          "case_id": "ir-before-packaging",
          "variant": "baseline",
          "status": "pass",
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
          "duration_ms": 35.53,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
            "input_tokens": 18,
            "output_tokens": 15,
            "total_tokens": 33,
            "estimated": true
          },
          "score": 0.0,
          "passed_count": 0,
          "failed_count": 4,
          "failed_assertions": [
            "has-ir-first",
            "has-core-ir-fields",
            "has-targets",
            "has-semantic-preservation"
          ],
          "output_sha256": "07a4aa9ee9e48341d4b84d5cb9b6414901aa2c8841340d67447e187240c6c4c2",
          "failure": ""
        },
        {
          "case_id": "ir-before-packaging",
          "variant": "with_skill",
          "status": "pass",
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
          "duration_ms": 48.73,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
            "input_tokens": 18,
            "output_tokens": 62,
            "total_tokens": 80,
            "estimated": true
          },
          "score": 100.0,
          "passed_count": 4,
          "failed_count": 0,
          "failed_assertions": [],
          "output_sha256": "707fde419b3d61e921561b1c4a8523e1f7b53b1acd5758a47ce21d9ed711fde0",
          "failure": ""
        },
        {
          "case_id": "near-neighbor-boundary",
          "variant": "baseline",
          "status": "pass",
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
          "duration_ms": 65.97,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
            "input_tokens": 17,
            "output_tokens": 19,
            "total_tokens": 36,
            "estimated": true
          },
          "score": 0.0,
          "passed_count": 0,
          "failed_count": 3,
          "failed_assertions": [
            "declines-skill",
            "names-near-neighbor",
            "requires-reuse-signal"
          ],
          "output_sha256": "648ebaa6e09486d05f33fa6639dc973b029d115158588fd192efbe15ccaaeac4",
          "failure": ""
        },
        {
          "case_id": "near-neighbor-boundary",
          "variant": "with_skill",
          "status": "pass",
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
          "duration_ms": 60.32,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
            "input_tokens": 17,
            "output_tokens": 48,
            "total_tokens": 65,
            "estimated": true
          },
          "score": 100.0,
          "passed_count": 3,
          "failed_count": 0,
          "failed_assertions": [],
          "output_sha256": "17a3a5286ad573dea86e51f82c04b596babaecb92cde8879f09e7c519205e2e1",
          "failure": ""
        },
        {
          "case_id": "file-backed-governed-package",
          "variant": "baseline",
          "status": "pass",
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
          "duration_ms": 50.55,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
            "input_tokens": 17,
            "output_tokens": 20,
            "total_tokens": 37,
            "estimated": true
          },
          "score": 0.0,
          "passed_count": 0,
          "failed_count": 5,
          "failed_assertions": [
            "uses-file-backed-evidence",
            "has-governance",
            "has-output-contract",
            "has-trust-and-scorecard",
            "does-not-invent-evidence"
          ],
          "output_sha256": "6e5827219459dee34143e4f11663415db80c3111291f75fb6c2115c7bda4cf30",
          "failure": ""
        },
        {
          "case_id": "file-backed-governed-package",
          "variant": "with_skill",
          "status": "pass",
          "execution_mode": "command",
          "model_executed": false,
          "command_executed": true,
          "duration_ms": 44.37,
          "provider": "local-output-eval-runner",
          "model": "",
          "usage": {
            "input_tokens": 17,
            "output_tokens": 81,
            "total_tokens": 98,
            "estimated": true
          },
          "score": 100.0,
          "passed_count": 5,
          "failed_count": 0,
          "failed_assertions": [],
          "output_sha256": "bcfdf036666d406abbc945fc42b93eb74d7074118893e540253c7d8715baad73",
          "failure": ""
        }
      ],
      "failures": [],
      "artifacts": {
        "json": "reports/output_execution_runs.json",
        "markdown": "reports/output_execution_runs.md"
      }
    },
    "output_blind_review": {
      "schema_version": "1.0",
      "seed": "yao-output-eval-blind-v1",
      "summary": {
        "pair_count": 5,
        "answer_key_separate": true,
        "with_skill_hidden_count": 5
      },
      "pairs": [
        {
          "case_id": "skill-package-contract",
          "prompt": "Turn this repeated workflow into a reusable team skill package.",
          "input_files": [],
          "metadata": {},
          "review_instruction": "Pick A or B based only on the rubric. Do not infer which output came from the skill.",
          "rubric": [
            {
              "id": "has-entrypoint",
              "description": "Output names the routeable Skill entrypoint.",
              "weight": 1.0
            },
            {
              "id": "has-interface",
              "description": "Output includes neutral interface metadata.",
              "weight": 1.0
            },
            {
              "id": "has-report",
              "description": "Output points reviewer to generated overview report.",
              "weight": 1.0
            },
            {
              "id": "has-resource-boundary",
              "description": "Output preserves entrypoint/resource separation.",
              "weight": 1.0
            }
          ],
          "variant_a": {
            "blind_id": "skill-package-contract:A",
            "output": "Create a routeable SKILL.md, agents/interface.yaml, reports/skill-overview.html, and a focused eval plan. Keep the root entrypoint lean, move durable guidance into references/, scripts into scripts/, and evidence into reports/."
          },
          "variant_b": {
            "blind_id": "skill-package-contract:B",
            "output": "I can write a prompt for that workflow and include a short checklist."
          }
        },
        {
          "case_id": "output-eval-expectation",
          "prompt": "Upgrade this production skill so we know whether the generated output is better than baseline.",
          "input_files": [],
          "metadata": {},
          "review_instruction": "Pick A or B based only on the rubric. Do not infer which output came from the skill.",
          "rubric": [
            {
              "id": "has-baseline-comparison",
              "description": "Output explicitly compares with-skill and baseline outputs.",
              "weight": 1.0
            },
            {
              "id": "has-assertion-grading",
              "description": "Output includes objective assertion grading.",
              "weight": 1.0
            },
            {
              "id": "has-scorecard",
              "description": "Output produces a scorecard report path.",
              "weight": 1.0
            },
            {
              "id": "has-failure-taxonomy",
              "description": "Output records failure taxonomy.",
              "weight": 1.0
            }
          ],
          "variant_a": {
            "blind_id": "output-eval-expectation:A",
            "output": "Add Output Eval Lab cases with baseline_output and with_skill_output, run assertion grading, report with-skill vs baseline pass-rate delta, and record failure taxonomy plus next fixes in reports/output_quality_scorecard.md."
          },
          "variant_b": {
            "blind_id": "output-eval-expectation:B",
            "output": "Add more examples and run the trigger eval again."
          }
        },
        {
          "case_id": "ir-before-packaging",
          "prompt": "Package this skill for OpenAI, Claude, Agent Skills, and generic targets.",
          "input_files": [],
          "metadata": {},
          "review_instruction": "Pick A or B based only on the rubric. Do not infer which output came from the skill.",
          "rubric": [
            {
              "id": "has-ir-first",
              "description": "Output requires Skill IR before packaging.",
              "weight": 1.0
            },
            {
              "id": "has-core-ir-fields",
              "description": "Output lists core IR contract fields.",
              "weight": 1.0
            },
            {
              "id": "has-targets",
              "description": "Output names requested runtime targets.",
              "weight": 1.0
            },
            {
              "id": "has-semantic-preservation",
              "description": "Output says targets must preserve the capability contract.",
              "weight": 1.0
            }
          ],
          "variant_a": {
            "blind_id": "ir-before-packaging:A",
            "output": "Export folders for each platform and adjust files as needed."
          },
          "variant_b": {
            "blind_id": "ir-before-packaging:B",
            "output": "Export Skill IR first with job_to_be_done, trigger_surface, workflow, resources, eval_plan, risk, and governance. Then compile or package targets from the IR so OpenAI, Claude, Agent Skills, and generic packages preserve the same capability contract."
          }
        },
        {
          "case_id": "near-neighbor-boundary",
          "prompt": "I only need a one-off summary of these notes, not a reusable process.",
          "input_files": [],
          "metadata": {
            "case_type": "near_neighbor",
            "tier": "production"
          },
          "review_instruction": "Pick A or B based only on the rubric. Do not infer which output came from the skill.",
          "rubric": [
            {
              "id": "declines-skill",
              "description": "Output refuses unnecessary skill creation for one-off work.",
              "weight": 1.0
            },
            {
              "id": "names-near-neighbor",
              "description": "Output labels the request as near-neighbor instead of owned work.",
              "weight": 1.0
            },
            {
              "id": "requires-reuse-signal",
              "description": "Output asks for repeat-use evidence before packaging.",
              "weight": 1.0
            }
          ],
          "variant_a": {
            "blind_id": "near-neighbor-boundary:A",
            "output": "Create a SKILL.md and a reusable workflow anyway so future notes can use it."
          },
          "variant_b": {
            "blind_id": "near-neighbor-boundary:B",
            "output": "Do not create a skill for this one-off request. Treat it as a near-neighbor: answer the summary directly unless the user confirms repeated use, shared ownership, or a reusable output contract."
          }
        },
        {
          "case_id": "file-backed-governed-package",
          "prompt": "Turn the attached release brief source into a governed skill package.",
          "input_files": [
            "fixtures/release-brief-source.md"
          ],
          "metadata": {
            "case_type": "boundary",
            "tier": "governed"
          },
          "review_instruction": "Pick A or B based only on the rubric. Do not infer which output came from the skill.",
          "rubric": [
            {
              "id": "uses-file-backed-evidence",
              "description": "Output names file-backed source evidence.",
              "weight": 1.0
            },
            {
              "id": "has-governance",
              "description": "Output preserves governed ownership metadata.",
              "weight": 1.0
            },
            {
              "id": "has-output-contract",
              "description": "Output preserves output and rollback boundaries.",
              "weight": 1.0
            },
            {
              "id": "has-trust-and-scorecard",
              "description": "Output requires trust and output scorecard artifacts.",
              "weight": 1.0
            },
            {
              "id": "does-not-invent-evidence",
              "description": "Output forbids invented launch evidence.",
              "weight": 1.0
            }
          ],
          "variant_a": {
            "blind_id": "file-backed-governed-package:A",
            "output": "Draft a release announcement with the changelog, support notes, and owner name."
          },
          "variant_b": {
            "blind_id": "file-backed-governed-package:B",
            "output": "Use the file-backed fixture as source evidence, then create a governed skill package with SKILL.md, agents/interface.yaml, owner, review cadence, input_files, output contract, rollback boundary, trust report, and reports/output_quality_scorecard.md. Mark missing launch metrics as missing evidence instead of inventing them."
          }
        }
      ]
    },
    "output_review_kit": {
      "schema_version": "1.0",
      "ok": true,
      "summary": {
        "case_count": 5,
        "ready_for_adjudication_count": 0,
        "pending_decision_count": 5,
        "invalid_decision_count": 0,
        "reviewer_metadata_present": false,
        "answer_key_hidden": true,
        "answer_key_path_exposed": false,
        "ready_to_run_adjudication": false,
        "failure_count": 0
      },
      "artifacts": {
        "reviewer_kit_json": "reports/output_review_kit.json",
        "reviewer_kit_markdown": "reports/output_review_kit.md",
        "reviewer_kit_html": "reports/output_review_kit.html",
        "blind_pack_json": "reports/output_blind_review_pack.json",
        "blind_pack_markdown": "reports/output_blind_review_pack.md",
        "decisions": "reports/output_review_decisions.json",
        "adjudication_json": "reports/output_review_adjudication.json",
        "adjudication_markdown": "reports/output_review_adjudication.md"
      },
      "template_written": false,
      "review_contract": {
        "reviewer_steps": [
          "Open reports/output_blind_review_pack.md or this kit and compare Variant A vs Variant B for each case.",
          "Record choices in reports/output_review_decisions.json without opening the answer key.",
          "Use winner_variant A or B, confidence from 0 to 1, and a short reason for every case.",
          "Run python3 scripts/yao.py output-review after choices are recorded.",
          "Refresh python3 scripts/yao.py review-studio . before asking for release approval."
        ],
        "required_fields": {
          "reviewer": "Human reviewer name or review group.",
          "reviewed_at": "Review date or timestamp.",
          "winner_variant": "A or B for every case.",
          "confidence": "Optional numeric confidence from 0 to 1.",
          "reason": "Short rationale based on the rubric, not on hidden labels."
        },
        "privacy_contract": [
          "The answer key is intentionally withheld from this kit.",
          "Do not inspect hidden labels or expected winners before decisions are recorded.",
          "Do not paste private user data into decision reasons.",
          "Pending decisions must stay pending instead of being counted as human agreement."
        ]
      },
      "cases": [
        {
          "case_id": "skill-package-contract",
          "prompt": "Turn this repeated workflow into a reusable team skill package.",
          "input_files": [],
          "review_instruction": "Pick A or B based only on the rubric. Do not infer which output came from the skill.",
          "rubric": [
            {
              "id": "has-entrypoint",
              "description": "Output names the routeable Skill entrypoint.",
              "weight": 1.0
            },
            {
              "id": "has-interface",
              "description": "Output includes neutral interface metadata.",
              "weight": 1.0
            },
            {
              "id": "has-report",
              "description": "Output points reviewer to generated overview report.",
              "weight": 1.0
            },
            {
              "id": "has-resource-boundary",
              "description": "Output preserves entrypoint/resource separation.",
              "weight": 1.0
            }
          ],
          "variant_a": {
            "blind_id": "skill-package-contract:A",
            "output": "Create a routeable SKILL.md, agents/interface.yaml, reports/skill-overview.html, and a focused eval plan. Keep the root entrypoint lean, move durable guidance into references/, scripts into scripts/, and evidence into reports/."
          },
          "variant_b": {
            "blind_id": "skill-package-contract:B",
            "output": "I can write a prompt for that workflow and include a short checklist."
          },
          "decision_state": {
            "status": "awaiting-decision",
            "winner_variant_recorded": false,
            "confidence_recorded": false,
            "reason_recorded": false,
            "blocking_reason": "Decision template exists but this row is still blank."
          }
        },
        {
          "case_id": "output-eval-expectation",
          "prompt": "Upgrade this production skill so we know whether the generated output is better than baseline.",
          "input_files": [],
          "review_instruction": "Pick A or B based only on the rubric. Do not infer which output came from the skill.",
          "rubric": [
            {
              "id": "has-baseline-comparison",
              "description": "Output explicitly compares with-skill and baseline outputs.",
              "weight": 1.0
            },
            {
              "id": "has-assertion-grading",
              "description": "Output includes objective assertion grading.",
              "weight": 1.0
            },
            {
              "id": "has-scorecard",
              "description": "Output produces a scorecard report path.",
              "weight": 1.0
            },
            {
              "id": "has-failure-taxonomy",
              "description": "Output records failure taxonomy.",
              "weight": 1.0
            }
          ],
          "variant_a": {
            "blind_id": "output-eval-expectation:A",
            "output": "Add Output Eval Lab cases with baseline_output and with_skill_output, run assertion grading, report with-skill vs baseline pass-rate delta, and record failure taxonomy plus next fixes in reports/output_quality_scorecard.md."
          },
          "variant_b": {
            "blind_id": "output-eval-expectation:B",
            "output": "Add more examples and run the trigger eval again."
          },
          "decision_state": {
            "status": "awaiting-decision",
            "winner_variant_recorded": false,
            "confidence_recorded": false,
            "reason_recorded": false,
            "blocking_reason": "Decision template exists but this row is still blank."
          }
        },
        {
          "case_id": "ir-before-packaging",
          "prompt": "Package this skill for OpenAI, Claude, Agent Skills, and generic targets.",
          "input_files": [],
          "review_instruction": "Pick A or B based only on the rubric. Do not infer which output came from the skill.",
          "rubric": [
            {
              "id": "has-ir-first",
              "description": "Output requires Skill IR before packaging.",
              "weight": 1.0
            },
            {
              "id": "has-core-ir-fields",
              "description": "Output lists core IR contract fields.",
              "weight": 1.0
            },
            {
              "id": "has-targets",
              "description": "Output names requested runtime targets.",
              "weight": 1.0
            },
            {
              "id": "has-semantic-preservation",
              "description": "Output says targets must preserve the capability contract.",
              "weight": 1.0
            }
          ],
          "variant_a": {
            "blind_id": "ir-before-packaging:A",
            "output": "Export folders for each platform and adjust files as needed."
          },
          "variant_b": {
            "blind_id": "ir-before-packaging:B",
            "output": "Export Skill IR first with job_to_be_done, trigger_surface, workflow, resources, eval_plan, risk, and governance. Then compile or package targets from the IR so OpenAI, Claude, Agent Skills, and generic packages preserve the same capability contract."
          },
          "decision_state": {
            "status": "awaiting-decision",
            "winner_variant_recorded": false,
            "confidence_recorded": false,
            "reason_recorded": false,
            "blocking_reason": "Decision template exists but this row is still blank."
          }
        },
        {
          "case_id": "near-neighbor-boundary",
          "prompt": "I only need a one-off summary of these notes, not a reusable process.",
          "input_files": [],
          "review_instruction": "Pick A or B based only on the rubric. Do not infer which output came from the skill.",
          "rubric": [
            {
              "id": "declines-skill",
              "description": "Output refuses unnecessary skill creation for one-off work.",
              "weight": 1.0
            },
            {
              "id": "names-near-neighbor",
              "description": "Output labels the request as near-neighbor instead of owned work.",
              "weight": 1.0
            },
            {
              "id": "requires-reuse-signal",
              "description": "Output asks for repeat-use evidence before packaging.",
              "weight": 1.0
            }
          ],
          "variant_a": {
            "blind_id": "near-neighbor-boundary:A",
            "output": "Create a SKILL.md and a reusable workflow anyway so future notes can use it."
          },
          "variant_b": {
            "blind_id": "near-neighbor-boundary:B",
            "output": "Do not create a skill for this one-off request. Treat it as a near-neighbor: answer the summary directly unless the user confirms repeated use, shared ownership, or a reusable output contract."
          },
          "decision_state": {
            "status": "awaiting-decision",
            "winner_variant_recorded": false,
            "confidence_recorded": false,
            "reason_recorded": false,
            "blocking_reason": "Decision template exists but this row is still blank."
          }
        },
        {
          "case_id": "file-backed-governed-package",
          "prompt": "Turn the attached release brief source into a governed skill package.",
          "input_files": [
            "fixtures/release-brief-source.md"
          ],
          "review_instruction": "Pick A or B based only on the rubric. Do not infer which output came from the skill.",
          "rubric": [
            {
              "id": "uses-file-backed-evidence",
              "description": "Output names file-backed source evidence.",
              "weight": 1.0
            },
            {
              "id": "has-governance",
              "description": "Output preserves governed ownership metadata.",
              "weight": 1.0
            },
            {
              "id": "has-output-contract",
              "description": "Output preserves output and rollback boundaries.",
              "weight": 1.0
            },
            {
              "id": "has-trust-and-scorecard",
              "description": "Output requires trust and output scorecard artifacts.",
              "weight": 1.0
            },
            {
              "id": "does-not-invent-evidence",
              "description": "Output forbids invented launch evidence.",
              "weight": 1.0
            }
          ],
          "variant_a": {
            "blind_id": "file-backed-governed-package:A",
            "output": "Draft a release announcement with the changelog, support notes, and owner name."
          },
          "variant_b": {
            "blind_id": "file-backed-governed-package:B",
            "output": "Use the file-backed fixture as source evidence, then create a governed skill package with SKILL.md, agents/interface.yaml, owner, review cadence, input_files, output contract, rollback boundary, trust report, and reports/output_quality_scorecard.md. Mark missing launch metrics as missing evidence instead of inventing them."
          },
          "decision_state": {
            "status": "awaiting-decision",
            "winner_variant_recorded": false,
            "confidence_recorded": false,
            "reason_recorded": false,
            "blocking_reason": "Decision template exists but this row is still blank."
          }
        }
      ],
      "failures": []
    },
    "output_review_adjudication": {
      "schema_version": "1.0",
      "ok": true,
      "summary": {
        "pair_count": 5,
        "judgment_count": 0,
        "pending_count": 5,
        "agreement_count": 0,
        "disagreement_count": 0,
        "invalid_decision_count": 0,
        "answer_revealed_count": 0,
        "pending_answer_hidden_count": 5,
        "agreement_rate": null,
        "needs_review": true,
        "failure_count": 0,
        "reviewer_checklist_count": 5,
        "reviewer_checklist_pending_count": 5,
        "reviewer_checklist_invalid_count": 0,
        "reviewer_checklist_ready_count": 0
      },
      "reviewer": "",
      "reviewed_at": "",
      "artifacts": {
        "blind_pack": "reports/output_blind_review_pack.json",
        "answer_key": "reports/output_blind_answer_key.json",
        "decisions": "reports/output_review_decisions.json",
        "json": "reports/output_review_adjudication.json",
        "markdown": "reports/output_review_adjudication.md"
      },
      "template_written": false,
      "pairs": [
        {
          "case_id": "skill-package-contract",
          "status": "pending",
          "expected_winner_variant": "",
          "expected_revealed": false,
          "reviewer_winner_variant": "",
          "confidence": null,
          "reason": "",
          "prompt": "Turn this repeated workflow into a reusable team skill package."
        },
        {
          "case_id": "output-eval-expectation",
          "status": "pending",
          "expected_winner_variant": "",
          "expected_revealed": false,
          "reviewer_winner_variant": "",
          "confidence": null,
          "reason": "",
          "prompt": "Upgrade this production skill so we know whether the generated output is better than baseline."
        },
        {
          "case_id": "ir-before-packaging",
          "status": "pending",
          "expected_winner_variant": "",
          "expected_revealed": false,
          "reviewer_winner_variant": "",
          "confidence": null,
          "reason": "",
          "prompt": "Package this skill for OpenAI, Claude, Agent Skills, and generic targets."
        },
        {
          "case_id": "near-neighbor-boundary",
          "status": "pending",
          "expected_winner_variant": "",
          "expected_revealed": false,
          "reviewer_winner_variant": "",
          "confidence": null,
          "reason": "",
          "prompt": "I only need a one-off summary of these notes, not a reusable process."
        },
        {
          "case_id": "file-backed-governed-package",
          "status": "pending",
          "expected_winner_variant": "",
          "expected_revealed": false,
          "reviewer_winner_variant": "",
          "confidence": null,
          "reason": "",
          "prompt": "Turn the attached release brief source into a governed skill package."
        }
      ],
      "reviewer_checklist": [
        {
          "case_id": "skill-package-contract",
          "readiness": "awaiting-decision",
          "blocking_reason": "Reviewer has not selected A or B yet; answer key remains hidden.",
          "status": "pending",
          "reviewer_winner_variant": "",
          "answer_key_visible": false,
          "prompt": "Turn this repeated workflow into a reusable team skill package.",
          "blind_pack_path": "reports/output_blind_review_pack.json",
          "decisions_path": "reports/output_review_decisions.json",
          "commands": {
            "prepare_review_kit": "python3 scripts/yao.py output-review-kit",
            "write_template": "python3 scripts/adjudicate_output_review.py --write-template",
            "adjudicate": "python3 scripts/yao.py output-review",
            "refresh_review_studio": "python3 scripts/yao.py review-studio ."
          },
          "required_fields": {
            "winner_variant": "A or B after reading only the blind review pack.",
            "confidence": "Optional number from 0 to 1.",
            "reason": "Short rationale; do not reveal baseline or with-skill labels before adjudication."
          },
          "privacy_contract": [
            "Do not paste raw private user data into the decision reason.",
            "Do not open the answer key before reviewer choices are recorded.",
            "Leave winner_variant blank when the reviewer is not ready to decide."
          ]
        },
        {
          "case_id": "output-eval-expectation",
          "readiness": "awaiting-decision",
          "blocking_reason": "Reviewer has not selected A or B yet; answer key remains hidden.",
          "status": "pending",
          "reviewer_winner_variant": "",
          "answer_key_visible": false,
          "prompt": "Upgrade this production skill so we know whether the generated output is better than baseline.",
          "blind_pack_path": "reports/output_blind_review_pack.json",
          "decisions_path": "reports/output_review_decisions.json",
          "commands": {
            "prepare_review_kit": "python3 scripts/yao.py output-review-kit",
            "write_template": "python3 scripts/adjudicate_output_review.py --write-template",
            "adjudicate": "python3 scripts/yao.py output-review",
            "refresh_review_studio": "python3 scripts/yao.py review-studio ."
          },
          "required_fields": {
            "winner_variant": "A or B after reading only the blind review pack.",
            "confidence": "Optional number from 0 to 1.",
            "reason": "Short rationale; do not reveal baseline or with-skill labels before adjudication."
          },
          "privacy_contract": [
            "Do not paste raw private user data into the decision reason.",
            "Do not open the answer key before reviewer choices are recorded.",
            "Leave winner_variant blank when the reviewer is not ready to decide."
          ]
        },
        {
          "case_id": "ir-before-packaging",
          "readiness": "awaiting-decision",
          "blocking_reason": "Reviewer has not selected A or B yet; answer key remains hidden.",
          "status": "pending",
          "reviewer_winner_variant": "",
          "answer_key_visible": false,
          "prompt": "Package this skill for OpenAI, Claude, Agent Skills, and generic targets.",
          "blind_pack_path": "reports/output_blind_review_pack.json",
          "decisions_path": "reports/output_review_decisions.json",
          "commands": {
            "prepare_review_kit": "python3 scripts/yao.py output-review-kit",
            "write_template": "python3 scripts/adjudicate_output_review.py --write-template",
            "adjudicate": "python3 scripts/yao.py output-review",
            "refresh_review_studio": "python3 scripts/yao.py review-studio ."
          },
          "required_fields": {
            "winner_variant": "A or B after reading only the blind review pack.",
            "confidence": "Optional number from 0 to 1.",
            "reason": "Short rationale; do not reveal baseline or with-skill labels before adjudication."
          },
          "privacy_contract": [
            "Do not paste raw private user data into the decision reason.",
            "Do not open the answer key before reviewer choices are recorded.",
            "Leave winner_variant blank when the reviewer is not ready to decide."
          ]
        },
        {
          "case_id": "near-neighbor-boundary",
          "readiness": "awaiting-decision",
          "blocking_reason": "Reviewer has not selected A or B yet; answer key remains hidden.",
          "status": "pending",
          "reviewer_winner_variant": "",
          "answer_key_visible": false,
          "prompt": "I only need a one-off summary of these notes, not a reusable process.",
          "blind_pack_path": "reports/output_blind_review_pack.json",
          "decisions_path": "reports/output_review_decisions.json",
          "commands": {
            "prepare_review_kit": "python3 scripts/yao.py output-review-kit",
            "write_template": "python3 scripts/adjudicate_output_review.py --write-template",
            "adjudicate": "python3 scripts/yao.py output-review",
            "refresh_review_studio": "python3 scripts/yao.py review-studio ."
          },
          "required_fields": {
            "winner_variant": "A or B after reading only the blind review pack.",
            "confidence": "Optional number from 0 to 1.",
            "reason": "Short rationale; do not reveal baseline or with-skill labels before adjudication."
          },
          "privacy_contract": [
            "Do not paste raw private user data into the decision reason.",
            "Do not open the answer key before reviewer choices are recorded.",
            "Leave winner_variant blank when the reviewer is not ready to decide."
          ]
        },
        {
          "case_id": "file-backed-governed-package",
          "readiness": "awaiting-decision",
          "blocking_reason": "Reviewer has not selected A or B yet; answer key remains hidden.",
          "status": "pending",
          "reviewer_winner_variant": "",
          "answer_key_visible": false,
          "prompt": "Turn the attached release brief source into a governed skill package.",
          "blind_pack_path": "reports/output_blind_review_pack.json",
          "decisions_path": "reports/output_review_decisions.json",
          "commands": {
            "prepare_review_kit": "python3 scripts/yao.py output-review-kit",
            "write_template": "python3 scripts/adjudicate_output_review.py --write-template",
            "adjudicate": "python3 scripts/yao.py output-review",
            "refresh_review_studio": "python3 scripts/yao.py review-studio ."
          },
          "required_fields": {
            "winner_variant": "A or B after reading only the blind review pack.",
            "confidence": "Optional number from 0 to 1.",
            "reason": "Short rationale; do not reveal baseline or with-skill labels before adjudication."
          },
          "privacy_contract": [
            "Do not paste raw private user data into the decision reason.",
            "Do not open the answer key before reviewer choices are recorded.",
            "Leave winner_variant blank when the reviewer is not ready to decide."
          ]
        }
      ],
      "failures": []
    },
    "benchmark_reproducibility": {
      "schema_version": "1.0",
      "ok": true,
      "generated_at": "2026-06-15",
      "skill_dir": ".",
      "commit": "5495734e7e33b19b84a932626112d783a3edf271",
      "git_status": {
        "available": true,
        "dirty": true,
        "changed_file_count": 61,
        "sample": [
          " M Makefile",
          " M README.md",
          " M reports/adoption_drift_report.json",
          " M reports/adoption_drift_report.md",
          " M reports/architecture_maintainability.json",
          " M reports/architecture_maintainability.md",
          " M reports/benchmark_reproducibility.json",
          " M reports/benchmark_reproducibility.md",
          " M reports/compiled_targets.json",
          " M reports/context_budget.json",
          " M reports/context_budget.md",
          " M reports/context_budget_summary.json"
        ],
        "scope": "generation-time status before this report is written"
      },
      "summary": {
        "reproducibility_ready": true,
        "release_lock_ready": false,
        "methodology_complete": true,
        "required_artifact_count": 24,
        "missing_artifact_count": 0,
        "evidence_bundle_sha256": "119f209f1d4665b38a489cc372140ec9f01c663c4d2637048e82b924cfadb6c5",
        "source_contract_sha256": "ecb6c742c79077b26d1f9e61ede1b1c4c078b485fc57467b969d9c1744bc91b6",
        "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
        "output_case_count": 5,
        "failure_disclosure_count": 3,
        "command_count": 21,
        "command_executed_count": 10,
        "timing_observed_count": 10,
        "model_executed_count": 0,
        "token_observed_count": 0,
        "human_review_complete": false,
        "provider_evidence_complete": false,
        "world_class_ready": false,
        "world_class_open_gap_count": 4,
        "world_class_task_count": 4,
        "world_class_ledger_pending_count": 4,
        "world_class_source_check_count": 13,
        "world_class_source_pass_count": 6,
        "world_class_source_blocked_count": 7,
        "public_claim_ready": false,
        "public_claim_blocker_count": 5,
        "working_tree_dirty": true,
        "changed_file_count": 61
      },
      "public_claim": {
        "ready": false,
        "scope": "public benchmark or world-class readiness claim",
        "blockers": [
          "release lock is not clean or commit is unavailable",
          "provider-backed model holdout evidence is incomplete",
          "human blind-review adjudication is incomplete",
          "world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)",
          "world-class source checks are not all accepted (6/13 pass, 7 blocked)"
        ],
        "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
      },
      "release_lock": {
        "ready": false,
        "commit": "5495734e7e33b19b84a932626112d783a3edf271",
        "status_scope": "generation-time status before this report is written",
        "reason": "working tree was dirty at generation time"
      },
      "evidence_bundle": {
        "algorithm": "sha256(path,label,exists,artifact_sha256)",
        "artifact_count": 24,
        "existing_count": 24,
        "missing_count": 0,
        "missing_paths": [],
        "sha256": "119f209f1d4665b38a489cc372140ec9f01c663c4d2637048e82b924cfadb6c5"
      },
      "methodology": {
        "path": "reports/benchmark_methodology.md",
        "exists": true,
        "sections": [
          {
            "heading": "## Benchmark Types",
            "exists": true
          },
          {
            "heading": "## Sample Sources",
            "exists": true
          },
          {
            "heading": "## Evaluation Dimensions",
            "exists": true
          },
          {
            "heading": "## Weighting Rule",
            "exists": true
          },
          {
            "heading": "## Failure Disclosure",
            "exists": true
          },
          {
            "heading": "## Reproduction",
            "exists": true
          }
        ],
        "missing_sections": []
      },
      "artifacts_checked": [
        {
          "label": "methodology",
          "path": "reports/benchmark_methodology.md",
          "exists": true,
          "bytes": 2715,
          "sha256": "57025e0123ce5d10401c5bff376d2eeeac7943c83897ae1ad3fb22cadf790f92"
        },
        {
          "label": "failure_disclosure",
          "path": "evals/failure-cases.md",
          "exists": true,
          "bytes": 889,
          "sha256": "28833c0d4a217d612879d193fb5de199880dd5b3093ab5757e4315600fa4fb08"
        },
        {
          "label": "output_cases",
          "path": "evals/output/cases.jsonl",
          "exists": true,
          "bytes": 6555,
          "sha256": "a6ae9685711620d7203b73ace4412194ae287689f945b5139ec8ad75b9eefe04"
        },
        {
          "label": "output_schema",
          "path": "evals/output/schema.json",
          "exists": true,
          "bytes": 2193,
          "sha256": "8ee340c95064260c5e952be614e19841ac676162c6bf01d21b107e38cb04e0b9"
        },
        {
          "label": "output_scorecard",
          "path": "reports/output_quality_scorecard.json",
          "exists": true,
          "bytes": 25530,
          "sha256": "0806258a8e084b27e112537faff0de64a8519ca90cfdc78b57c0e4c08a514cca"
        },
        {
          "label": "output_execution",
          "path": "reports/output_execution_runs.json",
          "exists": true,
          "bytes": 7965,
          "sha256": "e559e6acf9f2e709f65dc36ea5646199a367fb760d7b7e6014570c59d3f46a55"
        },
        {
          "label": "blind_review",
          "path": "reports/output_blind_review_pack.json",
          "exists": true,
          "bytes": 7804,
          "sha256": "bbe2db8ec2776fe289cd7d6bb78d48c2b8baa106ad37f79c15e43669b10c9390"
        },
        {
          "label": "review_adjudication",
          "path": "reports/output_review_adjudication.json",
          "exists": true,
          "bytes": 9495,
          "sha256": "240485a721af49d5c75fe8049e9ef74b50546f685aa6346ab9e20713fb1105f4"
        },
        {
          "label": "trigger_scorecard",
          "path": "reports/route_scorecard.json",
          "exists": true,
          "bytes": 16961,
          "sha256": "c164e83e36d0af276b6af2de2a5e026d7f0711b83eef2b5dcd0e760bd8bb28fc"
        },
        {
          "label": "runtime_conformance",
          "path": "reports/conformance_matrix.json",
          "exists": true,
          "bytes": 10313,
          "sha256": "8251329e663dda51472f29b7721e73d72ccbec9760d96fda022f6218a5a6e347"
        },
        {
          "label": "trust_report",
          "path": "reports/security_trust_report.json",
          "exists": true,
          "bytes": 105694,
          "sha256": "5c1cc74ef5306f2959c7bc4d01068dd2cc36a840500724922f2fb346e63ddbc5"
        },
        {
          "label": "python_compatibility",
          "path": "reports/python_compatibility.json",
          "exists": true,
          "bytes": 22252,
          "sha256": "fcf288346cb5159e070b2df75a8e371cca2501945c971aead521e7ac3557a4bc"
        },
        {
          "label": "registry_audit",
          "path": "reports/registry_audit.json",
          "exists": true,
          "bytes": 3183,
          "sha256": "9b54f3fd07680c2a9dd18ec9845e1faa1e19e8fbc854cd13a2d5bc1b84360f0e"
        },
        {
          "label": "package_verification",
          "path": "reports/package_verification.json",
          "exists": true,
          "bytes": 19338,
          "sha256": "2476ae8ec9c491a3f7f31ec3f0c6c78cceead8e80700dcb696838eec226c675b"
        },
        {
          "label": "install_simulation",
          "path": "reports/install_simulation.json",
          "exists": true,
          "bytes": 8758,
          "sha256": "491fabea4624d41967ff04952b72e0b165882c1b3b276124047c921daea4f3b7"
        },
        {
          "label": "skill_os2_audit",
          "path": "reports/skill_os2_audit.json",
          "exists": true,
          "bytes": 14310,
          "sha256": "8481f4d78f2ad4ff0e74936b58b643a91052a30b6d12bcbbf24e0b4291b8fb1f"
        },
        {
          "label": "world_class_evidence_plan",
          "path": "reports/world_class_evidence_plan.json",
          "exists": true,
          "bytes": 19940,
          "sha256": "933cdb0021818c0a8c5fc199af7dfa7879777ebf7959ed3a36bba52a0aed9c6c"
        },
        {
          "label": "world_class_evidence_ledger",
          "path": "reports/world_class_evidence_ledger.json",
          "exists": true,
          "bytes": 20006,
          "sha256": "5407409841eb8e1174a07ea0af17ddf709155f0c548c897b82c2f75b869b333a"
        },
        {
          "label": "world_class_evidence_intake",
          "path": "reports/world_class_evidence_intake.json",
          "exists": true,
          "bytes": 18865,
          "sha256": "b10e1ce0a5a17df72462ce8f0c468356f58ff88bd7ceab349c82a1fb3b6697ef"
        },
        {
          "label": "world_class_submission_review",
          "path": "reports/world_class_submission_review.json",
          "exists": true,
          "bytes": 12413,
          "sha256": "3bce5f072d037a6c383cfd597f8530c2bc87ba31781fa90c843a9186dd2f8fea"
        },
        {
          "label": "world_class_operator_runbook",
          "path": "reports/world_class_operator_runbook.json",
          "exists": true,
          "bytes": 24021,
          "sha256": "d377b8d99831ce297011e4e270fc7287a53727500f5d503dd3dc4b984d26f0ad"
        },
        {
          "label": "world_class_operator_runbook_markdown",
          "path": "reports/world_class_operator_runbook.md",
          "exists": true,
          "bytes": 15080,
          "sha256": "9f141f09bf485a4299b37eb8c21ebab9f212ea130a0daea8b0d7d5bd7ab020aa"
        },
        {
          "label": "world_class_operator_runbook_html",
          "path": "reports/world_class_operator_runbook.html",
          "exists": true,
          "bytes": 21030,
          "sha256": "04cc091b113f018072d07a1d71ad142773c415a49e633493689903e7b399b5e6"
        },
        {
          "label": "world_class_claim_guard",
          "path": "reports/world_class_claim_guard.json",
          "exists": true,
          "bytes": 8634,
          "sha256": "a2e6953e92e667cc0913c08e48b6954ea48420ad3a4056ed15eb19a183825e67"
        }
      ],
      "missing_artifacts": [],
      "reproduction_commands": [
        {
          "label": "source commit",
          "command": "git rev-parse HEAD",
          "evidence": "git commit hash"
        },
        {
          "label": "trigger eval",
          "command": "make eval-suite",
          "evidence": "reports/eval_suite.json"
        },
        {
          "label": "output eval",
          "command": "python3 scripts/yao.py output-eval",
          "evidence": "reports/output_quality_scorecard.json"
        },
        {
          "label": "output execution",
          "command": "python3 scripts/yao.py output-exec --runner-command '[\"python3\",\"scripts/local_output_eval_runner.py\"]'",
          "evidence": "reports/output_execution_runs.json"
        },
        {
          "label": "blind review adjudication",
          "command": "python3 scripts/yao.py output-review",
          "evidence": "reports/output_review_adjudication.json"
        },
        {
          "label": "skill ir",
          "command": "python3 scripts/yao.py skill-ir . --output-json skill-ir/examples/yao-meta-skill.json",
          "evidence": "skill-ir/examples/yao-meta-skill.json"
        },
        {
          "label": "runtime conformance",
          "command": "python3 scripts/yao.py conformance .",
          "evidence": "reports/conformance_matrix.json"
        },
        {
          "label": "trust report",
          "command": "python3 scripts/yao.py trust .",
          "evidence": "reports/security_trust_report.json"
        },
        {
          "label": "python compatibility",
          "command": "python3 scripts/yao.py python-compat .",
          "evidence": "reports/python_compatibility.json"
        },
        {
          "label": "package",
          "command": "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --expectations evals/packaging_expectations.json --output-dir dist --zip",
          "evidence": "dist/yao-meta-skill.zip"
        },
        {
          "label": "package verify",
          "command": "python3 scripts/yao.py package-verify . --package-dir dist --require-zip",
          "evidence": "reports/package_verification.json"
        },
        {
          "label": "install simulate",
          "command": "python3 scripts/yao.py install-simulate . --package-dir dist",
          "evidence": "reports/install_simulation.json"
        },
        {
          "label": "registry audit",
          "command": "python3 scripts/yao.py registry-audit .",
          "evidence": "reports/registry_audit.json"
        },
        {
          "label": "skill os audit",
          "command": "python3 scripts/yao.py skill-os2-audit .",
          "evidence": "reports/skill_os2_audit.json"
        },
        {
          "label": "world-class evidence plan",
          "command": "python3 scripts/yao.py world-class-evidence .",
          "evidence": "reports/world_class_evidence_plan.json"
        },
        {
          "label": "world-class evidence ledger",
          "command": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions",
          "evidence": "reports/world_class_evidence_ledger.json"
        },
        {
          "label": "world-class evidence intake",
          "command": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
          "evidence": "reports/world_class_evidence_intake.json"
        },
        {
          "label": "world-class submission review",
          "command": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",
          "evidence": "reports/world_class_submission_review.json"
        },
        {
          "label": "world-class operator runbook",
          "command": "python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions",
          "evidence": "reports/world_class_operator_runbook.json"
        },
        {
          "label": "world-class claim guard",
          "command": "python3 scripts/yao.py world-class-claim-guard .",
          "evidence": "reports/world_class_claim_guard.json"
        },
        {
          "label": "full ci",
          "command": "make ci-test",
          "evidence": "CI target output"
        }
      ],
      "failure_disclosure": {
        "path": "evals/failure-cases.md",
        "case_count": 3,
        "policy": "Keep representative failures visible and tied to regression checks."
      },
      "limitations": [
        "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
        "Local command-runner evidence is reproducible but does not replace provider-backed model holdout evidence.",
        "Pending blind-review decisions are visible but do not count as human adjudication.",
        "World-class readiness remains false until external and human evidence gaps close."
      ],
      "artifacts": {
        "json": "reports/benchmark_reproducibility.json",
        "markdown": "reports/benchmark_reproducibility.md"
      }
    },
    "skill_os2_coverage": {
      "schema_version": "1.0",
      "ok": true,
      "generated_at": "2026-06-15",
      "skill_dir": ".",
      "summary": {
        "item_count": 20,
        "module_count": 8,
        "recommended_pr_count": 12,
        "pass_count": 20,
        "warn_count": 0,
        "missing_count": 0,
        "extension_track_count": 2,
        "extension_partial_count": 1,
        "extension_planned_count": 0,
        "extension_covered_count": 1,
        "adaptive_extension_ready": false,
        "local_blueprint_ready": true,
        "public_world_class_ready": false,
        "world_class_evidence_pending_count": 4,
        "decision": "local-blueprint-covered-evidence-pending"
      },
      "status_counts": {
        "pass": 20,
        "warn": 0,
        "missing": 0
      },
      "extension_status_counts": {
        "covered": 1,
        "partial": 1
      },
      "modules": [
        {
          "key": "skill-ir",
          "category": "core-module",
          "label": "Skill IR",
          "status": "pass",
          "objective": "Platform-neutral capability contract exists before platform-specific packaging.",
          "current": "schema 2.0.0; targets 5",
          "command": "python3 scripts/yao.py skill-ir .",
          "test": "python3 tests/verify_skill_ir.py",
          "evidence": [
            {
              "path": "skill-ir/schema.json",
              "exists": true
            },
            {
              "path": "skill-ir/examples/yao-meta-skill.json",
              "exists": true
            },
            {
              "path": "scripts/export_skill_ir.py",
              "exists": true
            },
            {
              "path": "tests/verify_skill_ir.py",
              "exists": true
            }
          ],
          "next_action": "Keep all target packages compiled from IR rather than hand-maintained per target."
        },
        {
          "key": "output-eval-lab",
          "category": "core-module",
          "label": "Output Eval Lab",
          "status": "pass",
          "objective": "with-skill/baseline output quality is measured with assertions, execution evidence, and blind review packs.",
          "current": "5 cases; delta 100.0; execution 10",
          "command": "python3 scripts/yao.py output-exec . && python3 scripts/yao.py output-review .",
          "test": "python3 tests/verify_output_eval_lab.py",
          "evidence": [
            {
              "path": "evals/output/schema.json",
              "exists": true
            },
            {
              "path": "evals/output/cases.jsonl",
              "exists": true
            },
            {
              "path": "scripts/run_output_eval.py",
              "exists": true
            },
            {
              "path": "scripts/run_output_execution.py",
              "exists": true
            },
            {
              "path": "reports/output_quality_scorecard.json",
              "exists": true
            },
            {
              "path": "tests/verify_output_eval_lab.py",
              "exists": true
            }
          ],
          "next_action": "Add more real-file and adversarial holdout cases as adoption data grows."
        },
        {
          "key": "runtime-conformance",
          "category": "core-module",
          "label": "Runtime Conformance",
          "status": "pass",
          "objective": "Target packages can be consumed by OpenAI, Claude, Agent Skills, VS Code, and generic targets.",
          "current": "5/5 targets pass",
          "command": "python3 scripts/yao.py conformance .",
          "test": "python3 tests/verify_conformance_suite.py",
          "evidence": [
            {
              "path": "runtime/conformance/schema.json",
              "exists": true
            },
            {
              "path": "scripts/run_conformance_suite.py",
              "exists": true
            },
            {
              "path": "reports/conformance_matrix.json",
              "exists": true
            },
            {
              "path": "tests/verify_conformance_suite.py",
              "exists": true
            }
          ],
          "next_action": "Keep conformance cases aligned with current platform metadata rules."
        },
        {
          "key": "trust-security",
          "category": "core-module",
          "label": "Trust Security",
          "status": "pass",
          "objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
          "current": "106 scripts; secrets 0; help failures 0",
          "command": "python3 scripts/yao.py trust .",
          "test": "python3 tests/verify_trust_check.py",
          "evidence": [
            {
              "path": "scripts/trust_check.py",
              "exists": true
            },
            {
              "path": "security/trust_policy.md",
              "exists": true
            },
            {
              "path": "security/script_policy.md",
              "exists": true
            },
            {
              "path": "security/permission_policy.json",
              "exists": true
            },
            {
              "path": "reports/security_trust_report.json",
              "exists": true
            },
            {
              "path": "tests/verify_trust_check.py",
              "exists": true
            }
          ],
          "next_action": "Keep high-permission approvals scoped, expiring, and mapped to target enforcement."
        },
        {
          "key": "skill-atlas",
          "category": "core-module",
          "label": "Skill Atlas",
          "status": "pass",
          "objective": "Team skill portfolio reveals route collisions, stale ownership, dependency graph, and no-route opportunities.",
          "current": "12 scanned skills; actionable collisions 0",
          "command": "python3 scripts/yao.py skill-atlas --workspace-root .",
          "test": "python3 tests/verify_skill_atlas.py",
          "evidence": [
            {
              "path": "scripts/build_skill_atlas.py",
              "exists": true
            },
            {
              "path": "skill_atlas/catalog.json",
              "exists": true
            },
            {
              "path": "skill_atlas/route_overlap_matrix.csv",
              "exists": true
            },
            {
              "path": "skill_atlas/dependency_graph.json",
              "exists": true
            },
            {
              "path": "reports/skill_atlas.json",
              "exists": true
            },
            {
              "path": "tests/verify_skill_atlas.py",
              "exists": true
            }
          ],
          "next_action": "Use real telemetry to rank stale or drifting skills by impact, not only by static metadata."
        },
        {
          "key": "registry-distribution",
          "category": "core-module",
          "label": "Registry Distribution",
          "status": "pass",
          "objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
          "current": "archive entries 586; install failures 0",
          "command": "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .",
          "test": "python3 tests/verify_registry_audit.py",
          "evidence": [
            {
              "path": "registry/index.schema.json",
              "exists": true
            },
            {
              "path": "registry/package.schema.json",
              "exists": true
            },
            {
              "path": "registry/packages/yao-meta-skill.json",
              "exists": true
            },
            {
              "path": "scripts/registry_audit.py",
              "exists": true
            },
            {
              "path": "reports/package_verification.json",
              "exists": true
            },
            {
              "path": "reports/install_simulation.json",
              "exists": true
            },
            {
              "path": "tests/verify_registry_audit.py",
              "exists": true
            }
          ],
          "next_action": "Regenerate registry metadata after package verification so source and archive checksums stay aligned."
        },
        {
          "key": "review-studio",
          "category": "core-module",
          "label": "Review Studio",
          "status": "pass",
          "objective": "One HTML page supports first-pass production review across trigger, output, runtime, trust, release, and evidence actions.",
          "current": "16 gates; decision review; warnings 3",
          "command": "python3 scripts/yao.py review-studio .",
          "test": "python3 tests/verify_review_studio.py",
          "evidence": [
            {
              "path": "scripts/render_review_studio.py",
              "exists": true
            },
            {
              "path": "reports/review-studio.html",
              "exists": true
            },
            {
              "path": "reports/review-studio.json",
              "exists": true
            },
            {
              "path": "tests/verify_review_studio.py",
              "exists": true
            }
          ],
          "next_action": "Close pending human and external evidence before claiming full release readiness."
        },
        {
          "key": "telemetry-drift",
          "category": "core-module",
          "label": "Telemetry Drift",
          "status": "pass",
          "objective": "Real usage feedback is captured as metadata-only local-first drift signals.",
          "current": "events 1; recipes 5; risk low",
          "command": "python3 scripts/yao.py telemetry-hooks . && python3 scripts/yao.py adoption-drift .",
          "test": "python3 tests/verify_telemetry_hooks.py",
          "evidence": [
            {
              "path": "scripts/emit_telemetry_event.py",
              "exists": true
            },
            {
              "path": "scripts/import_telemetry_events.py",
              "exists": true
            },
            {
              "path": "scripts/telemetry_native_host.py",
              "exists": true
            },
            {
              "path": "reports/adoption_drift_report.json",
              "exists": true
            },
            {
              "path": "reports/telemetry_hook_recipes.json",
              "exists": true
            },
            {
              "path": "tests/verify_telemetry_hooks.py",
              "exists": true
            }
          ],
          "next_action": "Install a real client and import production metadata-only events into the local drift loop."
        }
      ],
      "recommended_prs": [
        {
          "key": "benchmark-methodology",
          "category": "recommended-pr",
          "label": "Benchmark Methodology",
          "status": "pass",
          "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
          "current": "24 required artifacts checked",
          "command": "make ci-test",
          "test": "tests/verify_benchmark_reproducibility.py",
          "evidence": [
            {
              "path": "reports/benchmark_methodology.md",
              "exists": true
            },
            {
              "path": "reports/benchmark_reproducibility.json",
              "exists": true
            },
            {
              "path": "tests/verify_benchmark_reproducibility.py",
              "exists": true
            }
          ],
          "next_action": "Keep this item covered as the implementation evolves."
        },
        {
          "key": "output-eval-schema",
          "category": "recommended-pr",
          "label": "Output Eval Schema",
          "status": "pass",
          "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
          "current": "5 output cases",
          "command": "make ci-test",
          "test": "tests/verify_output_eval_lab.py",
          "evidence": [
            {
              "path": "evals/output/schema.json",
              "exists": true
            },
            {
              "path": "evals/output/cases.jsonl",
              "exists": true
            },
            {
              "path": "tests/verify_output_eval_lab.py",
              "exists": true
            }
          ],
          "next_action": "Keep this item covered as the implementation evolves."
        },
        {
          "key": "output-eval-runner",
          "category": "recommended-pr",
          "label": "Output Eval Runner",
          "status": "pass",
          "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
          "current": "delta 100.0",
          "command": "make ci-test",
          "test": "tests/verify_output_eval_lab.py",
          "evidence": [
            {
              "path": "scripts/run_output_eval.py",
              "exists": true
            },
            {
              "path": "reports/output_quality_scorecard.json",
              "exists": true
            },
            {
              "path": "tests/verify_output_eval_lab.py",
              "exists": true
            }
          ],
          "next_action": "Keep this item covered as the implementation evolves."
        },
        {
          "key": "output-quality-scorecard",
          "category": "recommended-pr",
          "label": "Output Quality Scorecard",
          "status": "pass",
          "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
          "current": "gate pass True",
          "command": "make ci-test",
          "test": "tests/verify_output_eval_lab.py",
          "evidence": [
            {
              "path": "reports/output_quality_scorecard.md",
              "exists": true
            },
            {
              "path": "reports/output_quality_scorecard.json",
              "exists": true
            },
            {
              "path": "tests/verify_output_eval_lab.py",
              "exists": true
            }
          ],
          "next_action": "Keep this item covered as the implementation evolves."
        },
        {
          "key": "skill-ir-v0",
          "category": "recommended-pr",
          "label": "Skill IR V0",
          "status": "pass",
          "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
          "current": "schema 2.0.0",
          "command": "make ci-test",
          "test": "tests/verify_skill_ir.py",
          "evidence": [
            {
              "path": "skill-ir/schema.json",
              "exists": true
            },
            {
              "path": "skill-ir/examples/yao-meta-skill.json",
              "exists": true
            },
            {
              "path": "tests/verify_skill_ir.py",
              "exists": true
            }
          ],
          "next_action": "Keep this item covered as the implementation evolves."
        },
        {
          "key": "compiler-refactor",
          "category": "recommended-pr",
          "label": "Compiler Refactor",
          "status": "pass",
          "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
          "current": "5/5 compiled targets",
          "command": "make ci-test",
          "test": "tests/verify_compile_skill.py",
          "evidence": [
            {
              "path": "scripts/compile_skill.py",
              "exists": true
            },
            {
              "path": "reports/compiled_targets.json",
              "exists": true
            },
            {
              "path": "tests/verify_compile_skill.py",
              "exists": true
            }
          ],
          "next_action": "Keep this item covered as the implementation evolves."
        },
        {
          "key": "agent-skills-conformance",
          "category": "recommended-pr",
          "label": "Agent Skills Conformance",
          "status": "pass",
          "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
          "current": "agent-skills target present",
          "command": "make ci-test",
          "test": "tests/verify_conformance_suite.py",
          "evidence": [
            {
              "path": "runtime/conformance/schema.json",
              "exists": true
            },
            {
              "path": "reports/conformance_matrix.json",
              "exists": true
            },
            {
              "path": "tests/verify_conformance_suite.py",
              "exists": true
            }
          ],
          "next_action": "Keep this item covered as the implementation evolves."
        },
        {
          "key": "trust-check",
          "category": "recommended-pr",
          "label": "Trust Check",
          "status": "pass",
          "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
          "current": "secret findings 0",
          "command": "make ci-test",
          "test": "tests/verify_trust_check.py",
          "evidence": [
            {
              "path": "scripts/trust_check.py",
              "exists": true
            },
            {
              "path": "reports/security_trust_report.json",
              "exists": true
            },
            {
              "path": "tests/verify_trust_check.py",
              "exists": true
            }
          ],
          "next_action": "Keep this item covered as the implementation evolves."
        },
        {
          "key": "skill-atlas-generator",
          "category": "recommended-pr",
          "label": "Skill Atlas Generator",
          "status": "pass",
          "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
          "current": "12 scanned skills",
          "command": "make ci-test",
          "test": "tests/verify_skill_atlas.py",
          "evidence": [
            {
              "path": "scripts/build_skill_atlas.py",
              "exists": true
            },
            {
              "path": "reports/skill_atlas.json",
              "exists": true
            },
            {
              "path": "tests/verify_skill_atlas.py",
              "exists": true
            }
          ],
          "next_action": "Keep this item covered as the implementation evolves."
        },
        {
          "key": "registry-package-format",
          "category": "recommended-pr",
          "label": "Registry Package Format",
          "status": "pass",
          "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
          "current": "registry ok True",
          "command": "make ci-test",
          "test": "tests/verify_registry_audit.py",
          "evidence": [
            {
              "path": "registry/package.schema.json",
              "exists": true
            },
            {
              "path": "reports/registry_audit.json",
              "exists": true
            },
            {
              "path": "tests/verify_registry_audit.py",
              "exists": true
            }
          ],
          "next_action": "Keep this item covered as the implementation evolves."
        },
        {
          "key": "review-studio-2",
          "category": "recommended-pr",
          "label": "Review Studio 2.0",
          "status": "pass",
          "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
          "current": "16 review gates",
          "command": "make ci-test",
          "test": "tests/verify_review_studio.py",
          "evidence": [
            {
              "path": "scripts/render_review_studio.py",
              "exists": true
            },
            {
              "path": "reports/review-studio.html",
              "exists": true
            },
            {
              "path": "tests/verify_review_studio.py",
              "exists": true
            }
          ],
          "next_action": "Keep this item covered as the implementation evolves."
        },
        {
          "key": "migration-v2-docs",
          "category": "recommended-pr",
          "label": "Migration V2 Docs",
          "status": "pass",
          "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
          "current": "migration guide present",
          "command": "make ci-test",
          "test": "docs review",
          "evidence": [
            {
              "path": "docs/migration-v2.md",
              "exists": true
            },
            {
              "path": "reports/skill-os-2-review.md",
              "exists": true
            },
            {
              "path": "README.md",
              "exists": true
            }
          ],
          "next_action": "Keep this item covered as the implementation evolves."
        }
      ],
      "reference_extension_tracks": [
        {
          "key": "skill-interpretation-report",
          "label": "Skill Interpretation Report",
          "status": "covered",
          "objective": "User-facing deep interpretation report explains use cases, triggers, inputs, outputs, workflow, principles, boundaries, quality gates, examples, and next iterations.",
          "current": "Skill Overview v2 is canonical and mirrored as first-class skill-interpretation HTML/JSON with schema and tests.",
          "target": "Either keep skill-overview as the canonical interpretation report with an explicit contract, or split a dedicated reports/skill-interpretation.* renderer and tests.",
          "evidence": [
            {
              "path": "reports/skill-overview.html",
              "exists": true
            },
            {
              "path": "reports/skill-overview.json",
              "exists": true
            },
            {
              "path": "scripts/render_skill_overview.py",
              "exists": true
            },
            {
              "path": "scripts/render_skill_interpretation.py",
              "exists": true
            },
            {
              "path": "schemas/skill-interpretation.schema.json",
              "exists": true
            },
            {
              "path": "tests/verify_skill_interpretation.py",
              "exists": true
            }
          ],
          "next_action": "Keep overview and interpretation contracts in lockstep when report sections, metrics, or layout semantics change."
        },
        {
          "key": "adaptive-self-iteration",
          "label": "Adaptive Self-Iteration",
          "status": "partial",
          "objective": "Local-first preference memory, repeated-signal extraction, adaptation proposals, approval, patch application, regression evidence, and rollback.",
          "current": "Proposal-only adapt-scan/adapt-propose foundation exists with policy, schema, and safety tests; approval-gated patch application is not implemented yet.",
          "target": "Proposal-only adaptation with explicit input source, redaction, allowlisted write targets, approval ledger, regression report, and rollback plan.",
          "evidence": [
            {
              "path": "references/autonomous-adaptation.md",
              "exists": true
            },
            {
              "path": "references/user-memory-policy.md",
              "exists": true
            },
            {
              "path": "schemas/adaptation-proposal.schema.json",
              "exists": true
            },
            {
              "path": "scripts/summarize_user_signals.py",
              "exists": true
            },
            {
              "path": "scripts/propose_adaptation.py",
              "exists": true
            },
            {
              "path": "tests/verify_adaptation_safety.py",
              "exists": true
            },
            {
              "path": "scripts/apply_adaptation.py",
              "exists": false
            },
            {
              "path": "reports/adaptation_approval_ledger.json",
              "exists": false
            },
            {
              "path": "reports/adaptation_regression_report.json",
              "exists": false
            },
            {
              "path": "reports/user_patterns.json",
              "exists": true
            },
            {
              "path": "reports/adaptation_proposals.json",
              "exists": true
            },
            {
              "path": "reports/iteration-directions.md",
              "exists": true
            },
            {
              "path": "reports/adoption_drift_report.md",
              "exists": true
            }
          ],
          "next_action": "Add adapt-apply only after approval ledger, allowlisted targets, dry-run diffs, regression reports, and rollback artifacts are designed."
        }
      ],
      "next_highest_leverage": [
        "Close the four world-class evidence ledger entries with accepted human or external evidence.",
        "Keep the first-class skill interpretation report and Skill Overview v2 contract synchronized as the report model evolves.",
        "Start adaptive self-iteration as explicit-source, proposal-only, approval-gated work; do not scan private logs by default.",
        "Keep the blueprint coverage report in CI so 2.0 plan drift is visible."
      ],
      "source_blueprint": {
        "title": "Skill Overview / Skill OS 2.0 upgrade plan",
        "core_module_count": 8,
        "recommended_pr_count": 12,
        "reference_extension_count": 2,
        "reference_extensions": [
          "Skill interpretation report",
          "Adaptive self-iteration with local preference memory and approval gates"
        ]
      },
      "artifacts": {
        "json": "reports/skill_os2_coverage.json",
        "markdown": "reports/skill_os2_coverage.md"
      }
    },
    "compiled_targets": {
      "schema_version": "1.0",
      "ok": true,
      "generated_at": "2026-06-13",
      "skill_dir": ".",
      "summary": {
        "target_count": 5,
        "pass_count": 5,
        "warn_count": 0,
        "block_count": 0,
        "failure_count": 0,
        "warning_count": 0
      },
      "targets": [
        {
          "schema_version": "1.0",
          "target": "openai",
          "status": "pass",
          "compiler": {
            "name": "yao-skill-ir-compiler",
            "schema_version": "1.0",
            "source": "skill-ir",
            "ir_source": "skill-ir/examples/yao-meta-skill.json",
            "ir_schema_version": "2.0.0"
          },
          "source": {
            "skill_dir": ".",
            "canonical_metadata": "agents/interface.yaml",
            "declared_targets": [
              "openai",
              "claude",
              "generic",
              "agent-skills-compatible",
              "vscode"
            ]
          },
          "compiled_contract": {
            "name": "yao-meta-skill",
            "title": "Yao Meta Skill",
            "version": "1.1.0",
            "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
            "job_to_be_done": "Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse.",
            "trigger": {
              "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
              "should_trigger": [
                "Create a skill from this repeated workflow.",
                "Turn this runbook into a reusable agent skill.",
                "Convert this process note into a reusable skill package for the team.",
                "Improve this skill description and add evals.",
                "Refactor this prompt into a proper skill package.",
                "Package this skill for team reuse.",
                "Create a meta-skill for packaging internal workflows.",
                "Standardize this recurring workflow as a shareable skill package with references."
              ],
              "should_not_trigger": [
                "Explain what a workflow is.",
                "Just explain what a skill is.",
                "Summarize this random note.",
                "Translate this README into Japanese.",
                "Write a product headline for this landing page.",
                "Draft a blog title for this article.",
                "Rewrite this paragraph more clearly, but do not package anything.",
                "Explain the difference between a runbook and a workflow.",
                "one-off writing, translation, explanation, or brainstorming requests that do not need a reusable skill",
                "general code review or debugging unless the user is packaging that workflow as a skill"
              ],
              "edge_cases": [
                "Create a one-off prompt for this task.",
                "Write a custom answer for this request without creating a skill package.",
                "Help me brainstorm process ideas without building a skill.",
                "Improve this README but do not turn it into a skill.",
                "Make a checklist for this task, but not a reusable skill.",
                "Create a reusable-looking checklist, but keep it as a plain note instead of a skill.",
                "Review this process note and explain it, no packaging needed.",
                "Turn this into a checklist and template, but stop short of making a full skill."
              ]
            },
            "workflow": {
              "steps": [
                "Decide whether the request should become a skill and choose the lightest fit.",
                "Capture job, output, exclusions, constraints, and standards.",
                "Run reference scan: external benchmarks first, user references second, local fit third; surface only uncertainty or conflict.",
                "Write the `description` early and test route quality before expanding the package.",
                "Add output-risk, artifact-design, prompt-quality, and system-model reports only when they matter.",
                "Add only folders and gates that earn their keep.",
                "Surface the top three next iteration directions."
              ],
              "decision_points": [
                "Route by frontmatter `description`.",
                "Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.",
                "Use the lightest reliable process.",
                "`Scaffold`: exploratory or personal.",
                "`Production`: team reuse.",
                "`Library`: shared infrastructure.",
                "`Governed`: high-trust, policy-sensitive, or release-critical.",
                "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.",
                "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.",
                "Do not silently broaden the skill into adjacent jobs just because the examples are nearby."
              ],
              "failure_modes": [
                "Tables can render as dense grids with weak hierarchy or poor mobile readability.",
                "Long bullets can make the output look complete while hiding the actual decision logic.",
                "Footnote markers or dense citation notes can interrupt the reading flow.",
                "Evidence can be over-attached to obvious statements and under-attached to risky claims.",
                "Screenshots can be captured from the wrong state, wrong viewport, or wrong crop.",
                "Missing screenshots can cause the skill to invent visual references instead of declaring the gap.",
                "Users start invoking the skill for adjacent one-off or explanation-only requests.",
                "Outputs remain valid but become generic, cluttered, or weakly aligned with the user's domain.",
                "Borrowed benchmark patterns no longer fit the local job or add ceremony without payoff.",
                "Skill usage becomes team-critical while ownership, review cadence, or rollback evidence stays informal."
              ]
            },
            "resources": {
              "references": [
                "references/artifact-design-doctrine.md",
                "references/authoring-discipline.md",
                "references/autonomous-adaptation.md",
                "references/distribution-registry-method.md",
                "references/eval-playbook.md",
                "references/gate-selection.md",
                "references/governance.md",
                "references/human-review-template.md",
                "references/intent-dialogue.md",
                "references/iteration-philosophy.md",
                "references/non-skill-decision-tree.md",
                "references/operating-modes.md",
                "references/output-eval-method.md",
                "references/output-quality-risk.md",
                "references/output-visual-quality.md",
                "references/packaging-contracts.md",
                "references/pattern-extraction-doctrine.md",
                "references/platform-capability-matrix.md",
                "references/prompt-engineering-doctrine.md",
                "references/qa-ladder.md",
                "references/reference-scan.md",
                "references/regression-cause-taxonomy.md",
                "references/resource-boundaries.md",
                "references/review-studio-method.md",
                "references/review-waiver-method.md",
                "references/runtime-conformance-method.md",
                "references/skill-archetypes.md",
                "references/skill-atlas-method.md",
                "references/skill-engineering-method.md",
                "references/skill-ir-method.md",
                "references/systems-thinking-doctrine.md",
                "references/telemetry-drift-method.md",
                "references/trust-security-method.md",
                "references/user-memory-policy.md"
              ],
              "scripts": [
                "scripts/adjudicate_output_review.py",
                "scripts/build_confusion_matrix.py",
                "scripts/build_skill_atlas.py",
                "scripts/check_update.py",
                "scripts/ci_test.py",
                "scripts/collect_feedback.py",
                "scripts/compile_skill.py",
                "scripts/context_sizer.py",
                "scripts/create_iteration_snapshot.py",
                "scripts/cross_packager.py",
                "scripts/diff_eval.py",
                "scripts/emit_telemetry_event.py",
                "scripts/export_skill_ir.py",
                "scripts/github_benchmark_scan.py",
                "scripts/governance_check.py",
                "scripts/html_rendering.py",
                "scripts/import_telemetry_events.py",
                "scripts/init_skill.py",
                "scripts/judge_blind_eval.py",
                "scripts/lint_skill.py",
                "scripts/local_output_eval_runner.py",
                "scripts/optimize_description.py",
                "scripts/prepare_output_review_kit.py",
                "scripts/prepare_world_class_submission_kit.py",
                "scripts/probe_runtime_permissions.py",
                "scripts/promotion_checker.py",
                "scripts/propose_adaptation.py",
                "scripts/provider_output_eval_runner.py",
                "scripts/python_compat_check.py",
                "scripts/registry_audit.py",
                "scripts/render_adoption_drift_report.py",
                "scripts/render_architecture_maintainability.py",
                "scripts/render_artifact_design_profile.py",
                "scripts/render_baseline_compare.py",
                "scripts/render_benchmark_reproducibility.py",
                "scripts/render_context_reports.py",
                "scripts/render_description_drift_history.py",
                "scripts/render_eval_dashboard.py",
                "scripts/render_intent_confidence.py",
                "scripts/render_intent_dialogue.py",
                "scripts/render_iteration_directions.py",
                "scripts/render_iteration_ledger.py",
                "scripts/render_output_risk_profile.py",
                "scripts/render_portability_report.py",
                "scripts/render_prompt_quality_profile.py",
                "scripts/render_reference_scan.py",
                "scripts/render_reference_synthesis.py",
                "scripts/render_regression_history.py",
                "scripts/render_review_annotations.py",
                "scripts/render_review_studio.py",
                "scripts/render_review_viewer.py",
                "scripts/render_review_waivers.py",
                "scripts/render_skill_os2_audit.py",
                "scripts/render_skill_os2_coverage.py",
                "scripts/render_skill_overview.py",
                "scripts/render_social_preview.py",
                "scripts/render_system_model.py",
                "scripts/render_telemetry_hook_recipes.py",
                "scripts/render_world_class_claim_guard.py",
                "scripts/render_world_class_evidence_intake.py",
                "scripts/render_world_class_evidence_ledger.py",
                "scripts/render_world_class_evidence_plan.py",
                "scripts/render_world_class_operator_runbook.py",
                "scripts/render_world_class_submission_review.py",
                "scripts/resource_boundary_check.py",
                "scripts/review_studio_action_evidence.py",
                "scripts/review_studio_actions.py",
                "scripts/review_studio_data.py",
                "scripts/review_studio_formatting.py",
                "scripts/review_studio_gates.py",
                "scripts/review_studio_layout.py",
                "scripts/review_studio_output_review.py",
                "scripts/review_studio_waivers.py",
                "scripts/review_studio_world_class.py",
                "scripts/review_viewer_data.py",
                "scripts/run_conformance_suite.py",
                "scripts/run_description_optimization_suite.py",
                "scripts/run_eval_suite.py",
                "scripts/run_output_eval.py",
                "scripts/run_output_execution.py"
              ],
              "assets": [
                "templates/basic_skill.md.j2",
                "templates/complex_skill.md.j2"
              ],
              "reports": [
                "reports/benchmark_methodology.md",
                "reports/intent-context.json",
                "reports/intent-confidence.json",
                "reports/intent-confidence.md",
                "reports/reference-synthesis.json",
                "reports/reference-synthesis.md",
                "reports/output-risk-profile.json",
                "reports/output-risk-profile.md",
                "reports/artifact-design-profile.json",
                "reports/artifact-design-profile.md",
                "reports/prompt-quality-profile.json",
                "reports/prompt-quality-profile.md",
                "reports/system-model.json",
                "reports/system-model.md",
                "reports/iteration-directions.json",
                "reports/iteration-directions.md",
                "reports/skill-overview.json",
                "reports/skill-overview.html",
                "reports/output_quality_scorecard.json",
                "reports/output_quality_scorecard.md",
                "reports/output_execution_runs.json",
                "reports/output_execution_runs.md",
                "reports/output_blind_review_pack.json",
                "reports/output_blind_review_pack.md",
                "reports/output_blind_answer_key.json",
                "reports/output_review_adjudication.json",
                "reports/output_review_adjudication.md",
                "reports/review_annotations.json",
                "reports/review_annotations.md",
                "reports/conformance_matrix.json",
                "reports/conformance_matrix.md",
                "reports/security_trust_report.json",
                "reports/security_trust_report.md",
                "reports/runtime_permission_probes.json",
                "reports/runtime_permission_probes.md",
                "reports/telemetry_hook_recipes.json",
                "reports/telemetry_hook_recipes.md",
                "reports/skill_atlas.json",
                "reports/skill_atlas.html",
                "reports/skill-os-2-review.md",
                "reports/portability_score.json",
                "reports/portability_score.md",
                "reports/governance_score.json"
              ],
              "counts": {
                "references": 34,
                "scripts": 80,
                "assets": 2,
                "reports": 43
              }
            },
            "eval_plan": {
              "trigger": [
                "evals/README.md",
                "evals/adaptation/user_signals.example.jsonl",
                "evals/adversarial/trigger_cases.json",
                "evals/blind_holdout/trigger_cases.json",
                "evals/confusion/route_cases.json",
                "evals/dev/trigger_cases.json",
                "evals/failure-cases.md",
                "evals/history/2026-03-31-context-first-pack.json",
                "evals/history/2026-03-31-family-suite-expansion.json",
                "evals/history/2026-03-31-governance-quality-gates.json",
                "evals/history/2026-03-31-governed-assets-and-history.json",
                "evals/history/2026-04-01-route-scorecard-foundation.json",
                "evals/history/README.md",
                "evals/history/description_optimization/2026-03-31-description-optimization-suite.json",
                "evals/history/description_optimization/2026-04-01-adversarial-calibration-and-family-drift.json",
                "evals/history/description_optimization/2026-04-01-blind-holdout-and-drift-history.json",
                "evals/history/description_optimization/2026-04-01-judge-backed-blind-eval.json",
                "evals/history/description_optimization/README.md",
                "evals/holdout/trigger_cases.json",
                "evals/output/cases.jsonl",
                "evals/output/fixtures/release-brief-source.md",
                "evals/output/schema.json",
                "evals/packaging_expectations.json",
                "evals/promotion_policy.md",
                "evals/semantic_config.json",
                "evals/train/trigger_cases.json",
                "evals/trigger_cases.json"
              ],
              "output": [
                "evals/output/cases.jsonl",
                "evals/output/fixtures/release-brief-source.md",
                "evals/output/schema.json"
              ],
              "adversarial": [
                "evals/adversarial/trigger_cases.json"
              ],
              "baseline": "without_skill",
              "counts": {
                "trigger": 27,
                "output": 3,
                "adversarial": 1,
                "baseline": 1
              }
            },
            "risk": {
              "output_risk": "high",
              "execution_risk": "medium",
              "trust_boundary": "external"
            },
            "governance": {
              "owner": "Yao Team",
              "maturity": "governed",
              "review_cadence": "quarterly",
              "review_due": ""
            },
            "runtime": {
              "activation": {
                "mode": "manual",
                "paths": []
              },
              "execution": {
                "context": "inline",
                "shell": "bash"
              },
              "trust": {
                "source_tier": "local",
                "remote_inline_execution": "forbid",
                "remote_metadata_policy": "allow-metadata-only"
              },
              "adapter_targets": [
                "openai",
                "claude",
                "generic",
                "vscode"
              ],
              "canonical_format": "agent-skills"
            },
            "permissions": {
              "schema_version": "1.0",
              "source": "reports/security_trust_report.json",
              "source_available": true,
              "declared_capabilities": [
                "network",
                "file_write",
                "subprocess"
              ],
              "review_required": true,
              "capabilities": {
                "network": {
                  "required": true,
                  "script_count": 3,
                  "scripts": [
                    "scripts/check_update.py",
                    "scripts/github_benchmark_scan.py",
                    "scripts/provider_output_eval_runner.py"
                  ],
                  "review_reason": "Outbound hosts must match security/network_policy.json."
                },
                "file_write": {
                  "required": true,
                  "script_count": 67,
                  "scripts": [
                    "scripts/adjudicate_output_review.py",
                    "scripts/build_confusion_matrix.py",
                    "scripts/build_skill_atlas.py",
                    "scripts/check_update.py",
                    "scripts/ci_test.py",
                    "scripts/collect_feedback.py",
                    "scripts/compile_skill.py",
                    "scripts/create_iteration_snapshot.py",
                    "scripts/cross_packager.py",
                    "scripts/emit_telemetry_event.py",
                    "scripts/export_skill_ir.py",
                    "scripts/github_benchmark_scan.py",
                    "scripts/import_telemetry_events.py",
                    "scripts/init_skill.py",
                    "scripts/prepare_output_review_kit.py",
                    "scripts/prepare_world_class_submission_kit.py",
                    "scripts/probe_runtime_permissions.py",
                    "scripts/promotion_checker.py",
                    "scripts/propose_adaptation.py",
                    "scripts/python_compat_check.py",
                    "scripts/registry_audit.py",
                    "scripts/render_adoption_drift_report.py",
                    "scripts/render_architecture_maintainability.py",
                    "scripts/render_artifact_design_profile.py",
                    "scripts/render_baseline_compare.py",
                    "scripts/render_benchmark_reproducibility.py",
                    "scripts/render_context_reports.py",
                    "scripts/render_description_drift_history.py",
                    "scripts/render_eval_dashboard.py",
                    "scripts/render_intent_confidence.py",
                    "scripts/render_intent_dialogue.py",
                    "scripts/render_iteration_directions.py",
                    "scripts/render_iteration_ledger.py",
                    "scripts/render_output_risk_profile.py",
                    "scripts/render_portability_report.py",
                    "scripts/render_prompt_quality_profile.py",
                    "scripts/render_reference_scan.py",
                    "scripts/render_reference_synthesis.py",
                    "scripts/render_regression_history.py",
                    "scripts/render_review_annotations.py",
                    "scripts/render_review_studio.py",
                    "scripts/render_review_viewer.py",
                    "scripts/render_review_waivers.py",
                    "scripts/render_skill_interpretation.py",
                    "scripts/render_skill_os2_audit.py",
                    "scripts/render_skill_os2_coverage.py",
                    "scripts/render_skill_overview.py",
                    "scripts/render_social_preview.py",
                    "scripts/render_system_model.py",
                    "scripts/render_telemetry_hook_recipes.py",
                    "scripts/render_world_class_claim_guard.py",
                    "scripts/render_world_class_evidence_intake.py",
                    "scripts/render_world_class_evidence_ledger.py",
                    "scripts/render_world_class_evidence_plan.py",
                    "scripts/render_world_class_operator_runbook.py",
                    "scripts/render_world_class_submission_review.py",
                    "scripts/run_conformance_suite.py",
                    "scripts/run_description_optimization_suite.py",
                    "scripts/run_output_eval.py",
                    "scripts/run_output_execution.py",
                    "scripts/simulate_install.py",
                    "scripts/summarize_user_signals.py",
                    "scripts/sync_local_install.py",
                    "scripts/telemetry_native_host.py",
                    "scripts/trust_check.py",
                    "scripts/upgrade_check.py",
                    "scripts/verify_package.py"
                  ],
                  "review_reason": "Scripts write local files or generated artifacts."
                },
                "subprocess": {
                  "required": true,
                  "script_count": 9,
                  "scripts": [
                    "scripts/ci_test.py",
                    "scripts/render_benchmark_reproducibility.py",
                    "scripts/render_eval_dashboard.py",
                    "scripts/run_eval_suite.py",
                    "scripts/run_output_execution.py",
                    "scripts/sync_local_install.py",
                    "scripts/trust_check.py",
                    "scripts/yao.py",
                    "scripts/yao_cli_runtime.py"
                  ],
                  "review_reason": "Scripts spawn local commands and need operator review."
                },
                "interactive": {
                  "required": false,
                  "script_count": 0,
                  "scripts": [],
                  "review_reason": ""
                }
              },
              "network_policy": {
                "source": "security/network_policy.json",
                "covered_scripts": [
                  "scripts/check_update.py",
                  "scripts/github_benchmark_scan.py",
                  "scripts/provider_output_eval_runner.py"
                ],
                "missing_scripts": [],
                "mismatches": []
              },
              "help_smoke": {
                "enabled": true,
                "checked_count": 80,
                "failed_count": 0,
                "failed_scripts": []
              },
              "trust_summary": {
                "secret_findings": 0,
                "network_script_count": 3,
                "file_write_script_count": 67,
                "subprocess_script_count": 9,
                "interactive_script_count": 0,
                "help_smoke_failed_count": 0
              }
            },
            "source_files_count": 6,
            "target": "openai",
            "target_permission_contract": {
              "schema_version": "1.0",
              "target": "openai",
              "permission_model": "metadata-only",
              "native_enforcement": false,
              "representation": "targets/openai/agents/openai.yaml::compatibility.permission_contract plus adapter.json",
              "review_required": true,
              "declared_capabilities": [
                "network",
                "file_write",
                "subprocess"
              ],
              "capability_counts": {
                "network": 3,
                "file_write": 67,
                "subprocess": 9,
                "interactive": 0
              },
              "evidence": "reports/security_trust_report.json",
              "operator_note": "OpenAI target carries permission metadata for reviewer visibility; host enforcement remains outside the package."
            },
            "target_native_contract": {
              "schema_version": "1.0",
              "target": "openai",
              "native_surface": "OpenAI-style interface metadata plus neutral Agent Skills source",
              "activation": {
                "policy": "Use frontmatter description for catalog routing and targets/openai/agents/openai.yaml for display name, default prompt, and compatibility metadata.",
                "trigger_description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
                "manual_activation_supported": true,
                "automatic_activation_note": "Depends on the target client route/catalog implementation."
              },
              "resources": {
                "strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.",
                "counts": {
                  "references": 34,
                  "scripts": 80,
                  "assets": 2,
                  "reports": 43
                },
                "generated_files": [
                  "targets/openai/adapter.json",
                  "targets/openai/agents/openai.yaml"
                ]
              },
              "scripts": {
                "strategy": "Keep scripts as local package resources; expose help-smoke and permission metadata for reviewer approval before execution.",
                "script_count": 80,
                "help_smoke_failed_count": 0
              },
              "permissions": {
                "enforcement": "metadata-only",
                "native_enforcement": false,
                "declared_capabilities": [
                  "network",
                  "file_write",
                  "subprocess"
                ],
                "review_required": true
              },
              "review": {
                "artifacts": [
                  "targets/openai/agents/openai.yaml",
                  "targets/openai/adapter.json",
                  "reports/review-studio.html"
                ],
                "fallback_behavior": "If OpenAI-native metadata is ignored, the package remains readable as neutral Agent Skills source.",
                "unsupported_native_features": [
                  "client-native permission prompts",
                  "provider-executed scripts",
                  "client-native script permission prompts are represented as permission contract metadata"
                ]
              },
              "install_scope": "plugin or skill package consumer"
            },
            "degradation_strategy": "metadata-adapter",
            "target_runtime": {
              "adapter_mode": "metadata-adapter",
              "generated_files": [
                "targets/openai/adapter.json",
                "targets/openai/agents/openai.yaml"
              ],
              "metadata_mapping": {
                "display_name": "targets/openai/agents/openai.yaml::interface.display_name",
                "default_prompt": "targets/openai/agents/openai.yaml::interface.default_prompt",
                "activation": "targets/openai/agents/openai.yaml::compatibility.activation_mode",
                "execution": "targets/openai/agents/openai.yaml::compatibility.execution_context",
                "trust": "targets/openai/agents/openai.yaml::compatibility.trust_level",
                "permissions": "targets/openai/agents/openai.yaml::compatibility.permission_contract",
                "degradation": "targets/openai/agents/openai.yaml::compatibility.degradation_strategy"
              },
              "preserved_semantics": [
                "trigger",
                "workflow-counts",
                "resources",
                "eval-plan",
                "risk",
                "governance",
                "runtime",
                "trust",
                "permissions"
              ],
              "native_surface": "OpenAI-style interface metadata plus neutral Agent Skills source"
            }
          },
          "permission_contract": {
            "schema_version": "1.0",
            "source": "reports/security_trust_report.json",
            "source_available": true,
            "declared_capabilities": [
              "network",
              "file_write",
              "subprocess"
            ],
            "review_required": true,
            "capabilities": {
              "network": {
                "required": true,
                "script_count": 3,
                "scripts": [
                  "scripts/check_update.py",
                  "scripts/github_benchmark_scan.py",
                  "scripts/provider_output_eval_runner.py"
                ],
                "review_reason": "Outbound hosts must match security/network_policy.json."
              },
              "file_write": {
                "required": true,
                "script_count": 67,
                "scripts": [
                  "scripts/adjudicate_output_review.py",
                  "scripts/build_confusion_matrix.py",
                  "scripts/build_skill_atlas.py",
                  "scripts/check_update.py",
                  "scripts/ci_test.py",
                  "scripts/collect_feedback.py",
                  "scripts/compile_skill.py",
                  "scripts/create_iteration_snapshot.py",
                  "scripts/cross_packager.py",
                  "scripts/emit_telemetry_event.py",
                  "scripts/export_skill_ir.py",
                  "scripts/github_benchmark_scan.py",
                  "scripts/import_telemetry_events.py",
                  "scripts/init_skill.py",
                  "scripts/prepare_output_review_kit.py",
                  "scripts/prepare_world_class_submission_kit.py",
                  "scripts/probe_runtime_permissions.py",
                  "scripts/promotion_checker.py",
                  "scripts/propose_adaptation.py",
                  "scripts/python_compat_check.py",
                  "scripts/registry_audit.py",
                  "scripts/render_adoption_drift_report.py",
                  "scripts/render_architecture_maintainability.py",
                  "scripts/render_artifact_design_profile.py",
                  "scripts/render_baseline_compare.py",
                  "scripts/render_benchmark_reproducibility.py",
                  "scripts/render_context_reports.py",
                  "scripts/render_description_drift_history.py",
                  "scripts/render_eval_dashboard.py",
                  "scripts/render_intent_confidence.py",
                  "scripts/render_intent_dialogue.py",
                  "scripts/render_iteration_directions.py",
                  "scripts/render_iteration_ledger.py",
                  "scripts/render_output_risk_profile.py",
                  "scripts/render_portability_report.py",
                  "scripts/render_prompt_quality_profile.py",
                  "scripts/render_reference_scan.py",
                  "scripts/render_reference_synthesis.py",
                  "scripts/render_regression_history.py",
                  "scripts/render_review_annotations.py",
                  "scripts/render_review_studio.py",
                  "scripts/render_review_viewer.py",
                  "scripts/render_review_waivers.py",
                  "scripts/render_skill_interpretation.py",
                  "scripts/render_skill_os2_audit.py",
                  "scripts/render_skill_os2_coverage.py",
                  "scripts/render_skill_overview.py",
                  "scripts/render_social_preview.py",
                  "scripts/render_system_model.py",
                  "scripts/render_telemetry_hook_recipes.py",
                  "scripts/render_world_class_claim_guard.py",
                  "scripts/render_world_class_evidence_intake.py",
                  "scripts/render_world_class_evidence_ledger.py",
                  "scripts/render_world_class_evidence_plan.py",
                  "scripts/render_world_class_operator_runbook.py",
                  "scripts/render_world_class_submission_review.py",
                  "scripts/run_conformance_suite.py",
                  "scripts/run_description_optimization_suite.py",
                  "scripts/run_output_eval.py",
                  "scripts/run_output_execution.py",
                  "scripts/simulate_install.py",
                  "scripts/summarize_user_signals.py",
                  "scripts/sync_local_install.py",
                  "scripts/telemetry_native_host.py",
                  "scripts/trust_check.py",
                  "scripts/upgrade_check.py",
                  "scripts/verify_package.py"
                ],
                "review_reason": "Scripts write local files or generated artifacts."
              },
              "subprocess": {
                "required": true,
                "script_count": 9,
                "scripts": [
                  "scripts/ci_test.py",
                  "scripts/render_benchmark_reproducibility.py",
                  "scripts/render_eval_dashboard.py",
                  "scripts/run_eval_suite.py",
                  "scripts/run_output_execution.py",
                  "scripts/sync_local_install.py",
                  "scripts/trust_check.py",
                  "scripts/yao.py",
                  "scripts/yao_cli_runtime.py"
                ],
                "review_reason": "Scripts spawn local commands and need operator review."
              },
              "interactive": {
                "required": false,
                "script_count": 0,
                "scripts": [],
                "review_reason": ""
              }
            },
            "network_policy": {
              "source": "security/network_policy.json",
              "covered_scripts": [
                "scripts/check_update.py",
                "scripts/github_benchmark_scan.py",
                "scripts/provider_output_eval_runner.py"
              ],
              "missing_scripts": [],
              "mismatches": []
            },
            "help_smoke": {
              "enabled": true,
              "checked_count": 80,
              "failed_count": 0,
              "failed_scripts": []
            },
            "trust_summary": {
              "secret_findings": 0,
              "network_script_count": 3,
              "file_write_script_count": 67,
              "subprocess_script_count": 9,
              "interactive_script_count": 0,
              "help_smoke_failed_count": 0
            }
          },
          "target_permission_contract": {
            "schema_version": "1.0",
            "target": "openai",
            "permission_model": "metadata-only",
            "native_enforcement": false,
            "representation": "targets/openai/agents/openai.yaml::compatibility.permission_contract plus adapter.json",
            "review_required": true,
            "declared_capabilities": [
              "network",
              "file_write",
              "subprocess"
            ],
            "capability_counts": {
              "network": 3,
              "file_write": 67,
              "subprocess": 9,
              "interactive": 0
            },
            "evidence": "reports/security_trust_report.json",
            "operator_note": "OpenAI target carries permission metadata for reviewer visibility; host enforcement remains outside the package."
          },
          "target_native_contract": {
            "schema_version": "1.0",
            "target": "openai",
            "native_surface": "OpenAI-style interface metadata plus neutral Agent Skills source",
            "activation": {
              "policy": "Use frontmatter description for catalog routing and targets/openai/agents/openai.yaml for display name, default prompt, and compatibility metadata.",
              "trigger_description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
              "manual_activation_supported": true,
              "automatic_activation_note": "Depends on the target client route/catalog implementation."
            },
            "resources": {
              "strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.",
              "counts": {
                "references": 34,
                "scripts": 80,
                "assets": 2,
                "reports": 43
              },
              "generated_files": [
                "targets/openai/adapter.json",
                "targets/openai/agents/openai.yaml"
              ]
            },
            "scripts": {
              "strategy": "Keep scripts as local package resources; expose help-smoke and permission metadata for reviewer approval before execution.",
              "script_count": 80,
              "help_smoke_failed_count": 0
            },
            "permissions": {
              "enforcement": "metadata-only",
              "native_enforcement": false,
              "declared_capabilities": [
                "network",
                "file_write",
                "subprocess"
              ],
              "review_required": true
            },
            "review": {
              "artifacts": [
                "targets/openai/agents/openai.yaml",
                "targets/openai/adapter.json",
                "reports/review-studio.html"
              ],
              "fallback_behavior": "If OpenAI-native metadata is ignored, the package remains readable as neutral Agent Skills source.",
              "unsupported_native_features": [
                "client-native permission prompts",
                "provider-executed scripts",
                "client-native script permission prompts are represented as permission contract metadata"
              ]
            },
            "install_scope": "plugin or skill package consumer"
          },
          "target_transform": {
            "target": "openai",
            "adapter_mode": "metadata-adapter",
            "generated_files": [
              "targets/openai/adapter.json",
              "targets/openai/agents/openai.yaml"
            ],
            "metadata_mapping": {
              "display_name": "targets/openai/agents/openai.yaml::interface.display_name",
              "default_prompt": "targets/openai/agents/openai.yaml::interface.default_prompt",
              "activation": "targets/openai/agents/openai.yaml::compatibility.activation_mode",
              "execution": "targets/openai/agents/openai.yaml::compatibility.execution_context",
              "trust": "targets/openai/agents/openai.yaml::compatibility.trust_level",
              "permissions": "targets/openai/agents/openai.yaml::compatibility.permission_contract",
              "degradation": "targets/openai/agents/openai.yaml::compatibility.degradation_strategy"
            },
            "preserved_semantics": [
              "trigger",
              "workflow-counts",
              "resources",
              "eval-plan",
              "risk",
              "governance",
              "runtime",
              "trust",
              "permissions"
            ],
            "degradation_strategy": "metadata-adapter",
            "permission_representation": "targets/openai/agents/openai.yaml::compatibility.permission_contract plus adapter.json",
            "native_surface": "OpenAI-style interface metadata plus neutral Agent Skills source",
            "activation_policy": "Use frontmatter description for catalog routing and targets/openai/agents/openai.yaml for display name, default prompt, and compatibility metadata.",
            "resource_strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.",
            "script_strategy": "Keep scripts as local package resources; expose help-smoke and permission metadata for reviewer approval before execution.",
            "permission_enforcement": "metadata-only"
          },
          "unsupported_features": [
            "client-native script permission prompts are represented as permission contract metadata"
          ],
          "warnings": [],
          "failures": []
        },
        {
          "schema_version": "1.0",
          "target": "claude",
          "status": "pass",
          "compiler": {
            "name": "yao-skill-ir-compiler",
            "schema_version": "1.0",
            "source": "skill-ir",
            "ir_source": "skill-ir/examples/yao-meta-skill.json",
            "ir_schema_version": "2.0.0"
          },
          "source": {
            "skill_dir": ".",
            "canonical_metadata": "agents/interface.yaml",
            "declared_targets": [
              "openai",
              "claude",
              "generic",
              "agent-skills-compatible",
              "vscode"
            ]
          },
          "compiled_contract": {
            "name": "yao-meta-skill",
            "title": "Yao Meta Skill",
            "version": "1.1.0",
            "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
            "job_to_be_done": "Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse.",
            "trigger": {
              "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
              "should_trigger": [
                "Create a skill from this repeated workflow.",
                "Turn this runbook into a reusable agent skill.",
                "Convert this process note into a reusable skill package for the team.",
                "Improve this skill description and add evals.",
                "Refactor this prompt into a proper skill package.",
                "Package this skill for team reuse.",
                "Create a meta-skill for packaging internal workflows.",
                "Standardize this recurring workflow as a shareable skill package with references."
              ],
              "should_not_trigger": [
                "Explain what a workflow is.",
                "Just explain what a skill is.",
                "Summarize this random note.",
                "Translate this README into Japanese.",
                "Write a product headline for this landing page.",
                "Draft a blog title for this article.",
                "Rewrite this paragraph more clearly, but do not package anything.",
                "Explain the difference between a runbook and a workflow.",
                "one-off writing, translation, explanation, or brainstorming requests that do not need a reusable skill",
                "general code review or debugging unless the user is packaging that workflow as a skill"
              ],
              "edge_cases": [
                "Create a one-off prompt for this task.",
                "Write a custom answer for this request without creating a skill package.",
                "Help me brainstorm process ideas without building a skill.",
                "Improve this README but do not turn it into a skill.",
                "Make a checklist for this task, but not a reusable skill.",
                "Create a reusable-looking checklist, but keep it as a plain note instead of a skill.",
                "Review this process note and explain it, no packaging needed.",
                "Turn this into a checklist and template, but stop short of making a full skill."
              ]
            },
            "workflow": {
              "steps": [
                "Decide whether the request should become a skill and choose the lightest fit.",
                "Capture job, output, exclusions, constraints, and standards.",
                "Run reference scan: external benchmarks first, user references second, local fit third; surface only uncertainty or conflict.",
                "Write the `description` early and test route quality before expanding the package.",
                "Add output-risk, artifact-design, prompt-quality, and system-model reports only when they matter.",
                "Add only folders and gates that earn their keep.",
                "Surface the top three next iteration directions."
              ],
              "decision_points": [
                "Route by frontmatter `description`.",
                "Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.",
                "Use the lightest reliable process.",
                "`Scaffold`: exploratory or personal.",
                "`Production`: team reuse.",
                "`Library`: shared infrastructure.",
                "`Governed`: high-trust, policy-sensitive, or release-critical.",
                "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.",
                "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.",
                "Do not silently broaden the skill into adjacent jobs just because the examples are nearby."
              ],
              "failure_modes": [
                "Tables can render as dense grids with weak hierarchy or poor mobile readability.",
                "Long bullets can make the output look complete while hiding the actual decision logic.",
                "Footnote markers or dense citation notes can interrupt the reading flow.",
                "Evidence can be over-attached to obvious statements and under-attached to risky claims.",
                "Screenshots can be captured from the wrong state, wrong viewport, or wrong crop.",
                "Missing screenshots can cause the skill to invent visual references instead of declaring the gap.",
                "Users start invoking the skill for adjacent one-off or explanation-only requests.",
                "Outputs remain valid but become generic, cluttered, or weakly aligned with the user's domain.",
                "Borrowed benchmark patterns no longer fit the local job or add ceremony without payoff.",
                "Skill usage becomes team-critical while ownership, review cadence, or rollback evidence stays informal."
              ]
            },
            "resources": {
              "references": [
                "references/artifact-design-doctrine.md",
                "references/authoring-discipline.md",
                "references/autonomous-adaptation.md",
                "references/distribution-registry-method.md",
                "references/eval-playbook.md",
                "references/gate-selection.md",
                "references/governance.md",
                "references/human-review-template.md",
                "references/intent-dialogue.md",
                "references/iteration-philosophy.md",
                "references/non-skill-decision-tree.md",
                "references/operating-modes.md",
                "references/output-eval-method.md",
                "references/output-quality-risk.md",
                "references/output-visual-quality.md",
                "references/packaging-contracts.md",
                "references/pattern-extraction-doctrine.md",
                "references/platform-capability-matrix.md",
                "references/prompt-engineering-doctrine.md",
                "references/qa-ladder.md",
                "references/reference-scan.md",
                "references/regression-cause-taxonomy.md",
                "references/resource-boundaries.md",
                "references/review-studio-method.md",
                "references/review-waiver-method.md",
                "references/runtime-conformance-method.md",
                "references/skill-archetypes.md",
                "references/skill-atlas-method.md",
                "references/skill-engineering-method.md",
                "references/skill-ir-method.md",
                "references/systems-thinking-doctrine.md",
                "references/telemetry-drift-method.md",
                "references/trust-security-method.md",
                "references/user-memory-policy.md"
              ],
              "scripts": [
                "scripts/adjudicate_output_review.py",
                "scripts/build_confusion_matrix.py",
                "scripts/build_skill_atlas.py",
                "scripts/check_update.py",
                "scripts/ci_test.py",
                "scripts/collect_feedback.py",
                "scripts/compile_skill.py",
                "scripts/context_sizer.py",
                "scripts/create_iteration_snapshot.py",
                "scripts/cross_packager.py",
                "scripts/diff_eval.py",
                "scripts/emit_telemetry_event.py",
                "scripts/export_skill_ir.py",
                "scripts/github_benchmark_scan.py",
                "scripts/governance_check.py",
                "scripts/html_rendering.py",
                "scripts/import_telemetry_events.py",
                "scripts/init_skill.py",
                "scripts/judge_blind_eval.py",
                "scripts/lint_skill.py",
                "scripts/local_output_eval_runner.py",
                "scripts/optimize_description.py",
                "scripts/prepare_output_review_kit.py",
                "scripts/prepare_world_class_submission_kit.py",
                "scripts/probe_runtime_permissions.py",
                "scripts/promotion_checker.py",
                "scripts/propose_adaptation.py",
                "scripts/provider_output_eval_runner.py",
                "scripts/python_compat_check.py",
                "scripts/registry_audit.py",
                "scripts/render_adoption_drift_report.py",
                "scripts/render_architecture_maintainability.py",
                "scripts/render_artifact_design_profile.py",
                "scripts/render_baseline_compare.py",
                "scripts/render_benchmark_reproducibility.py",
                "scripts/render_context_reports.py",
                "scripts/render_description_drift_history.py",
                "scripts/render_eval_dashboard.py",
                "scripts/render_intent_confidence.py",
                "scripts/render_intent_dialogue.py",
                "scripts/render_iteration_directions.py",
                "scripts/render_iteration_ledger.py",
                "scripts/render_output_risk_profile.py",
                "scripts/render_portability_report.py",
                "scripts/render_prompt_quality_profile.py",
                "scripts/render_reference_scan.py",
                "scripts/render_reference_synthesis.py",
                "scripts/render_regression_history.py",
                "scripts/render_review_annotations.py",
                "scripts/render_review_studio.py",
                "scripts/render_review_viewer.py",
                "scripts/render_review_waivers.py",
                "scripts/render_skill_os2_audit.py",
                "scripts/render_skill_os2_coverage.py",
                "scripts/render_skill_overview.py",
                "scripts/render_social_preview.py",
                "scripts/render_system_model.py",
                "scripts/render_telemetry_hook_recipes.py",
                "scripts/render_world_class_claim_guard.py",
                "scripts/render_world_class_evidence_intake.py",
                "scripts/render_world_class_evidence_ledger.py",
                "scripts/render_world_class_evidence_plan.py",
                "scripts/render_world_class_operator_runbook.py",
                "scripts/render_world_class_submission_review.py",
                "scripts/resource_boundary_check.py",
                "scripts/review_studio_action_evidence.py",
                "scripts/review_studio_actions.py",
                "scripts/review_studio_data.py",
                "scripts/review_studio_formatting.py",
                "scripts/review_studio_gates.py",
                "scripts/review_studio_layout.py",
                "scripts/review_studio_output_review.py",
                "scripts/review_studio_waivers.py",
                "scripts/review_studio_world_class.py",
                "scripts/review_viewer_data.py",
                "scripts/run_conformance_suite.py",
                "scripts/run_description_optimization_suite.py",
                "scripts/run_eval_suite.py",
                "scripts/run_output_eval.py",
                "scripts/run_output_execution.py"
              ],
              "assets": [
                "templates/basic_skill.md.j2",
                "templates/complex_skill.md.j2"
              ],
              "reports": [
                "reports/benchmark_methodology.md",
                "reports/intent-context.json",
                "reports/intent-confidence.json",
                "reports/intent-confidence.md",
                "reports/reference-synthesis.json",
                "reports/reference-synthesis.md",
                "reports/output-risk-profile.json",
                "reports/output-risk-profile.md",
                "reports/artifact-design-profile.json",
                "reports/artifact-design-profile.md",
                "reports/prompt-quality-profile.json",
                "reports/prompt-quality-profile.md",
                "reports/system-model.json",
                "reports/system-model.md",
                "reports/iteration-directions.json",
                "reports/iteration-directions.md",
                "reports/skill-overview.json",
                "reports/skill-overview.html",
                "reports/output_quality_scorecard.json",
                "reports/output_quality_scorecard.md",
                "reports/output_execution_runs.json",
                "reports/output_execution_runs.md",
                "reports/output_blind_review_pack.json",
                "reports/output_blind_review_pack.md",
                "reports/output_blind_answer_key.json",
                "reports/output_review_adjudication.json",
                "reports/output_review_adjudication.md",
                "reports/review_annotations.json",
                "reports/review_annotations.md",
                "reports/conformance_matrix.json",
                "reports/conformance_matrix.md",
                "reports/security_trust_report.json",
                "reports/security_trust_report.md",
                "reports/runtime_permission_probes.json",
                "reports/runtime_permission_probes.md",
                "reports/telemetry_hook_recipes.json",
                "reports/telemetry_hook_recipes.md",
                "reports/skill_atlas.json",
                "reports/skill_atlas.html",
                "reports/skill-os-2-review.md",
                "reports/portability_score.json",
                "reports/portability_score.md",
                "reports/governance_score.json"
              ],
              "counts": {
                "references": 34,
                "scripts": 80,
                "assets": 2,
                "reports": 43
              }
            },
            "eval_plan": {
              "trigger": [
                "evals/README.md",
                "evals/adaptation/user_signals.example.jsonl",
                "evals/adversarial/trigger_cases.json",
                "evals/blind_holdout/trigger_cases.json",
                "evals/confusion/route_cases.json",
                "evals/dev/trigger_cases.json",
                "evals/failure-cases.md",
                "evals/history/2026-03-31-context-first-pack.json",
                "evals/history/2026-03-31-family-suite-expansion.json",
                "evals/history/2026-03-31-governance-quality-gates.json",
                "evals/history/2026-03-31-governed-assets-and-history.json",
                "evals/history/2026-04-01-route-scorecard-foundation.json",
                "evals/history/README.md",
                "evals/history/description_optimization/2026-03-31-description-optimization-suite.json",
                "evals/history/description_optimization/2026-04-01-adversarial-calibration-and-family-drift.json",
                "evals/history/description_optimization/2026-04-01-blind-holdout-and-drift-history.json",
                "evals/history/description_optimization/2026-04-01-judge-backed-blind-eval.json",
                "evals/history/description_optimization/README.md",
                "evals/holdout/trigger_cases.json",
                "evals/output/cases.jsonl",
                "evals/output/fixtures/release-brief-source.md",
                "evals/output/schema.json",
                "evals/packaging_expectations.json",
                "evals/promotion_policy.md",
                "evals/semantic_config.json",
                "evals/train/trigger_cases.json",
                "evals/trigger_cases.json"
              ],
              "output": [
                "evals/output/cases.jsonl",
                "evals/output/fixtures/release-brief-source.md",
                "evals/output/schema.json"
              ],
              "adversarial": [
                "evals/adversarial/trigger_cases.json"
              ],
              "baseline": "without_skill",
              "counts": {
                "trigger": 27,
                "output": 3,
                "adversarial": 1,
                "baseline": 1
              }
            },
            "risk": {
              "output_risk": "high",
              "execution_risk": "medium",
              "trust_boundary": "external"
            },
            "governance": {
              "owner": "Yao Team",
              "maturity": "governed",
              "review_cadence": "quarterly",
              "review_due": ""
            },
            "runtime": {
              "activation": {
                "mode": "manual",
                "paths": []
              },
              "execution": {
                "context": "inline",
                "shell": "bash"
              },
              "trust": {
                "source_tier": "local",
                "remote_inline_execution": "forbid",
                "remote_metadata_policy": "allow-metadata-only"
              },
              "adapter_targets": [
                "openai",
                "claude",
                "generic",
                "vscode"
              ],
              "canonical_format": "agent-skills"
            },
            "permissions": {
              "schema_version": "1.0",
              "source": "reports/security_trust_report.json",
              "source_available": true,
              "declared_capabilities": [
                "network",
                "file_write",
                "subprocess"
              ],
              "review_required": true,
              "capabilities": {
                "network": {
                  "required": true,
                  "script_count": 3,
                  "scripts": [
                    "scripts/check_update.py",
                    "scripts/github_benchmark_scan.py",
                    "scripts/provider_output_eval_runner.py"
                  ],
                  "review_reason": "Outbound hosts must match security/network_policy.json."
                },
                "file_write": {
                  "required": true,
                  "script_count": 67,
                  "scripts": [
                    "scripts/adjudicate_output_review.py",
                    "scripts/build_confusion_matrix.py",
                    "scripts/build_skill_atlas.py",
                    "scripts/check_update.py",
                    "scripts/ci_test.py",
                    "scripts/collect_feedback.py",
                    "scripts/compile_skill.py",
                    "scripts/create_iteration_snapshot.py",
                    "scripts/cross_packager.py",
                    "scripts/emit_telemetry_event.py",
                    "scripts/export_skill_ir.py",
                    "scripts/github_benchmark_scan.py",
                    "scripts/import_telemetry_events.py",
                    "scripts/init_skill.py",
                    "scripts/prepare_output_review_kit.py",
                    "scripts/prepare_world_class_submission_kit.py",
                    "scripts/probe_runtime_permissions.py",
                    "scripts/promotion_checker.py",
                    "scripts/propose_adaptation.py",
                    "scripts/python_compat_check.py",
                    "scripts/registry_audit.py",
                    "scripts/render_adoption_drift_report.py",
                    "scripts/render_architecture_maintainability.py",
                    "scripts/render_artifact_design_profile.py",
                    "scripts/render_baseline_compare.py",
                    "scripts/render_benchmark_reproducibility.py",
                    "scripts/render_context_reports.py",
                    "scripts/render_description_drift_history.py",
                    "scripts/render_eval_dashboard.py",
                    "scripts/render_intent_confidence.py",
                    "scripts/render_intent_dialogue.py",
                    "scripts/render_iteration_directions.py",
                    "scripts/render_iteration_ledger.py",
                    "scripts/render_output_risk_profile.py",
                    "scripts/render_portability_report.py",
                    "scripts/render_prompt_quality_profile.py",
                    "scripts/render_reference_scan.py",
                    "scripts/render_reference_synthesis.py",
                    "scripts/render_regression_history.py",
                    "scripts/render_review_annotations.py",
                    "scripts/render_review_studio.py",
                    "scripts/render_review_viewer.py",
                    "scripts/render_review_waivers.py",
                    "scripts/render_skill_interpretation.py",
                    "scripts/render_skill_os2_audit.py",
                    "scripts/render_skill_os2_coverage.py",
                    "scripts/render_skill_overview.py",
                    "scripts/render_social_preview.py",
                    "scripts/render_system_model.py",
                    "scripts/render_telemetry_hook_recipes.py",
                    "scripts/render_world_class_claim_guard.py",
                    "scripts/render_world_class_evidence_intake.py",
                    "scripts/render_world_class_evidence_ledger.py",
                    "scripts/render_world_class_evidence_plan.py",
                    "scripts/render_world_class_operator_runbook.py",
                    "scripts/render_world_class_submission_review.py",
                    "scripts/run_conformance_suite.py",
                    "scripts/run_description_optimization_suite.py",
                    "scripts/run_output_eval.py",
                    "scripts/run_output_execution.py",
                    "scripts/simulate_install.py",
                    "scripts/summarize_user_signals.py",
                    "scripts/sync_local_install.py",
                    "scripts/telemetry_native_host.py",
                    "scripts/trust_check.py",
                    "scripts/upgrade_check.py",
                    "scripts/verify_package.py"
                  ],
                  "review_reason": "Scripts write local files or generated artifacts."
                },
                "subprocess": {
                  "required": true,
                  "script_count": 9,
                  "scripts": [
                    "scripts/ci_test.py",
                    "scripts/render_benchmark_reproducibility.py",
                    "scripts/render_eval_dashboard.py",
                    "scripts/run_eval_suite.py",
                    "scripts/run_output_execution.py",
                    "scripts/sync_local_install.py",
                    "scripts/trust_check.py",
                    "scripts/yao.py",
                    "scripts/yao_cli_runtime.py"
                  ],
                  "review_reason": "Scripts spawn local commands and need operator review."
                },
                "interactive": {
                  "required": false,
                  "script_count": 0,
                  "scripts": [],
                  "review_reason": ""
                }
              },
              "network_policy": {
                "source": "security/network_policy.json",
                "covered_scripts": [
                  "scripts/check_update.py",
                  "scripts/github_benchmark_scan.py",
                  "scripts/provider_output_eval_runner.py"
                ],
                "missing_scripts": [],
                "mismatches": []
              },
              "help_smoke": {
                "enabled": true,
                "checked_count": 80,
                "failed_count": 0,
                "failed_scripts": []
              },
              "trust_summary": {
                "secret_findings": 0,
                "network_script_count": 3,
                "file_write_script_count": 67,
                "subprocess_script_count": 9,
                "interactive_script_count": 0,
                "help_smoke_failed_count": 0
              }
            },
            "source_files_count": 6,
            "target": "claude",
            "target_permission_contract": {
              "schema_version": "1.0",
              "target": "claude",
              "permission_model": "neutral-source-plus-adapter",
              "native_enforcement": false,
              "representation": "targets/claude/adapter.json::target_permission_contract and README notes",
              "review_required": true,
              "declared_capabilities": [
                "network",
                "file_write",
                "subprocess"
              ],
              "capability_counts": {
                "network": 3,
                "file_write": 67,
                "subprocess": 9,
                "interactive": 0
              },
              "evidence": "reports/security_trust_report.json",
              "operator_note": "Claude-compatible package keeps permission intent in adapter metadata for install review."
            },
            "target_native_contract": {
              "schema_version": "1.0",
              "target": "claude",
              "native_surface": "Claude-compatible neutral source folder with adapter notes",
              "activation": {
                "policy": "Use SKILL.md frontmatter description as the primary activation contract and adapter.json for review metadata.",
                "trigger_description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
                "manual_activation_supported": true,
                "automatic_activation_note": "Depends on the target client route/catalog implementation."
              },
              "resources": {
                "strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.",
                "counts": {
                  "references": 34,
                  "scripts": 80,
                  "assets": 2,
                  "reports": 43
                },
                "generated_files": [
                  "targets/claude/adapter.json",
                  "targets/claude/README.md"
                ]
              },
              "scripts": {
                "strategy": "Scripts remain local package resources and must be reviewed through trust and permission reports before use.",
                "script_count": 80,
                "help_smoke_failed_count": 0
              },
              "permissions": {
                "enforcement": "metadata-fallback",
                "native_enforcement": false,
                "declared_capabilities": [
                  "network",
                  "file_write",
                  "subprocess"
                ],
                "review_required": true
              },
              "review": {
                "artifacts": [
                  "targets/claude/README.md",
                  "targets/claude/adapter.json",
                  "reports/review-studio.html"
                ],
                "fallback_behavior": "If Claude-specific metadata is not consumed, SKILL.md and references remain the source of truth.",
                "unsupported_native_features": [
                  "vendor-native permission enforcement",
                  "provider-specific execution transforms",
                  "vendor-native metadata fields are carried as adapter JSON and README notes"
                ]
              },
              "install_scope": "user or project skill directory"
            },
            "degradation_strategy": "neutral-source-plus-adapter",
            "target_runtime": {
              "adapter_mode": "neutral-source-plus-adapter",
              "generated_files": [
                "targets/claude/adapter.json",
                "targets/claude/README.md"
              ],
              "metadata_mapping": {
                "display_name": "targets/claude/adapter.json::display_name",
                "default_prompt": "targets/claude/adapter.json::default_prompt",
                "activation": "targets/claude/adapter.json::activation_mode",
                "execution": "targets/claude/adapter.json::execution_context",
                "trust": "targets/claude/adapter.json::trust_level",
                "permissions": "targets/claude/adapter.json::target_permission_contract",
                "degradation": "targets/claude/adapter.json::degradation_strategy"
              },
              "preserved_semantics": [
                "trigger",
                "workflow-counts",
                "resources",
                "eval-plan",
                "risk",
                "governance",
                "runtime",
                "trust",
                "permissions"
              ],
              "native_surface": "Claude-compatible neutral source folder with adapter notes"
            }
          },
          "permission_contract": {
            "schema_version": "1.0",
            "source": "reports/security_trust_report.json",
            "source_available": true,
            "declared_capabilities": [
              "network",
              "file_write",
              "subprocess"
            ],
            "review_required": true,
            "capabilities": {
              "network": {
                "required": true,
                "script_count": 3,
                "scripts": [
                  "scripts/check_update.py",
                  "scripts/github_benchmark_scan.py",
                  "scripts/provider_output_eval_runner.py"
                ],
                "review_reason": "Outbound hosts must match security/network_policy.json."
              },
              "file_write": {
                "required": true,
                "script_count": 67,
                "scripts": [
                  "scripts/adjudicate_output_review.py",
                  "scripts/build_confusion_matrix.py",
                  "scripts/build_skill_atlas.py",
                  "scripts/check_update.py",
                  "scripts/ci_test.py",
                  "scripts/collect_feedback.py",
                  "scripts/compile_skill.py",
                  "scripts/create_iteration_snapshot.py",
                  "scripts/cross_packager.py",
                  "scripts/emit_telemetry_event.py",
                  "scripts/export_skill_ir.py",
                  "scripts/github_benchmark_scan.py",
                  "scripts/import_telemetry_events.py",
                  "scripts/init_skill.py",
                  "scripts/prepare_output_review_kit.py",
                  "scripts/prepare_world_class_submission_kit.py",
                  "scripts/probe_runtime_permissions.py",
                  "scripts/promotion_checker.py",
                  "scripts/propose_adaptation.py",
                  "scripts/python_compat_check.py",
                  "scripts/registry_audit.py",
                  "scripts/render_adoption_drift_report.py",
                  "scripts/render_architecture_maintainability.py",
                  "scripts/render_artifact_design_profile.py",
                  "scripts/render_baseline_compare.py",
                  "scripts/render_benchmark_reproducibility.py",
                  "scripts/render_context_reports.py",
                  "scripts/render_description_drift_history.py",
                  "scripts/render_eval_dashboard.py",
                  "scripts/render_intent_confidence.py",
                  "scripts/render_intent_dialogue.py",
                  "scripts/render_iteration_directions.py",
                  "scripts/render_iteration_ledger.py",
                  "scripts/render_output_risk_profile.py",
                  "scripts/render_portability_report.py",
                  "scripts/render_prompt_quality_profile.py",
                  "scripts/render_reference_scan.py",
                  "scripts/render_reference_synthesis.py",
                  "scripts/render_regression_history.py",
                  "scripts/render_review_annotations.py",
                  "scripts/render_review_studio.py",
                  "scripts/render_review_viewer.py",
                  "scripts/render_review_waivers.py",
                  "scripts/render_skill_interpretation.py",
                  "scripts/render_skill_os2_audit.py",
                  "scripts/render_skill_os2_coverage.py",
                  "scripts/render_skill_overview.py",
                  "scripts/render_social_preview.py",
                  "scripts/render_system_model.py",
                  "scripts/render_telemetry_hook_recipes.py",
                  "scripts/render_world_class_claim_guard.py",
                  "scripts/render_world_class_evidence_intake.py",
                  "scripts/render_world_class_evidence_ledger.py",
                  "scripts/render_world_class_evidence_plan.py",
                  "scripts/render_world_class_operator_runbook.py",
                  "scripts/render_world_class_submission_review.py",
                  "scripts/run_conformance_suite.py",
                  "scripts/run_description_optimization_suite.py",
                  "scripts/run_output_eval.py",
                  "scripts/run_output_execution.py",
                  "scripts/simulate_install.py",
                  "scripts/summarize_user_signals.py",
                  "scripts/sync_local_install.py",
                  "scripts/telemetry_native_host.py",
                  "scripts/trust_check.py",
                  "scripts/upgrade_check.py",
                  "scripts/verify_package.py"
                ],
                "review_reason": "Scripts write local files or generated artifacts."
              },
              "subprocess": {
                "required": true,
                "script_count": 9,
                "scripts": [
                  "scripts/ci_test.py",
                  "scripts/render_benchmark_reproducibility.py",
                  "scripts/render_eval_dashboard.py",
                  "scripts/run_eval_suite.py",
                  "scripts/run_output_execution.py",
                  "scripts/sync_local_install.py",
                  "scripts/trust_check.py",
                  "scripts/yao.py",
                  "scripts/yao_cli_runtime.py"
                ],
                "review_reason": "Scripts spawn local commands and need operator review."
              },
              "interactive": {
                "required": false,
                "script_count": 0,
                "scripts": [],
                "review_reason": ""
              }
            },
            "network_policy": {
              "source": "security/network_policy.json",
              "covered_scripts": [
                "scripts/check_update.py",
                "scripts/github_benchmark_scan.py",
                "scripts/provider_output_eval_runner.py"
              ],
              "missing_scripts": [],
              "mismatches": []
            },
            "help_smoke": {
              "enabled": true,
              "checked_count": 80,
              "failed_count": 0,
              "failed_scripts": []
            },
            "trust_summary": {
              "secret_findings": 0,
              "network_script_count": 3,
              "file_write_script_count": 67,
              "subprocess_script_count": 9,
              "interactive_script_count": 0,
              "help_smoke_failed_count": 0
            }
          },
          "target_permission_contract": {
            "schema_version": "1.0",
            "target": "claude",
            "permission_model": "neutral-source-plus-adapter",
            "native_enforcement": false,
            "representation": "targets/claude/adapter.json::target_permission_contract and README notes",
            "review_required": true,
            "declared_capabilities": [
              "network",
              "file_write",
              "subprocess"
            ],
            "capability_counts": {
              "network": 3,
              "file_write": 67,
              "subprocess": 9,
              "interactive": 0
            },
            "evidence": "reports/security_trust_report.json",
            "operator_note": "Claude-compatible package keeps permission intent in adapter metadata for install review."
          },
          "target_native_contract": {
            "schema_version": "1.0",
            "target": "claude",
            "native_surface": "Claude-compatible neutral source folder with adapter notes",
            "activation": {
              "policy": "Use SKILL.md frontmatter description as the primary activation contract and adapter.json for review metadata.",
              "trigger_description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
              "manual_activation_supported": true,
              "automatic_activation_note": "Depends on the target client route/catalog implementation."
            },
            "resources": {
              "strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.",
              "counts": {
                "references": 34,
                "scripts": 80,
                "assets": 2,
                "reports": 43
              },
              "generated_files": [
                "targets/claude/adapter.json",
                "targets/claude/README.md"
              ]
            },
            "scripts": {
              "strategy": "Scripts remain local package resources and must be reviewed through trust and permission reports before use.",
              "script_count": 80,
              "help_smoke_failed_count": 0
            },
            "permissions": {
              "enforcement": "metadata-fallback",
              "native_enforcement": false,
              "declared_capabilities": [
                "network",
                "file_write",
                "subprocess"
              ],
              "review_required": true
            },
            "review": {
              "artifacts": [
                "targets/claude/README.md",
                "targets/claude/adapter.json",
                "reports/review-studio.html"
              ],
              "fallback_behavior": "If Claude-specific metadata is not consumed, SKILL.md and references remain the source of truth.",
              "unsupported_native_features": [
                "vendor-native permission enforcement",
                "provider-specific execution transforms",
                "vendor-native metadata fields are carried as adapter JSON and README notes"
              ]
            },
            "install_scope": "user or project skill directory"
          },
          "target_transform": {
            "target": "claude",
            "adapter_mode": "neutral-source-plus-adapter",
            "generated_files": [
              "targets/claude/adapter.json",
              "targets/claude/README.md"
            ],
            "metadata_mapping": {
              "display_name": "targets/claude/adapter.json::display_name",
              "default_prompt": "targets/claude/adapter.json::default_prompt",
              "activation": "targets/claude/adapter.json::activation_mode",
              "execution": "targets/claude/adapter.json::execution_context",
              "trust": "targets/claude/adapter.json::trust_level",
              "permissions": "targets/claude/adapter.json::target_permission_contract",
              "degradation": "targets/claude/adapter.json::degradation_strategy"
            },
            "preserved_semantics": [
              "trigger",
              "workflow-counts",
              "resources",
              "eval-plan",
              "risk",
              "governance",
              "runtime",
              "trust",
              "permissions"
            ],
            "degradation_strategy": "neutral-source-plus-adapter",
            "permission_representation": "targets/claude/adapter.json::target_permission_contract and README notes",
            "native_surface": "Claude-compatible neutral source folder with adapter notes",
            "activation_policy": "Use SKILL.md frontmatter description as the primary activation contract and adapter.json for review metadata.",
            "resource_strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.",
            "script_strategy": "Scripts remain local package resources and must be reviewed through trust and permission reports before use.",
            "permission_enforcement": "metadata-fallback"
          },
          "unsupported_features": [
            "vendor-native metadata fields are carried as adapter JSON and README notes"
          ],
          "warnings": [],
          "failures": []
        },
        {
          "schema_version": "1.0",
          "target": "generic",
          "status": "pass",
          "compiler": {
            "name": "yao-skill-ir-compiler",
            "schema_version": "1.0",
            "source": "skill-ir",
            "ir_source": "skill-ir/examples/yao-meta-skill.json",
            "ir_schema_version": "2.0.0"
          },
          "source": {
            "skill_dir": ".",
            "canonical_metadata": "agents/interface.yaml",
            "declared_targets": [
              "openai",
              "claude",
              "generic",
              "agent-skills-compatible",
              "vscode"
            ]
          },
          "compiled_contract": {
            "name": "yao-meta-skill",
            "title": "Yao Meta Skill",
            "version": "1.1.0",
            "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
            "job_to_be_done": "Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse.",
            "trigger": {
              "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
              "should_trigger": [
                "Create a skill from this repeated workflow.",
                "Turn this runbook into a reusable agent skill.",
                "Convert this process note into a reusable skill package for the team.",
                "Improve this skill description and add evals.",
                "Refactor this prompt into a proper skill package.",
                "Package this skill for team reuse.",
                "Create a meta-skill for packaging internal workflows.",
                "Standardize this recurring workflow as a shareable skill package with references."
              ],
              "should_not_trigger": [
                "Explain what a workflow is.",
                "Just explain what a skill is.",
                "Summarize this random note.",
                "Translate this README into Japanese.",
                "Write a product headline for this landing page.",
                "Draft a blog title for this article.",
                "Rewrite this paragraph more clearly, but do not package anything.",
                "Explain the difference between a runbook and a workflow.",
                "one-off writing, translation, explanation, or brainstorming requests that do not need a reusable skill",
                "general code review or debugging unless the user is packaging that workflow as a skill"
              ],
              "edge_cases": [
                "Create a one-off prompt for this task.",
                "Write a custom answer for this request without creating a skill package.",
                "Help me brainstorm process ideas without building a skill.",
                "Improve this README but do not turn it into a skill.",
                "Make a checklist for this task, but not a reusable skill.",
                "Create a reusable-looking checklist, but keep it as a plain note instead of a skill.",
                "Review this process note and explain it, no packaging needed.",
                "Turn this into a checklist and template, but stop short of making a full skill."
              ]
            },
            "workflow": {
              "steps": [
                "Decide whether the request should become a skill and choose the lightest fit.",
                "Capture job, output, exclusions, constraints, and standards.",
                "Run reference scan: external benchmarks first, user references second, local fit third; surface only uncertainty or conflict.",
                "Write the `description` early and test route quality before expanding the package.",
                "Add output-risk, artifact-design, prompt-quality, and system-model reports only when they matter.",
                "Add only folders and gates that earn their keep.",
                "Surface the top three next iteration directions."
              ],
              "decision_points": [
                "Route by frontmatter `description`.",
                "Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.",
                "Use the lightest reliable process.",
                "`Scaffold`: exploratory or personal.",
                "`Production`: team reuse.",
                "`Library`: shared infrastructure.",
                "`Governed`: high-trust, policy-sensitive, or release-critical.",
                "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.",
                "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.",
                "Do not silently broaden the skill into adjacent jobs just because the examples are nearby."
              ],
              "failure_modes": [
                "Tables can render as dense grids with weak hierarchy or poor mobile readability.",
                "Long bullets can make the output look complete while hiding the actual decision logic.",
                "Footnote markers or dense citation notes can interrupt the reading flow.",
                "Evidence can be over-attached to obvious statements and under-attached to risky claims.",
                "Screenshots can be captured from the wrong state, wrong viewport, or wrong crop.",
                "Missing screenshots can cause the skill to invent visual references instead of declaring the gap.",
                "Users start invoking the skill for adjacent one-off or explanation-only requests.",
                "Outputs remain valid but become generic, cluttered, or weakly aligned with the user's domain.",
                "Borrowed benchmark patterns no longer fit the local job or add ceremony without payoff.",
                "Skill usage becomes team-critical while ownership, review cadence, or rollback evidence stays informal."
              ]
            },
            "resources": {
              "references": [
                "references/artifact-design-doctrine.md",
                "references/authoring-discipline.md",
                "references/autonomous-adaptation.md",
                "references/distribution-registry-method.md",
                "references/eval-playbook.md",
                "references/gate-selection.md",
                "references/governance.md",
                "references/human-review-template.md",
                "references/intent-dialogue.md",
                "references/iteration-philosophy.md",
                "references/non-skill-decision-tree.md",
                "references/operating-modes.md",
                "references/output-eval-method.md",
                "references/output-quality-risk.md",
                "references/output-visual-quality.md",
                "references/packaging-contracts.md",
                "references/pattern-extraction-doctrine.md",
                "references/platform-capability-matrix.md",
                "references/prompt-engineering-doctrine.md",
                "references/qa-ladder.md",
                "references/reference-scan.md",
                "references/regression-cause-taxonomy.md",
                "references/resource-boundaries.md",
                "references/review-studio-method.md",
                "references/review-waiver-method.md",
                "references/runtime-conformance-method.md",
                "references/skill-archetypes.md",
                "references/skill-atlas-method.md",
                "references/skill-engineering-method.md",
                "references/skill-ir-method.md",
                "references/systems-thinking-doctrine.md",
                "references/telemetry-drift-method.md",
                "references/trust-security-method.md",
                "references/user-memory-policy.md"
              ],
              "scripts": [
                "scripts/adjudicate_output_review.py",
                "scripts/build_confusion_matrix.py",
                "scripts/build_skill_atlas.py",
                "scripts/check_update.py",
                "scripts/ci_test.py",
                "scripts/collect_feedback.py",
                "scripts/compile_skill.py",
                "scripts/context_sizer.py",
                "scripts/create_iteration_snapshot.py",
                "scripts/cross_packager.py",
                "scripts/diff_eval.py",
                "scripts/emit_telemetry_event.py",
                "scripts/export_skill_ir.py",
                "scripts/github_benchmark_scan.py",
                "scripts/governance_check.py",
                "scripts/html_rendering.py",
                "scripts/import_telemetry_events.py",
                "scripts/init_skill.py",
                "scripts/judge_blind_eval.py",
                "scripts/lint_skill.py",
                "scripts/local_output_eval_runner.py",
                "scripts/optimize_description.py",
                "scripts/prepare_output_review_kit.py",
                "scripts/prepare_world_class_submission_kit.py",
                "scripts/probe_runtime_permissions.py",
                "scripts/promotion_checker.py",
                "scripts/propose_adaptation.py",
                "scripts/provider_output_eval_runner.py",
                "scripts/python_compat_check.py",
                "scripts/registry_audit.py",
                "scripts/render_adoption_drift_report.py",
                "scripts/render_architecture_maintainability.py",
                "scripts/render_artifact_design_profile.py",
                "scripts/render_baseline_compare.py",
                "scripts/render_benchmark_reproducibility.py",
                "scripts/render_context_reports.py",
                "scripts/render_description_drift_history.py",
                "scripts/render_eval_dashboard.py",
                "scripts/render_intent_confidence.py",
                "scripts/render_intent_dialogue.py",
                "scripts/render_iteration_directions.py",
                "scripts/render_iteration_ledger.py",
                "scripts/render_output_risk_profile.py",
                "scripts/render_portability_report.py",
                "scripts/render_prompt_quality_profile.py",
                "scripts/render_reference_scan.py",
                "scripts/render_reference_synthesis.py",
                "scripts/render_regression_history.py",
                "scripts/render_review_annotations.py",
                "scripts/render_review_studio.py",
                "scripts/render_review_viewer.py",
                "scripts/render_review_waivers.py",
                "scripts/render_skill_os2_audit.py",
                "scripts/render_skill_os2_coverage.py",
                "scripts/render_skill_overview.py",
                "scripts/render_social_preview.py",
                "scripts/render_system_model.py",
                "scripts/render_telemetry_hook_recipes.py",
                "scripts/render_world_class_claim_guard.py",
                "scripts/render_world_class_evidence_intake.py",
                "scripts/render_world_class_evidence_ledger.py",
                "scripts/render_world_class_evidence_plan.py",
                "scripts/render_world_class_operator_runbook.py",
                "scripts/render_world_class_submission_review.py",
                "scripts/resource_boundary_check.py",
                "scripts/review_studio_action_evidence.py",
                "scripts/review_studio_actions.py",
                "scripts/review_studio_data.py",
                "scripts/review_studio_formatting.py",
                "scripts/review_studio_gates.py",
                "scripts/review_studio_layout.py",
                "scripts/review_studio_output_review.py",
                "scripts/review_studio_waivers.py",
                "scripts/review_studio_world_class.py",
                "scripts/review_viewer_data.py",
                "scripts/run_conformance_suite.py",
                "scripts/run_description_optimization_suite.py",
                "scripts/run_eval_suite.py",
                "scripts/run_output_eval.py",
                "scripts/run_output_execution.py"
              ],
              "assets": [
                "templates/basic_skill.md.j2",
                "templates/complex_skill.md.j2"
              ],
              "reports": [
                "reports/benchmark_methodology.md",
                "reports/intent-context.json",
                "reports/intent-confidence.json",
                "reports/intent-confidence.md",
                "reports/reference-synthesis.json",
                "reports/reference-synthesis.md",
                "reports/output-risk-profile.json",
                "reports/output-risk-profile.md",
                "reports/artifact-design-profile.json",
                "reports/artifact-design-profile.md",
                "reports/prompt-quality-profile.json",
                "reports/prompt-quality-profile.md",
                "reports/system-model.json",
                "reports/system-model.md",
                "reports/iteration-directions.json",
                "reports/iteration-directions.md",
                "reports/skill-overview.json",
                "reports/skill-overview.html",
                "reports/output_quality_scorecard.json",
                "reports/output_quality_scorecard.md",
                "reports/output_execution_runs.json",
                "reports/output_execution_runs.md",
                "reports/output_blind_review_pack.json",
                "reports/output_blind_review_pack.md",
                "reports/output_blind_answer_key.json",
                "reports/output_review_adjudication.json",
                "reports/output_review_adjudication.md",
                "reports/review_annotations.json",
                "reports/review_annotations.md",
                "reports/conformance_matrix.json",
                "reports/conformance_matrix.md",
                "reports/security_trust_report.json",
                "reports/security_trust_report.md",
                "reports/runtime_permission_probes.json",
                "reports/runtime_permission_probes.md",
                "reports/telemetry_hook_recipes.json",
                "reports/telemetry_hook_recipes.md",
                "reports/skill_atlas.json",
                "reports/skill_atlas.html",
                "reports/skill-os-2-review.md",
                "reports/portability_score.json",
                "reports/portability_score.md",
                "reports/governance_score.json"
              ],
              "counts": {
                "references": 34,
                "scripts": 80,
                "assets": 2,
                "reports": 43
              }
            },
            "eval_plan": {
              "trigger": [
                "evals/README.md",
                "evals/adaptation/user_signals.example.jsonl",
                "evals/adversarial/trigger_cases.json",
                "evals/blind_holdout/trigger_cases.json",
                "evals/confusion/route_cases.json",
                "evals/dev/trigger_cases.json",
                "evals/failure-cases.md",
                "evals/history/2026-03-31-context-first-pack.json",
                "evals/history/2026-03-31-family-suite-expansion.json",
                "evals/history/2026-03-31-governance-quality-gates.json",
                "evals/history/2026-03-31-governed-assets-and-history.json",
                "evals/history/2026-04-01-route-scorecard-foundation.json",
                "evals/history/README.md",
                "evals/history/description_optimization/2026-03-31-description-optimization-suite.json",
                "evals/history/description_optimization/2026-04-01-adversarial-calibration-and-family-drift.json",
                "evals/history/description_optimization/2026-04-01-blind-holdout-and-drift-history.json",
                "evals/history/description_optimization/2026-04-01-judge-backed-blind-eval.json",
                "evals/history/description_optimization/README.md",
                "evals/holdout/trigger_cases.json",
                "evals/output/cases.jsonl",
                "evals/output/fixtures/release-brief-source.md",
                "evals/output/schema.json",
                "evals/packaging_expectations.json",
                "evals/promotion_policy.md",
                "evals/semantic_config.json",
                "evals/train/trigger_cases.json",
                "evals/trigger_cases.json"
              ],
              "output": [
                "evals/output/cases.jsonl",
                "evals/output/fixtures/release-brief-source.md",
                "evals/output/schema.json"
              ],
              "adversarial": [
                "evals/adversarial/trigger_cases.json"
              ],
              "baseline": "without_skill",
              "counts": {
                "trigger": 27,
                "output": 3,
                "adversarial": 1,
                "baseline": 1
              }
            },
            "risk": {
              "output_risk": "high",
              "execution_risk": "medium",
              "trust_boundary": "external"
            },
            "governance": {
              "owner": "Yao Team",
              "maturity": "governed",
              "review_cadence": "quarterly",
              "review_due": ""
            },
            "runtime": {
              "activation": {
                "mode": "manual",
                "paths": []
              },
              "execution": {
                "context": "inline",
                "shell": "bash"
              },
              "trust": {
                "source_tier": "local",
                "remote_inline_execution": "forbid",
                "remote_metadata_policy": "allow-metadata-only"
              },
              "adapter_targets": [
                "openai",
                "claude",
                "generic",
                "vscode"
              ],
              "canonical_format": "agent-skills"
            },
            "permissions": {
              "schema_version": "1.0",
              "source": "reports/security_trust_report.json",
              "source_available": true,
              "declared_capabilities": [
                "network",
                "file_write",
                "subprocess"
              ],
              "review_required": true,
              "capabilities": {
                "network": {
                  "required": true,
                  "script_count": 3,
                  "scripts": [
                    "scripts/check_update.py",
                    "scripts/github_benchmark_scan.py",
                    "scripts/provider_output_eval_runner.py"
                  ],
                  "review_reason": "Outbound hosts must match security/network_policy.json."
                },
                "file_write": {
                  "required": true,
                  "script_count": 67,
                  "scripts": [
                    "scripts/adjudicate_output_review.py",
                    "scripts/build_confusion_matrix.py",
                    "scripts/build_skill_atlas.py",
                    "scripts/check_update.py",
                    "scripts/ci_test.py",
                    "scripts/collect_feedback.py",
                    "scripts/compile_skill.py",
                    "scripts/create_iteration_snapshot.py",
                    "scripts/cross_packager.py",
                    "scripts/emit_telemetry_event.py",
                    "scripts/export_skill_ir.py",
                    "scripts/github_benchmark_scan.py",
                    "scripts/import_telemetry_events.py",
                    "scripts/init_skill.py",
                    "scripts/prepare_output_review_kit.py",
                    "scripts/prepare_world_class_submission_kit.py",
                    "scripts/probe_runtime_permissions.py",
                    "scripts/promotion_checker.py",
                    "scripts/propose_adaptation.py",
                    "scripts/python_compat_check.py",
                    "scripts/registry_audit.py",
                    "scripts/render_adoption_drift_report.py",
                    "scripts/render_architecture_maintainability.py",
                    "scripts/render_artifact_design_profile.py",
                    "scripts/render_baseline_compare.py",
                    "scripts/render_benchmark_reproducibility.py",
                    "scripts/render_context_reports.py",
                    "scripts/render_description_drift_history.py",
                    "scripts/render_eval_dashboard.py",
                    "scripts/render_intent_confidence.py",
                    "scripts/render_intent_dialogue.py",
                    "scripts/render_iteration_directions.py",
                    "scripts/render_iteration_ledger.py",
                    "scripts/render_output_risk_profile.py",
                    "scripts/render_portability_report.py",
                    "scripts/render_prompt_quality_profile.py",
                    "scripts/render_reference_scan.py",
                    "scripts/render_reference_synthesis.py",
                    "scripts/render_regression_history.py",
                    "scripts/render_review_annotations.py",
                    "scripts/render_review_studio.py",
                    "scripts/render_review_viewer.py",
                    "scripts/render_review_waivers.py",
                    "scripts/render_skill_interpretation.py",
                    "scripts/render_skill_os2_audit.py",
                    "scripts/render_skill_os2_coverage.py",
                    "scripts/render_skill_overview.py",
                    "scripts/render_social_preview.py",
                    "scripts/render_system_model.py",
                    "scripts/render_telemetry_hook_recipes.py",
                    "scripts/render_world_class_claim_guard.py",
                    "scripts/render_world_class_evidence_intake.py",
                    "scripts/render_world_class_evidence_ledger.py",
                    "scripts/render_world_class_evidence_plan.py",
                    "scripts/render_world_class_operator_runbook.py",
                    "scripts/render_world_class_submission_review.py",
                    "scripts/run_conformance_suite.py",
                    "scripts/run_description_optimization_suite.py",
                    "scripts/run_output_eval.py",
                    "scripts/run_output_execution.py",
                    "scripts/simulate_install.py",
                    "scripts/summarize_user_signals.py",
                    "scripts/sync_local_install.py",
                    "scripts/telemetry_native_host.py",
                    "scripts/trust_check.py",
                    "scripts/upgrade_check.py",
                    "scripts/verify_package.py"
                  ],
                  "review_reason": "Scripts write local files or generated artifacts."
                },
                "subprocess": {
                  "required": true,
                  "script_count": 9,
                  "scripts": [
                    "scripts/ci_test.py",
                    "scripts/render_benchmark_reproducibility.py",
                    "scripts/render_eval_dashboard.py",
                    "scripts/run_eval_suite.py",
                    "scripts/run_output_execution.py",
                    "scripts/sync_local_install.py",
                    "scripts/trust_check.py",
                    "scripts/yao.py",
                    "scripts/yao_cli_runtime.py"
                  ],
                  "review_reason": "Scripts spawn local commands and need operator review."
                },
                "interactive": {
                  "required": false,
                  "script_count": 0,
                  "scripts": [],
                  "review_reason": ""
                }
              },
              "network_policy": {
                "source": "security/network_policy.json",
                "covered_scripts": [
                  "scripts/check_update.py",
                  "scripts/github_benchmark_scan.py",
                  "scripts/provider_output_eval_runner.py"
                ],
                "missing_scripts": [],
                "mismatches": []
              },
              "help_smoke": {
                "enabled": true,
                "checked_count": 80,
                "failed_count": 0,
                "failed_scripts": []
              },
              "trust_summary": {
                "secret_findings": 0,
                "network_script_count": 3,
                "file_write_script_count": 67,
                "subprocess_script_count": 9,
                "interactive_script_count": 0,
                "help_smoke_failed_count": 0
              }
            },
            "source_files_count": 6,
            "target": "generic",
            "target_permission_contract": {
              "schema_version": "1.0",
              "target": "generic",
              "permission_model": "agent-skills-compatible-metadata",
              "native_enforcement": false,
              "representation": "targets/generic/adapter.json::target_permission_contract",
              "review_required": true,
              "declared_capabilities": [
                "network",
                "file_write",
                "subprocess"
              ],
              "capability_counts": {
                "network": 3,
                "file_write": 67,
                "subprocess": 9,
                "interactive": 0
              },
              "evidence": "reports/security_trust_report.json",
              "operator_note": "Generic target exposes permission metadata for downstream clients to enforce or review."
            },
            "target_native_contract": {
              "schema_version": "1.0",
              "target": "generic",
              "native_surface": "Agent Skills compatible neutral package",
              "activation": {
                "policy": "Use SKILL.md name and description; consumers decide automatic or manual activation.",
                "trigger_description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
                "manual_activation_supported": true,
                "automatic_activation_note": "Depends on the target client route/catalog implementation."
              },
              "resources": {
                "strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.",
                "counts": {
                  "references": 34,
                  "scripts": 80,
                  "assets": 2,
                  "reports": 43
                },
                "generated_files": [
                  "targets/generic/adapter.json"
                ]
              },
              "scripts": {
                "strategy": "Expose script and permission metadata for downstream clients or installers to enforce.",
                "script_count": 80,
                "help_smoke_failed_count": 0
              },
              "permissions": {
                "enforcement": "consumer-enforced-or-metadata-only",
                "native_enforcement": false,
                "declared_capabilities": [
                  "network",
                  "file_write",
                  "subprocess"
                ],
                "review_required": true
              },
              "review": {
                "artifacts": [
                  "targets/generic/adapter.json",
                  "reports/review-studio.html"
                ],
                "fallback_behavior": "Neutral source is the runtime fallback.",
                "unsupported_native_features": []
              },
              "install_scope": "generic Agent Skills compatible root"
            },
            "degradation_strategy": "neutral-source",
            "target_runtime": {
              "adapter_mode": "agent-skills-compatible",
              "generated_files": [
                "targets/generic/adapter.json"
              ],
              "metadata_mapping": {
                "display_name": "targets/generic/adapter.json::display_name",
                "default_prompt": "targets/generic/adapter.json::default_prompt",
                "activation": "targets/generic/adapter.json::activation_mode",
                "execution": "targets/generic/adapter.json::execution_context",
                "trust": "targets/generic/adapter.json::trust_level",
                "permissions": "targets/generic/adapter.json::target_permission_contract",
                "degradation": "targets/generic/adapter.json::degradation_strategy"
              },
              "preserved_semantics": [
                "trigger",
                "workflow-counts",
                "resources",
                "eval-plan",
                "risk",
                "governance",
                "runtime",
                "trust",
                "permissions"
              ],
              "native_surface": "Agent Skills compatible neutral package"
            }
          },
          "permission_contract": {
            "schema_version": "1.0",
            "source": "reports/security_trust_report.json",
            "source_available": true,
            "declared_capabilities": [
              "network",
              "file_write",
              "subprocess"
            ],
            "review_required": true,
            "capabilities": {
              "network": {
                "required": true,
                "script_count": 3,
                "scripts": [
                  "scripts/check_update.py",
                  "scripts/github_benchmark_scan.py",
                  "scripts/provider_output_eval_runner.py"
                ],
                "review_reason": "Outbound hosts must match security/network_policy.json."
              },
              "file_write": {
                "required": true,
                "script_count": 67,
                "scripts": [
                  "scripts/adjudicate_output_review.py",
                  "scripts/build_confusion_matrix.py",
                  "scripts/build_skill_atlas.py",
                  "scripts/check_update.py",
                  "scripts/ci_test.py",
                  "scripts/collect_feedback.py",
                  "scripts/compile_skill.py",
                  "scripts/create_iteration_snapshot.py",
                  "scripts/cross_packager.py",
                  "scripts/emit_telemetry_event.py",
                  "scripts/export_skill_ir.py",
                  "scripts/github_benchmark_scan.py",
                  "scripts/import_telemetry_events.py",
                  "scripts/init_skill.py",
                  "scripts/prepare_output_review_kit.py",
                  "scripts/prepare_world_class_submission_kit.py",
                  "scripts/probe_runtime_permissions.py",
                  "scripts/promotion_checker.py",
                  "scripts/propose_adaptation.py",
                  "scripts/python_compat_check.py",
                  "scripts/registry_audit.py",
                  "scripts/render_adoption_drift_report.py",
                  "scripts/render_architecture_maintainability.py",
                  "scripts/render_artifact_design_profile.py",
                  "scripts/render_baseline_compare.py",
                  "scripts/render_benchmark_reproducibility.py",
                  "scripts/render_context_reports.py",
                  "scripts/render_description_drift_history.py",
                  "scripts/render_eval_dashboard.py",
                  "scripts/render_intent_confidence.py",
                  "scripts/render_intent_dialogue.py",
                  "scripts/render_iteration_directions.py",
                  "scripts/render_iteration_ledger.py",
                  "scripts/render_output_risk_profile.py",
                  "scripts/render_portability_report.py",
                  "scripts/render_prompt_quality_profile.py",
                  "scripts/render_reference_scan.py",
                  "scripts/render_reference_synthesis.py",
                  "scripts/render_regression_history.py",
                  "scripts/render_review_annotations.py",
                  "scripts/render_review_studio.py",
                  "scripts/render_review_viewer.py",
                  "scripts/render_review_waivers.py",
                  "scripts/render_skill_interpretation.py",
                  "scripts/render_skill_os2_audit.py",
                  "scripts/render_skill_os2_coverage.py",
                  "scripts/render_skill_overview.py",
                  "scripts/render_social_preview.py",
                  "scripts/render_system_model.py",
                  "scripts/render_telemetry_hook_recipes.py",
                  "scripts/render_world_class_claim_guard.py",
                  "scripts/render_world_class_evidence_intake.py",
                  "scripts/render_world_class_evidence_ledger.py",
                  "scripts/render_world_class_evidence_plan.py",
                  "scripts/render_world_class_operator_runbook.py",
                  "scripts/render_world_class_submission_review.py",
                  "scripts/run_conformance_suite.py",
                  "scripts/run_description_optimization_suite.py",
                  "scripts/run_output_eval.py",
                  "scripts/run_output_execution.py",
                  "scripts/simulate_install.py",
                  "scripts/summarize_user_signals.py",
                  "scripts/sync_local_install.py",
                  "scripts/telemetry_native_host.py",
                  "scripts/trust_check.py",
                  "scripts/upgrade_check.py",
                  "scripts/verify_package.py"
                ],
                "review_reason": "Scripts write local files or generated artifacts."
              },
              "subprocess": {
                "required": true,
                "script_count": 9,
                "scripts": [
                  "scripts/ci_test.py",
                  "scripts/render_benchmark_reproducibility.py",
                  "scripts/render_eval_dashboard.py",
                  "scripts/run_eval_suite.py",
                  "scripts/run_output_execution.py",
                  "scripts/sync_local_install.py",
                  "scripts/trust_check.py",
                  "scripts/yao.py",
                  "scripts/yao_cli_runtime.py"
                ],
                "review_reason": "Scripts spawn local commands and need operator review."
              },
              "interactive": {
                "required": false,
                "script_count": 0,
                "scripts": [],
                "review_reason": ""
              }
            },
            "network_policy": {
              "source": "security/network_policy.json",
              "covered_scripts": [
                "scripts/check_update.py",
                "scripts/github_benchmark_scan.py",
                "scripts/provider_output_eval_runner.py"
              ],
              "missing_scripts": [],
              "mismatches": []
            },
            "help_smoke": {
              "enabled": true,
              "checked_count": 80,
              "failed_count": 0,
              "failed_scripts": []
            },
            "trust_summary": {
              "secret_findings": 0,
              "network_script_count": 3,
              "file_write_script_count": 67,
              "subprocess_script_count": 9,
              "interactive_script_count": 0,
              "help_smoke_failed_count": 0
            }
          },
          "target_permission_contract": {
            "schema_version": "1.0",
            "target": "generic",
            "permission_model": "agent-skills-compatible-metadata",
            "native_enforcement": false,
            "representation": "targets/generic/adapter.json::target_permission_contract",
            "review_required": true,
            "declared_capabilities": [
              "network",
              "file_write",
              "subprocess"
            ],
            "capability_counts": {
              "network": 3,
              "file_write": 67,
              "subprocess": 9,
              "interactive": 0
            },
            "evidence": "reports/security_trust_report.json",
            "operator_note": "Generic target exposes permission metadata for downstream clients to enforce or review."
          },
          "target_native_contract": {
            "schema_version": "1.0",
            "target": "generic",
            "native_surface": "Agent Skills compatible neutral package",
            "activation": {
              "policy": "Use SKILL.md name and description; consumers decide automatic or manual activation.",
              "trigger_description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
              "manual_activation_supported": true,
              "automatic_activation_note": "Depends on the target client route/catalog implementation."
            },
            "resources": {
              "strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.",
              "counts": {
                "references": 34,
                "scripts": 80,
                "assets": 2,
                "reports": 43
              },
              "generated_files": [
                "targets/generic/adapter.json"
              ]
            },
            "scripts": {
              "strategy": "Expose script and permission metadata for downstream clients or installers to enforce.",
              "script_count": 80,
              "help_smoke_failed_count": 0
            },
            "permissions": {
              "enforcement": "consumer-enforced-or-metadata-only",
              "native_enforcement": false,
              "declared_capabilities": [
                "network",
                "file_write",
                "subprocess"
              ],
              "review_required": true
            },
            "review": {
              "artifacts": [
                "targets/generic/adapter.json",
                "reports/review-studio.html"
              ],
              "fallback_behavior": "Neutral source is the runtime fallback.",
              "unsupported_native_features": []
            },
            "install_scope": "generic Agent Skills compatible root"
          },
          "target_transform": {
            "target": "generic",
            "adapter_mode": "agent-skills-compatible",
            "generated_files": [
              "targets/generic/adapter.json"
            ],
            "metadata_mapping": {
              "display_name": "targets/generic/adapter.json::display_name",
              "default_prompt": "targets/generic/adapter.json::default_prompt",
              "activation": "targets/generic/adapter.json::activation_mode",
              "execution": "targets/generic/adapter.json::execution_context",
              "trust": "targets/generic/adapter.json::trust_level",
              "permissions": "targets/generic/adapter.json::target_permission_contract",
              "degradation": "targets/generic/adapter.json::degradation_strategy"
            },
            "preserved_semantics": [
              "trigger",
              "workflow-counts",
              "resources",
              "eval-plan",
              "risk",
              "governance",
              "runtime",
              "trust",
              "permissions"
            ],
            "degradation_strategy": "neutral-source",
            "permission_representation": "targets/generic/adapter.json::target_permission_contract",
            "native_surface": "Agent Skills compatible neutral package",
            "activation_policy": "Use SKILL.md name and description; consumers decide automatic or manual activation.",
            "resource_strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.",
            "script_strategy": "Expose script and permission metadata for downstream clients or installers to enforce.",
            "permission_enforcement": "consumer-enforced-or-metadata-only"
          },
          "unsupported_features": [],
          "warnings": [],
          "failures": []
        },
        {
          "schema_version": "1.0",
          "target": "agent-skills-compatible",
          "status": "pass",
          "compiler": {
            "name": "yao-skill-ir-compiler",
            "schema_version": "1.0",
            "source": "skill-ir",
            "ir_source": "skill-ir/examples/yao-meta-skill.json",
            "ir_schema_version": "2.0.0"
          },
          "source": {
            "skill_dir": ".",
            "canonical_metadata": "agents/interface.yaml",
            "declared_targets": [
              "openai",
              "claude",
              "generic",
              "agent-skills-compatible",
              "vscode"
            ]
          },
          "compiled_contract": {
            "name": "yao-meta-skill",
            "title": "Yao Meta Skill",
            "version": "1.1.0",
            "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
            "job_to_be_done": "Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse.",
            "trigger": {
              "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
              "should_trigger": [
                "Create a skill from this repeated workflow.",
                "Turn this runbook into a reusable agent skill.",
                "Convert this process note into a reusable skill package for the team.",
                "Improve this skill description and add evals.",
                "Refactor this prompt into a proper skill package.",
                "Package this skill for team reuse.",
                "Create a meta-skill for packaging internal workflows.",
                "Standardize this recurring workflow as a shareable skill package with references."
              ],
              "should_not_trigger": [
                "Explain what a workflow is.",
                "Just explain what a skill is.",
                "Summarize this random note.",
                "Translate this README into Japanese.",
                "Write a product headline for this landing page.",
                "Draft a blog title for this article.",
                "Rewrite this paragraph more clearly, but do not package anything.",
                "Explain the difference between a runbook and a workflow.",
                "one-off writing, translation, explanation, or brainstorming requests that do not need a reusable skill",
                "general code review or debugging unless the user is packaging that workflow as a skill"
              ],
              "edge_cases": [
                "Create a one-off prompt for this task.",
                "Write a custom answer for this request without creating a skill package.",
                "Help me brainstorm process ideas without building a skill.",
                "Improve this README but do not turn it into a skill.",
                "Make a checklist for this task, but not a reusable skill.",
                "Create a reusable-looking checklist, but keep it as a plain note instead of a skill.",
                "Review this process note and explain it, no packaging needed.",
                "Turn this into a checklist and template, but stop short of making a full skill."
              ]
            },
            "workflow": {
              "steps": [
                "Decide whether the request should become a skill and choose the lightest fit.",
                "Capture job, output, exclusions, constraints, and standards.",
                "Run reference scan: external benchmarks first, user references second, local fit third; surface only uncertainty or conflict.",
                "Write the `description` early and test route quality before expanding the package.",
                "Add output-risk, artifact-design, prompt-quality, and system-model reports only when they matter.",
                "Add only folders and gates that earn their keep.",
                "Surface the top three next iteration directions."
              ],
              "decision_points": [
                "Route by frontmatter `description`.",
                "Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.",
                "Use the lightest reliable process.",
                "`Scaffold`: exploratory or personal.",
                "`Production`: team reuse.",
                "`Library`: shared infrastructure.",
                "`Governed`: high-trust, policy-sensitive, or release-critical.",
                "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.",
                "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.",
                "Do not silently broaden the skill into adjacent jobs just because the examples are nearby."
              ],
              "failure_modes": [
                "Tables can render as dense grids with weak hierarchy or poor mobile readability.",
                "Long bullets can make the output look complete while hiding the actual decision logic.",
                "Footnote markers or dense citation notes can interrupt the reading flow.",
                "Evidence can be over-attached to obvious statements and under-attached to risky claims.",
                "Screenshots can be captured from the wrong state, wrong viewport, or wrong crop.",
                "Missing screenshots can cause the skill to invent visual references instead of declaring the gap.",
                "Users start invoking the skill for adjacent one-off or explanation-only requests.",
                "Outputs remain valid but become generic, cluttered, or weakly aligned with the user's domain.",
                "Borrowed benchmark patterns no longer fit the local job or add ceremony without payoff.",
                "Skill usage becomes team-critical while ownership, review cadence, or rollback evidence stays informal."
              ]
            },
            "resources": {
              "references": [
                "references/artifact-design-doctrine.md",
                "references/authoring-discipline.md",
                "references/autonomous-adaptation.md",
                "references/distribution-registry-method.md",
                "references/eval-playbook.md",
                "references/gate-selection.md",
                "references/governance.md",
                "references/human-review-template.md",
                "references/intent-dialogue.md",
                "references/iteration-philosophy.md",
                "references/non-skill-decision-tree.md",
                "references/operating-modes.md",
                "references/output-eval-method.md",
                "references/output-quality-risk.md",
                "references/output-visual-quality.md",
                "references/packaging-contracts.md",
                "references/pattern-extraction-doctrine.md",
                "references/platform-capability-matrix.md",
                "references/prompt-engineering-doctrine.md",
                "references/qa-ladder.md",
                "references/reference-scan.md",
                "references/regression-cause-taxonomy.md",
                "references/resource-boundaries.md",
                "references/review-studio-method.md",
                "references/review-waiver-method.md",
                "references/runtime-conformance-method.md",
                "references/skill-archetypes.md",
                "references/skill-atlas-method.md",
                "references/skill-engineering-method.md",
                "references/skill-ir-method.md",
                "references/systems-thinking-doctrine.md",
                "references/telemetry-drift-method.md",
                "references/trust-security-method.md",
                "references/user-memory-policy.md"
              ],
              "scripts": [
                "scripts/adjudicate_output_review.py",
                "scripts/build_confusion_matrix.py",
                "scripts/build_skill_atlas.py",
                "scripts/check_update.py",
                "scripts/ci_test.py",
                "scripts/collect_feedback.py",
                "scripts/compile_skill.py",
                "scripts/context_sizer.py",
                "scripts/create_iteration_snapshot.py",
                "scripts/cross_packager.py",
                "scripts/diff_eval.py",
                "scripts/emit_telemetry_event.py",
                "scripts/export_skill_ir.py",
                "scripts/github_benchmark_scan.py",
                "scripts/governance_check.py",
                "scripts/html_rendering.py",
                "scripts/import_telemetry_events.py",
                "scripts/init_skill.py",
                "scripts/judge_blind_eval.py",
                "scripts/lint_skill.py",
                "scripts/local_output_eval_runner.py",
                "scripts/optimize_description.py",
                "scripts/prepare_output_review_kit.py",
                "scripts/prepare_world_class_submission_kit.py",
                "scripts/probe_runtime_permissions.py",
                "scripts/promotion_checker.py",
                "scripts/propose_adaptation.py",
                "scripts/provider_output_eval_runner.py",
                "scripts/python_compat_check.py",
                "scripts/registry_audit.py",
                "scripts/render_adoption_drift_report.py",
                "scripts/render_architecture_maintainability.py",
                "scripts/render_artifact_design_profile.py",
                "scripts/render_baseline_compare.py",
                "scripts/render_benchmark_reproducibility.py",
                "scripts/render_context_reports.py",
                "scripts/render_description_drift_history.py",
                "scripts/render_eval_dashboard.py",
                "scripts/render_intent_confidence.py",
                "scripts/render_intent_dialogue.py",
                "scripts/render_iteration_directions.py",
                "scripts/render_iteration_ledger.py",
                "scripts/render_output_risk_profile.py",
                "scripts/render_portability_report.py",
                "scripts/render_prompt_quality_profile.py",
                "scripts/render_reference_scan.py",
                "scripts/render_reference_synthesis.py",
                "scripts/render_regression_history.py",
                "scripts/render_review_annotations.py",
                "scripts/render_review_studio.py",
                "scripts/render_review_viewer.py",
                "scripts/render_review_waivers.py",
                "scripts/render_skill_os2_audit.py",
                "scripts/render_skill_os2_coverage.py",
                "scripts/render_skill_overview.py",
                "scripts/render_social_preview.py",
                "scripts/render_system_model.py",
                "scripts/render_telemetry_hook_recipes.py",
                "scripts/render_world_class_claim_guard.py",
                "scripts/render_world_class_evidence_intake.py",
                "scripts/render_world_class_evidence_ledger.py",
                "scripts/render_world_class_evidence_plan.py",
                "scripts/render_world_class_operator_runbook.py",
                "scripts/render_world_class_submission_review.py",
                "scripts/resource_boundary_check.py",
                "scripts/review_studio_action_evidence.py",
                "scripts/review_studio_actions.py",
                "scripts/review_studio_data.py",
                "scripts/review_studio_formatting.py",
                "scripts/review_studio_gates.py",
                "scripts/review_studio_layout.py",
                "scripts/review_studio_output_review.py",
                "scripts/review_studio_waivers.py",
                "scripts/review_studio_world_class.py",
                "scripts/review_viewer_data.py",
                "scripts/run_conformance_suite.py",
                "scripts/run_description_optimization_suite.py",
                "scripts/run_eval_suite.py",
                "scripts/run_output_eval.py",
                "scripts/run_output_execution.py"
              ],
              "assets": [
                "templates/basic_skill.md.j2",
                "templates/complex_skill.md.j2"
              ],
              "reports": [
                "reports/benchmark_methodology.md",
                "reports/intent-context.json",
                "reports/intent-confidence.json",
                "reports/intent-confidence.md",
                "reports/reference-synthesis.json",
                "reports/reference-synthesis.md",
                "reports/output-risk-profile.json",
                "reports/output-risk-profile.md",
                "reports/artifact-design-profile.json",
                "reports/artifact-design-profile.md",
                "reports/prompt-quality-profile.json",
                "reports/prompt-quality-profile.md",
                "reports/system-model.json",
                "reports/system-model.md",
                "reports/iteration-directions.json",
                "reports/iteration-directions.md",
                "reports/skill-overview.json",
                "reports/skill-overview.html",
                "reports/output_quality_scorecard.json",
                "reports/output_quality_scorecard.md",
                "reports/output_execution_runs.json",
                "reports/output_execution_runs.md",
                "reports/output_blind_review_pack.json",
                "reports/output_blind_review_pack.md",
                "reports/output_blind_answer_key.json",
                "reports/output_review_adjudication.json",
                "reports/output_review_adjudication.md",
                "reports/review_annotations.json",
                "reports/review_annotations.md",
                "reports/conformance_matrix.json",
                "reports/conformance_matrix.md",
                "reports/security_trust_report.json",
                "reports/security_trust_report.md",
                "reports/runtime_permission_probes.json",
                "reports/runtime_permission_probes.md",
                "reports/telemetry_hook_recipes.json",
                "reports/telemetry_hook_recipes.md",
                "reports/skill_atlas.json",
                "reports/skill_atlas.html",
                "reports/skill-os-2-review.md",
                "reports/portability_score.json",
                "reports/portability_score.md",
                "reports/governance_score.json"
              ],
              "counts": {
                "references": 34,
                "scripts": 80,
                "assets": 2,
                "reports": 43
              }
            },
            "eval_plan": {
              "trigger": [
                "evals/README.md",
                "evals/adaptation/user_signals.example.jsonl",
                "evals/adversarial/trigger_cases.json",
                "evals/blind_holdout/trigger_cases.json",
                "evals/confusion/route_cases.json",
                "evals/dev/trigger_cases.json",
                "evals/failure-cases.md",
                "evals/history/2026-03-31-context-first-pack.json",
                "evals/history/2026-03-31-family-suite-expansion.json",
                "evals/history/2026-03-31-governance-quality-gates.json",
                "evals/history/2026-03-31-governed-assets-and-history.json",
                "evals/history/2026-04-01-route-scorecard-foundation.json",
                "evals/history/README.md",
                "evals/history/description_optimization/2026-03-31-description-optimization-suite.json",
                "evals/history/description_optimization/2026-04-01-adversarial-calibration-and-family-drift.json",
                "evals/history/description_optimization/2026-04-01-blind-holdout-and-drift-history.json",
                "evals/history/description_optimization/2026-04-01-judge-backed-blind-eval.json",
                "evals/history/description_optimization/README.md",
                "evals/holdout/trigger_cases.json",
                "evals/output/cases.jsonl",
                "evals/output/fixtures/release-brief-source.md",
                "evals/output/schema.json",
                "evals/packaging_expectations.json",
                "evals/promotion_policy.md",
                "evals/semantic_config.json",
                "evals/train/trigger_cases.json",
                "evals/trigger_cases.json"
              ],
              "output": [
                "evals/output/cases.jsonl",
                "evals/output/fixtures/release-brief-source.md",
                "evals/output/schema.json"
              ],
              "adversarial": [
                "evals/adversarial/trigger_cases.json"
              ],
              "baseline": "without_skill",
              "counts": {
                "trigger": 27,
                "output": 3,
                "adversarial": 1,
                "baseline": 1
              }
            },
            "risk": {
              "output_risk": "high",
              "execution_risk": "medium",
              "trust_boundary": "external"
            },
            "governance": {
              "owner": "Yao Team",
              "maturity": "governed",
              "review_cadence": "quarterly",
              "review_due": ""
            },
            "runtime": {
              "activation": {
                "mode": "manual",
                "paths": []
              },
              "execution": {
                "context": "inline",
                "shell": "bash"
              },
              "trust": {
                "source_tier": "local",
                "remote_inline_execution": "forbid",
                "remote_metadata_policy": "allow-metadata-only"
              },
              "adapter_targets": [
                "openai",
                "claude",
                "generic",
                "vscode"
              ],
              "canonical_format": "agent-skills"
            },
            "permissions": {
              "schema_version": "1.0",
              "source": "reports/security_trust_report.json",
              "source_available": true,
              "declared_capabilities": [
                "network",
                "file_write",
                "subprocess"
              ],
              "review_required": true,
              "capabilities": {
                "network": {
                  "required": true,
                  "script_count": 3,
                  "scripts": [
                    "scripts/check_update.py",
                    "scripts/github_benchmark_scan.py",
                    "scripts/provider_output_eval_runner.py"
                  ],
                  "review_reason": "Outbound hosts must match security/network_policy.json."
                },
                "file_write": {
                  "required": true,
                  "script_count": 67,
                  "scripts": [
                    "scripts/adjudicate_output_review.py",
                    "scripts/build_confusion_matrix.py",
                    "scripts/build_skill_atlas.py",
                    "scripts/check_update.py",
                    "scripts/ci_test.py",
                    "scripts/collect_feedback.py",
                    "scripts/compile_skill.py",
                    "scripts/create_iteration_snapshot.py",
                    "scripts/cross_packager.py",
                    "scripts/emit_telemetry_event.py",
                    "scripts/export_skill_ir.py",
                    "scripts/github_benchmark_scan.py",
                    "scripts/import_telemetry_events.py",
                    "scripts/init_skill.py",
                    "scripts/prepare_output_review_kit.py",
                    "scripts/prepare_world_class_submission_kit.py",
                    "scripts/probe_runtime_permissions.py",
                    "scripts/promotion_checker.py",
                    "scripts/propose_adaptation.py",
                    "scripts/python_compat_check.py",
                    "scripts/registry_audit.py",
                    "scripts/render_adoption_drift_report.py",
                    "scripts/render_architecture_maintainability.py",
                    "scripts/render_artifact_design_profile.py",
                    "scripts/render_baseline_compare.py",
                    "scripts/render_benchmark_reproducibility.py",
                    "scripts/render_context_reports.py",
                    "scripts/render_description_drift_history.py",
                    "scripts/render_eval_dashboard.py",
                    "scripts/render_intent_confidence.py",
                    "scripts/render_intent_dialogue.py",
                    "scripts/render_iteration_directions.py",
                    "scripts/render_iteration_ledger.py",
                    "scripts/render_output_risk_profile.py",
                    "scripts/render_portability_report.py",
                    "scripts/render_prompt_quality_profile.py",
                    "scripts/render_reference_scan.py",
                    "scripts/render_reference_synthesis.py",
                    "scripts/render_regression_history.py",
                    "scripts/render_review_annotations.py",
                    "scripts/render_review_studio.py",
                    "scripts/render_review_viewer.py",
                    "scripts/render_review_waivers.py",
                    "scripts/render_skill_interpretation.py",
                    "scripts/render_skill_os2_audit.py",
                    "scripts/render_skill_os2_coverage.py",
                    "scripts/render_skill_overview.py",
                    "scripts/render_social_preview.py",
                    "scripts/render_system_model.py",
                    "scripts/render_telemetry_hook_recipes.py",
                    "scripts/render_world_class_claim_guard.py",
                    "scripts/render_world_class_evidence_intake.py",
                    "scripts/render_world_class_evidence_ledger.py",
                    "scripts/render_world_class_evidence_plan.py",
                    "scripts/render_world_class_operator_runbook.py",
                    "scripts/render_world_class_submission_review.py",
                    "scripts/run_conformance_suite.py",
                    "scripts/run_description_optimization_suite.py",
                    "scripts/run_output_eval.py",
                    "scripts/run_output_execution.py",
                    "scripts/simulate_install.py",
                    "scripts/summarize_user_signals.py",
                    "scripts/sync_local_install.py",
                    "scripts/telemetry_native_host.py",
                    "scripts/trust_check.py",
                    "scripts/upgrade_check.py",
                    "scripts/verify_package.py"
                  ],
                  "review_reason": "Scripts write local files or generated artifacts."
                },
                "subprocess": {
                  "required": true,
                  "script_count": 9,
                  "scripts": [
                    "scripts/ci_test.py",
                    "scripts/render_benchmark_reproducibility.py",
                    "scripts/render_eval_dashboard.py",
                    "scripts/run_eval_suite.py",
                    "scripts/run_output_execution.py",
                    "scripts/sync_local_install.py",
                    "scripts/trust_check.py",
                    "scripts/yao.py",
                    "scripts/yao_cli_runtime.py"
                  ],
                  "review_reason": "Scripts spawn local commands and need operator review."
                },
                "interactive": {
                  "required": false,
                  "script_count": 0,
                  "scripts": [],
                  "review_reason": ""
                }
              },
              "network_policy": {
                "source": "security/network_policy.json",
                "covered_scripts": [
                  "scripts/check_update.py",
                  "scripts/github_benchmark_scan.py",
                  "scripts/provider_output_eval_runner.py"
                ],
                "missing_scripts": [],
                "mismatches": []
              },
              "help_smoke": {
                "enabled": true,
                "checked_count": 80,
                "failed_count": 0,
                "failed_scripts": []
              },
              "trust_summary": {
                "secret_findings": 0,
                "network_script_count": 3,
                "file_write_script_count": 67,
                "subprocess_script_count": 9,
                "interactive_script_count": 0,
                "help_smoke_failed_count": 0
              }
            },
            "source_files_count": 6,
            "target": "agent-skills-compatible",
            "target_permission_contract": {
              "schema_version": "1.0",
              "target": "agent-skills-compatible",
              "permission_model": "metadata-only",
              "native_enforcement": false,
              "representation": "adapter metadata",
              "review_required": true,
              "declared_capabilities": [
                "network",
                "file_write",
                "subprocess"
              ],
              "capability_counts": {
                "network": 3,
                "file_write": 67,
                "subprocess": 9,
                "interactive": 0
              },
              "evidence": "reports/security_trust_report.json",
              "operator_note": "Permission semantics are preserved as metadata for reviewer visibility."
            },
            "target_native_contract": {
              "schema_version": "1.0",
              "target": "agent-skills-compatible",
              "native_surface": "Agent Skills standard source tree",
              "activation": {
                "policy": "Use SKILL.md frontmatter name and description for progressive disclosure.",
                "trigger_description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
                "manual_activation_supported": true,
                "automatic_activation_note": "Depends on the target client route/catalog implementation."
              },
              "resources": {
                "strategy": "Keep optional directories as relative resources next to SKILL.md.",
                "counts": {
                  "references": 34,
                  "scripts": 80,
                  "assets": 2,
                  "reports": 43
                },
                "generated_files": [
                  "SKILL.md",
                  "agents/interface.yaml"
                ]
              },
              "scripts": {
                "strategy": "Scripts remain local optional resources and should advertise --help when executable.",
                "script_count": 80,
                "help_smoke_failed_count": 0
              },
              "permissions": {
                "enforcement": "consumer-enforced-or-metadata-only",
                "native_enforcement": false,
                "declared_capabilities": [
                  "network",
                  "file_write",
                  "subprocess"
                ],
                "review_required": true
              },
              "review": {
                "artifacts": [
                  "SKILL.md",
                  "agents/interface.yaml",
                  "reports/review-studio.html"
                ],
                "fallback_behavior": "The source tree itself is the target artifact.",
                "unsupported_native_features": []
              },
              "install_scope": "Agent Skills source root"
            },
            "degradation_strategy": "neutral-source",
            "target_runtime": {
              "adapter_mode": "neutral-agent-skills-source",
              "generated_files": [
                "SKILL.md",
                "agents/interface.yaml"
              ],
              "metadata_mapping": {
                "name": "SKILL.md::frontmatter.name",
                "description": "SKILL.md::frontmatter.description",
                "interface": "agents/interface.yaml",
                "manifest": "manifest.json"
              },
              "preserved_semantics": [
                "trigger",
                "workflow",
                "resources",
                "eval-plan",
                "risk",
                "governance",
                "runtime",
                "trust",
                "permissions"
              ],
              "native_surface": "Agent Skills standard source tree"
            }
          },
          "permission_contract": {
            "schema_version": "1.0",
            "source": "reports/security_trust_report.json",
            "source_available": true,
            "declared_capabilities": [
              "network",
              "file_write",
              "subprocess"
            ],
            "review_required": true,
            "capabilities": {
              "network": {
                "required": true,
                "script_count": 3,
                "scripts": [
                  "scripts/check_update.py",
                  "scripts/github_benchmark_scan.py",
                  "scripts/provider_output_eval_runner.py"
                ],
                "review_reason": "Outbound hosts must match security/network_policy.json."
              },
              "file_write": {
                "required": true,
                "script_count": 67,
                "scripts": [
                  "scripts/adjudicate_output_review.py",
                  "scripts/build_confusion_matrix.py",
                  "scripts/build_skill_atlas.py",
                  "scripts/check_update.py",
                  "scripts/ci_test.py",
                  "scripts/collect_feedback.py",
                  "scripts/compile_skill.py",
                  "scripts/create_iteration_snapshot.py",
                  "scripts/cross_packager.py",
                  "scripts/emit_telemetry_event.py",
                  "scripts/export_skill_ir.py",
                  "scripts/github_benchmark_scan.py",
                  "scripts/import_telemetry_events.py",
                  "scripts/init_skill.py",
                  "scripts/prepare_output_review_kit.py",
                  "scripts/prepare_world_class_submission_kit.py",
                  "scripts/probe_runtime_permissions.py",
                  "scripts/promotion_checker.py",
                  "scripts/propose_adaptation.py",
                  "scripts/python_compat_check.py",
                  "scripts/registry_audit.py",
                  "scripts/render_adoption_drift_report.py",
                  "scripts/render_architecture_maintainability.py",
                  "scripts/render_artifact_design_profile.py",
                  "scripts/render_baseline_compare.py",
                  "scripts/render_benchmark_reproducibility.py",
                  "scripts/render_context_reports.py",
                  "scripts/render_description_drift_history.py",
                  "scripts/render_eval_dashboard.py",
                  "scripts/render_intent_confidence.py",
                  "scripts/render_intent_dialogue.py",
                  "scripts/render_iteration_directions.py",
                  "scripts/render_iteration_ledger.py",
                  "scripts/render_output_risk_profile.py",
                  "scripts/render_portability_report.py",
                  "scripts/render_prompt_quality_profile.py",
                  "scripts/render_reference_scan.py",
                  "scripts/render_reference_synthesis.py",
                  "scripts/render_regression_history.py",
                  "scripts/render_review_annotations.py",
                  "scripts/render_review_studio.py",
                  "scripts/render_review_viewer.py",
                  "scripts/render_review_waivers.py",
                  "scripts/render_skill_interpretation.py",
                  "scripts/render_skill_os2_audit.py",
                  "scripts/render_skill_os2_coverage.py",
                  "scripts/render_skill_overview.py",
                  "scripts/render_social_preview.py",
                  "scripts/render_system_model.py",
                  "scripts/render_telemetry_hook_recipes.py",
                  "scripts/render_world_class_claim_guard.py",
                  "scripts/render_world_class_evidence_intake.py",
                  "scripts/render_world_class_evidence_ledger.py",
                  "scripts/render_world_class_evidence_plan.py",
                  "scripts/render_world_class_operator_runbook.py",
                  "scripts/render_world_class_submission_review.py",
                  "scripts/run_conformance_suite.py",
                  "scripts/run_description_optimization_suite.py",
                  "scripts/run_output_eval.py",
                  "scripts/run_output_execution.py",
                  "scripts/simulate_install.py",
                  "scripts/summarize_user_signals.py",
                  "scripts/sync_local_install.py",
                  "scripts/telemetry_native_host.py",
                  "scripts/trust_check.py",
                  "scripts/upgrade_check.py",
                  "scripts/verify_package.py"
                ],
                "review_reason": "Scripts write local files or generated artifacts."
              },
              "subprocess": {
                "required": true,
                "script_count": 9,
                "scripts": [
                  "scripts/ci_test.py",
                  "scripts/render_benchmark_reproducibility.py",
                  "scripts/render_eval_dashboard.py",
                  "scripts/run_eval_suite.py",
                  "scripts/run_output_execution.py",
                  "scripts/sync_local_install.py",
                  "scripts/trust_check.py",
                  "scripts/yao.py",
                  "scripts/yao_cli_runtime.py"
                ],
                "review_reason": "Scripts spawn local commands and need operator review."
              },
              "interactive": {
                "required": false,
                "script_count": 0,
                "scripts": [],
                "review_reason": ""
              }
            },
            "network_policy": {
              "source": "security/network_policy.json",
              "covered_scripts": [
                "scripts/check_update.py",
                "scripts/github_benchmark_scan.py",
                "scripts/provider_output_eval_runner.py"
              ],
              "missing_scripts": [],
              "mismatches": []
            },
            "help_smoke": {
              "enabled": true,
              "checked_count": 80,
              "failed_count": 0,
              "failed_scripts": []
            },
            "trust_summary": {
              "secret_findings": 0,
              "network_script_count": 3,
              "file_write_script_count": 67,
              "subprocess_script_count": 9,
              "interactive_script_count": 0,
              "help_smoke_failed_count": 0
            }
          },
          "target_permission_contract": {
            "schema_version": "1.0",
            "target": "agent-skills-compatible",
            "permission_model": "metadata-only",
            "native_enforcement": false,
            "representation": "adapter metadata",
            "review_required": true,
            "declared_capabilities": [
              "network",
              "file_write",
              "subprocess"
            ],
            "capability_counts": {
              "network": 3,
              "file_write": 67,
              "subprocess": 9,
              "interactive": 0
            },
            "evidence": "reports/security_trust_report.json",
            "operator_note": "Permission semantics are preserved as metadata for reviewer visibility."
          },
          "target_native_contract": {
            "schema_version": "1.0",
            "target": "agent-skills-compatible",
            "native_surface": "Agent Skills standard source tree",
            "activation": {
              "policy": "Use SKILL.md frontmatter name and description for progressive disclosure.",
              "trigger_description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
              "manual_activation_supported": true,
              "automatic_activation_note": "Depends on the target client route/catalog implementation."
            },
            "resources": {
              "strategy": "Keep optional directories as relative resources next to SKILL.md.",
              "counts": {
                "references": 34,
                "scripts": 80,
                "assets": 2,
                "reports": 43
              },
              "generated_files": [
                "SKILL.md",
                "agents/interface.yaml"
              ]
            },
            "scripts": {
              "strategy": "Scripts remain local optional resources and should advertise --help when executable.",
              "script_count": 80,
              "help_smoke_failed_count": 0
            },
            "permissions": {
              "enforcement": "consumer-enforced-or-metadata-only",
              "native_enforcement": false,
              "declared_capabilities": [
                "network",
                "file_write",
                "subprocess"
              ],
              "review_required": true
            },
            "review": {
              "artifacts": [
                "SKILL.md",
                "agents/interface.yaml",
                "reports/review-studio.html"
              ],
              "fallback_behavior": "The source tree itself is the target artifact.",
              "unsupported_native_features": []
            },
            "install_scope": "Agent Skills source root"
          },
          "target_transform": {
            "target": "agent-skills-compatible",
            "adapter_mode": "neutral-agent-skills-source",
            "generated_files": [
              "SKILL.md",
              "agents/interface.yaml"
            ],
            "metadata_mapping": {
              "name": "SKILL.md::frontmatter.name",
              "description": "SKILL.md::frontmatter.description",
              "interface": "agents/interface.yaml",
              "manifest": "manifest.json"
            },
            "preserved_semantics": [
              "trigger",
              "workflow",
              "resources",
              "eval-plan",
              "risk",
              "governance",
              "runtime",
              "trust",
              "permissions"
            ],
            "degradation_strategy": "neutral-source",
            "permission_representation": "adapter metadata",
            "native_surface": "Agent Skills standard source tree",
            "activation_policy": "Use SKILL.md frontmatter name and description for progressive disclosure.",
            "resource_strategy": "Keep optional directories as relative resources next to SKILL.md.",
            "script_strategy": "Scripts remain local optional resources and should advertise --help when executable.",
            "permission_enforcement": "consumer-enforced-or-metadata-only"
          },
          "unsupported_features": [],
          "warnings": [],
          "failures": []
        },
        {
          "schema_version": "1.0",
          "target": "vscode",
          "status": "pass",
          "compiler": {
            "name": "yao-skill-ir-compiler",
            "schema_version": "1.0",
            "source": "skill-ir",
            "ir_source": "skill-ir/examples/yao-meta-skill.json",
            "ir_schema_version": "2.0.0"
          },
          "source": {
            "skill_dir": ".",
            "canonical_metadata": "agents/interface.yaml",
            "declared_targets": [
              "openai",
              "claude",
              "generic",
              "agent-skills-compatible",
              "vscode"
            ]
          },
          "compiled_contract": {
            "name": "yao-meta-skill",
            "title": "Yao Meta Skill",
            "version": "1.1.0",
            "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
            "job_to_be_done": "Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse.",
            "trigger": {
              "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
              "should_trigger": [
                "Create a skill from this repeated workflow.",
                "Turn this runbook into a reusable agent skill.",
                "Convert this process note into a reusable skill package for the team.",
                "Improve this skill description and add evals.",
                "Refactor this prompt into a proper skill package.",
                "Package this skill for team reuse.",
                "Create a meta-skill for packaging internal workflows.",
                "Standardize this recurring workflow as a shareable skill package with references."
              ],
              "should_not_trigger": [
                "Explain what a workflow is.",
                "Just explain what a skill is.",
                "Summarize this random note.",
                "Translate this README into Japanese.",
                "Write a product headline for this landing page.",
                "Draft a blog title for this article.",
                "Rewrite this paragraph more clearly, but do not package anything.",
                "Explain the difference between a runbook and a workflow.",
                "one-off writing, translation, explanation, or brainstorming requests that do not need a reusable skill",
                "general code review or debugging unless the user is packaging that workflow as a skill"
              ],
              "edge_cases": [
                "Create a one-off prompt for this task.",
                "Write a custom answer for this request without creating a skill package.",
                "Help me brainstorm process ideas without building a skill.",
                "Improve this README but do not turn it into a skill.",
                "Make a checklist for this task, but not a reusable skill.",
                "Create a reusable-looking checklist, but keep it as a plain note instead of a skill.",
                "Review this process note and explain it, no packaging needed.",
                "Turn this into a checklist and template, but stop short of making a full skill."
              ]
            },
            "workflow": {
              "steps": [
                "Decide whether the request should become a skill and choose the lightest fit.",
                "Capture job, output, exclusions, constraints, and standards.",
                "Run reference scan: external benchmarks first, user references second, local fit third; surface only uncertainty or conflict.",
                "Write the `description` early and test route quality before expanding the package.",
                "Add output-risk, artifact-design, prompt-quality, and system-model reports only when they matter.",
                "Add only folders and gates that earn their keep.",
                "Surface the top three next iteration directions."
              ],
              "decision_points": [
                "Route by frontmatter `description`.",
                "Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.",
                "Use the lightest reliable process.",
                "`Scaffold`: exploratory or personal.",
                "`Production`: team reuse.",
                "`Library`: shared infrastructure.",
                "`Governed`: high-trust, policy-sensitive, or release-critical.",
                "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.",
                "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.",
                "Do not silently broaden the skill into adjacent jobs just because the examples are nearby."
              ],
              "failure_modes": [
                "Tables can render as dense grids with weak hierarchy or poor mobile readability.",
                "Long bullets can make the output look complete while hiding the actual decision logic.",
                "Footnote markers or dense citation notes can interrupt the reading flow.",
                "Evidence can be over-attached to obvious statements and under-attached to risky claims.",
                "Screenshots can be captured from the wrong state, wrong viewport, or wrong crop.",
                "Missing screenshots can cause the skill to invent visual references instead of declaring the gap.",
                "Users start invoking the skill for adjacent one-off or explanation-only requests.",
                "Outputs remain valid but become generic, cluttered, or weakly aligned with the user's domain.",
                "Borrowed benchmark patterns no longer fit the local job or add ceremony without payoff.",
                "Skill usage becomes team-critical while ownership, review cadence, or rollback evidence stays informal."
              ]
            },
            "resources": {
              "references": [
                "references/artifact-design-doctrine.md",
                "references/authoring-discipline.md",
                "references/autonomous-adaptation.md",
                "references/distribution-registry-method.md",
                "references/eval-playbook.md",
                "references/gate-selection.md",
                "references/governance.md",
                "references/human-review-template.md",
                "references/intent-dialogue.md",
                "references/iteration-philosophy.md",
                "references/non-skill-decision-tree.md",
                "references/operating-modes.md",
                "references/output-eval-method.md",
                "references/output-quality-risk.md",
                "references/output-visual-quality.md",
                "references/packaging-contracts.md",
                "references/pattern-extraction-doctrine.md",
                "references/platform-capability-matrix.md",
                "references/prompt-engineering-doctrine.md",
                "references/qa-ladder.md",
                "references/reference-scan.md",
                "references/regression-cause-taxonomy.md",
                "references/resource-boundaries.md",
                "references/review-studio-method.md",
                "references/review-waiver-method.md",
                "references/runtime-conformance-method.md",
                "references/skill-archetypes.md",
                "references/skill-atlas-method.md",
                "references/skill-engineering-method.md",
                "references/skill-ir-method.md",
                "references/systems-thinking-doctrine.md",
                "references/telemetry-drift-method.md",
                "references/trust-security-method.md",
                "references/user-memory-policy.md"
              ],
              "scripts": [
                "scripts/adjudicate_output_review.py",
                "scripts/build_confusion_matrix.py",
                "scripts/build_skill_atlas.py",
                "scripts/check_update.py",
                "scripts/ci_test.py",
                "scripts/collect_feedback.py",
                "scripts/compile_skill.py",
                "scripts/context_sizer.py",
                "scripts/create_iteration_snapshot.py",
                "scripts/cross_packager.py",
                "scripts/diff_eval.py",
                "scripts/emit_telemetry_event.py",
                "scripts/export_skill_ir.py",
                "scripts/github_benchmark_scan.py",
                "scripts/governance_check.py",
                "scripts/html_rendering.py",
                "scripts/import_telemetry_events.py",
                "scripts/init_skill.py",
                "scripts/judge_blind_eval.py",
                "scripts/lint_skill.py",
                "scripts/local_output_eval_runner.py",
                "scripts/optimize_description.py",
                "scripts/prepare_output_review_kit.py",
                "scripts/prepare_world_class_submission_kit.py",
                "scripts/probe_runtime_permissions.py",
                "scripts/promotion_checker.py",
                "scripts/propose_adaptation.py",
                "scripts/provider_output_eval_runner.py",
                "scripts/python_compat_check.py",
                "scripts/registry_audit.py",
                "scripts/render_adoption_drift_report.py",
                "scripts/render_architecture_maintainability.py",
                "scripts/render_artifact_design_profile.py",
                "scripts/render_baseline_compare.py",
                "scripts/render_benchmark_reproducibility.py",
                "scripts/render_context_reports.py",
                "scripts/render_description_drift_history.py",
                "scripts/render_eval_dashboard.py",
                "scripts/render_intent_confidence.py",
                "scripts/render_intent_dialogue.py",
                "scripts/render_iteration_directions.py",
                "scripts/render_iteration_ledger.py",
                "scripts/render_output_risk_profile.py",
                "scripts/render_portability_report.py",
                "scripts/render_prompt_quality_profile.py",
                "scripts/render_reference_scan.py",
                "scripts/render_reference_synthesis.py",
                "scripts/render_regression_history.py",
                "scripts/render_review_annotations.py",
                "scripts/render_review_studio.py",
                "scripts/render_review_viewer.py",
                "scripts/render_review_waivers.py",
                "scripts/render_skill_os2_audit.py",
                "scripts/render_skill_os2_coverage.py",
                "scripts/render_skill_overview.py",
                "scripts/render_social_preview.py",
                "scripts/render_system_model.py",
                "scripts/render_telemetry_hook_recipes.py",
                "scripts/render_world_class_claim_guard.py",
                "scripts/render_world_class_evidence_intake.py",
                "scripts/render_world_class_evidence_ledger.py",
                "scripts/render_world_class_evidence_plan.py",
                "scripts/render_world_class_operator_runbook.py",
                "scripts/render_world_class_submission_review.py",
                "scripts/resource_boundary_check.py",
                "scripts/review_studio_action_evidence.py",
                "scripts/review_studio_actions.py",
                "scripts/review_studio_data.py",
                "scripts/review_studio_formatting.py",
                "scripts/review_studio_gates.py",
                "scripts/review_studio_layout.py",
                "scripts/review_studio_output_review.py",
                "scripts/review_studio_waivers.py",
                "scripts/review_studio_world_class.py",
                "scripts/review_viewer_data.py",
                "scripts/run_conformance_suite.py",
                "scripts/run_description_optimization_suite.py",
                "scripts/run_eval_suite.py",
                "scripts/run_output_eval.py",
                "scripts/run_output_execution.py"
              ],
              "assets": [
                "templates/basic_skill.md.j2",
                "templates/complex_skill.md.j2"
              ],
              "reports": [
                "reports/benchmark_methodology.md",
                "reports/intent-context.json",
                "reports/intent-confidence.json",
                "reports/intent-confidence.md",
                "reports/reference-synthesis.json",
                "reports/reference-synthesis.md",
                "reports/output-risk-profile.json",
                "reports/output-risk-profile.md",
                "reports/artifact-design-profile.json",
                "reports/artifact-design-profile.md",
                "reports/prompt-quality-profile.json",
                "reports/prompt-quality-profile.md",
                "reports/system-model.json",
                "reports/system-model.md",
                "reports/iteration-directions.json",
                "reports/iteration-directions.md",
                "reports/skill-overview.json",
                "reports/skill-overview.html",
                "reports/output_quality_scorecard.json",
                "reports/output_quality_scorecard.md",
                "reports/output_execution_runs.json",
                "reports/output_execution_runs.md",
                "reports/output_blind_review_pack.json",
                "reports/output_blind_review_pack.md",
                "reports/output_blind_answer_key.json",
                "reports/output_review_adjudication.json",
                "reports/output_review_adjudication.md",
                "reports/review_annotations.json",
                "reports/review_annotations.md",
                "reports/conformance_matrix.json",
                "reports/conformance_matrix.md",
                "reports/security_trust_report.json",
                "reports/security_trust_report.md",
                "reports/runtime_permission_probes.json",
                "reports/runtime_permission_probes.md",
                "reports/telemetry_hook_recipes.json",
                "reports/telemetry_hook_recipes.md",
                "reports/skill_atlas.json",
                "reports/skill_atlas.html",
                "reports/skill-os-2-review.md",
                "reports/portability_score.json",
                "reports/portability_score.md",
                "reports/governance_score.json"
              ],
              "counts": {
                "references": 34,
                "scripts": 80,
                "assets": 2,
                "reports": 43
              }
            },
            "eval_plan": {
              "trigger": [
                "evals/README.md",
                "evals/adaptation/user_signals.example.jsonl",
                "evals/adversarial/trigger_cases.json",
                "evals/blind_holdout/trigger_cases.json",
                "evals/confusion/route_cases.json",
                "evals/dev/trigger_cases.json",
                "evals/failure-cases.md",
                "evals/history/2026-03-31-context-first-pack.json",
                "evals/history/2026-03-31-family-suite-expansion.json",
                "evals/history/2026-03-31-governance-quality-gates.json",
                "evals/history/2026-03-31-governed-assets-and-history.json",
                "evals/history/2026-04-01-route-scorecard-foundation.json",
                "evals/history/README.md",
                "evals/history/description_optimization/2026-03-31-description-optimization-suite.json",
                "evals/history/description_optimization/2026-04-01-adversarial-calibration-and-family-drift.json",
                "evals/history/description_optimization/2026-04-01-blind-holdout-and-drift-history.json",
                "evals/history/description_optimization/2026-04-01-judge-backed-blind-eval.json",
                "evals/history/description_optimization/README.md",
                "evals/holdout/trigger_cases.json",
                "evals/output/cases.jsonl",
                "evals/output/fixtures/release-brief-source.md",
                "evals/output/schema.json",
                "evals/packaging_expectations.json",
                "evals/promotion_policy.md",
                "evals/semantic_config.json",
                "evals/train/trigger_cases.json",
                "evals/trigger_cases.json"
              ],
              "output": [
                "evals/output/cases.jsonl",
                "evals/output/fixtures/release-brief-source.md",
                "evals/output/schema.json"
              ],
              "adversarial": [
                "evals/adversarial/trigger_cases.json"
              ],
              "baseline": "without_skill",
              "counts": {
                "trigger": 27,
                "output": 3,
                "adversarial": 1,
                "baseline": 1
              }
            },
            "risk": {
              "output_risk": "high",
              "execution_risk": "medium",
              "trust_boundary": "external"
            },
            "governance": {
              "owner": "Yao Team",
              "maturity": "governed",
              "review_cadence": "quarterly",
              "review_due": ""
            },
            "runtime": {
              "activation": {
                "mode": "manual",
                "paths": []
              },
              "execution": {
                "context": "inline",
                "shell": "bash"
              },
              "trust": {
                "source_tier": "local",
                "remote_inline_execution": "forbid",
                "remote_metadata_policy": "allow-metadata-only"
              },
              "adapter_targets": [
                "openai",
                "claude",
                "generic",
                "vscode"
              ],
              "canonical_format": "agent-skills"
            },
            "permissions": {
              "schema_version": "1.0",
              "source": "reports/security_trust_report.json",
              "source_available": true,
              "declared_capabilities": [
                "network",
                "file_write",
                "subprocess"
              ],
              "review_required": true,
              "capabilities": {
                "network": {
                  "required": true,
                  "script_count": 3,
                  "scripts": [
                    "scripts/check_update.py",
                    "scripts/github_benchmark_scan.py",
                    "scripts/provider_output_eval_runner.py"
                  ],
                  "review_reason": "Outbound hosts must match security/network_policy.json."
                },
                "file_write": {
                  "required": true,
                  "script_count": 67,
                  "scripts": [
                    "scripts/adjudicate_output_review.py",
                    "scripts/build_confusion_matrix.py",
                    "scripts/build_skill_atlas.py",
                    "scripts/check_update.py",
                    "scripts/ci_test.py",
                    "scripts/collect_feedback.py",
                    "scripts/compile_skill.py",
                    "scripts/create_iteration_snapshot.py",
                    "scripts/cross_packager.py",
                    "scripts/emit_telemetry_event.py",
                    "scripts/export_skill_ir.py",
                    "scripts/github_benchmark_scan.py",
                    "scripts/import_telemetry_events.py",
                    "scripts/init_skill.py",
                    "scripts/prepare_output_review_kit.py",
                    "scripts/prepare_world_class_submission_kit.py",
                    "scripts/probe_runtime_permissions.py",
                    "scripts/promotion_checker.py",
                    "scripts/propose_adaptation.py",
                    "scripts/python_compat_check.py",
                    "scripts/registry_audit.py",
                    "scripts/render_adoption_drift_report.py",
                    "scripts/render_architecture_maintainability.py",
                    "scripts/render_artifact_design_profile.py",
                    "scripts/render_baseline_compare.py",
                    "scripts/render_benchmark_reproducibility.py",
                    "scripts/render_context_reports.py",
                    "scripts/render_description_drift_history.py",
                    "scripts/render_eval_dashboard.py",
                    "scripts/render_intent_confidence.py",
                    "scripts/render_intent_dialogue.py",
                    "scripts/render_iteration_directions.py",
                    "scripts/render_iteration_ledger.py",
                    "scripts/render_output_risk_profile.py",
                    "scripts/render_portability_report.py",
                    "scripts/render_prompt_quality_profile.py",
                    "scripts/render_reference_scan.py",
                    "scripts/render_reference_synthesis.py",
                    "scripts/render_regression_history.py",
                    "scripts/render_review_annotations.py",
                    "scripts/render_review_studio.py",
                    "scripts/render_review_viewer.py",
                    "scripts/render_review_waivers.py",
                    "scripts/render_skill_interpretation.py",
                    "scripts/render_skill_os2_audit.py",
                    "scripts/render_skill_os2_coverage.py",
                    "scripts/render_skill_overview.py",
                    "scripts/render_social_preview.py",
                    "scripts/render_system_model.py",
                    "scripts/render_telemetry_hook_recipes.py",
                    "scripts/render_world_class_claim_guard.py",
                    "scripts/render_world_class_evidence_intake.py",
                    "scripts/render_world_class_evidence_ledger.py",
                    "scripts/render_world_class_evidence_plan.py",
                    "scripts/render_world_class_operator_runbook.py",
                    "scripts/render_world_class_submission_review.py",
                    "scripts/run_conformance_suite.py",
                    "scripts/run_description_optimization_suite.py",
                    "scripts/run_output_eval.py",
                    "scripts/run_output_execution.py",
                    "scripts/simulate_install.py",
                    "scripts/summarize_user_signals.py",
                    "scripts/sync_local_install.py",
                    "scripts/telemetry_native_host.py",
                    "scripts/trust_check.py",
                    "scripts/upgrade_check.py",
                    "scripts/verify_package.py"
                  ],
                  "review_reason": "Scripts write local files or generated artifacts."
                },
                "subprocess": {
                  "required": true,
                  "script_count": 9,
                  "scripts": [
                    "scripts/ci_test.py",
                    "scripts/render_benchmark_reproducibility.py",
                    "scripts/render_eval_dashboard.py",
                    "scripts/run_eval_suite.py",
                    "scripts/run_output_execution.py",
                    "scripts/sync_local_install.py",
                    "scripts/trust_check.py",
                    "scripts/yao.py",
                    "scripts/yao_cli_runtime.py"
                  ],
                  "review_reason": "Scripts spawn local commands and need operator review."
                },
                "interactive": {
                  "required": false,
                  "script_count": 0,
                  "scripts": [],
                  "review_reason": ""
                }
              },
              "network_policy": {
                "source": "security/network_policy.json",
                "covered_scripts": [
                  "scripts/check_update.py",
                  "scripts/github_benchmark_scan.py",
                  "scripts/provider_output_eval_runner.py"
                ],
                "missing_scripts": [],
                "mismatches": []
              },
              "help_smoke": {
                "enabled": true,
                "checked_count": 80,
                "failed_count": 0,
                "failed_scripts": []
              },
              "trust_summary": {
                "secret_findings": 0,
                "network_script_count": 3,
                "file_write_script_count": 67,
                "subprocess_script_count": 9,
                "interactive_script_count": 0,
                "help_smoke_failed_count": 0
              }
            },
            "source_files_count": 6,
            "target": "vscode",
            "target_permission_contract": {
              "schema_version": "1.0",
              "target": "vscode",
              "permission_model": "vscode-workspace-trust-plus-metadata",
              "native_enforcement": false,
              "representation": "targets/vscode/adapter.json::target_permission_contract and targets/vscode/README.md install notes",
              "review_required": true,
              "declared_capabilities": [
                "network",
                "file_write",
                "subprocess"
              ],
              "capability_counts": {
                "network": 3,
                "file_write": 67,
                "subprocess": 9,
                "interactive": 0
              },
              "evidence": "reports/security_trust_report.json",
              "operator_note": "VS Code target relies on project or user skill installation plus VS Code workspace trust; Yao preserves permission metadata for reviewer and installer checks."
            },
            "target_native_contract": {
              "schema_version": "1.0",
              "target": "vscode",
              "native_surface": "VS Code/Copilot Agent Skills project or user scope",
              "activation": {
                "policy": "Use folder name plus SKILL.md name/description; keep description under platform limits.",
                "trigger_description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
                "manual_activation_supported": true,
                "automatic_activation_note": "Depends on the target client route/catalog implementation."
              },
              "resources": {
                "strategy": "Install as project or user scoped skill source, preserving relative references and scripts.",
                "counts": {
                  "references": 34,
                  "scripts": 80,
                  "assets": 2,
                  "reports": 43
                },
                "generated_files": [
                  "targets/vscode/adapter.json",
                  "targets/vscode/README.md"
                ]
              },
              "scripts": {
                "strategy": "Scripts require workspace trust and operator/client approval outside this compiler.",
                "script_count": 80,
                "help_smoke_failed_count": 0
              },
              "permissions": {
                "enforcement": "client-or-workspace-trust",
                "native_enforcement": false,
                "declared_capabilities": [
                  "network",
                  "file_write",
                  "subprocess"
                ],
                "review_required": true
              },
              "review": {
                "artifacts": [
                  "SKILL.md",
                  "agents/interface.yaml",
                  "reports/review-studio.html"
                ],
                "fallback_behavior": "If VS Code scope is not installed, use the neutral Agent Skills source.",
                "unsupported_native_features": [
                  "automatic VS Code installation",
                  "VS Code installation scope is documented but not installed by this compiler"
                ]
              },
              "install_scope": "VS Code user or project skills directory"
            },
            "degradation_strategy": "agent-skills-source-with-vscode-notes",
            "target_runtime": {
              "adapter_mode": "vscode-agent-skills-adapter",
              "generated_files": [
                "targets/vscode/adapter.json",
                "targets/vscode/README.md"
              ],
              "metadata_mapping": {
                "name": "folder-name-and-SKILL.md::frontmatter.name",
                "description": "SKILL.md::frontmatter.description",
                "interface": "agents/interface.yaml",
                "permissions": "targets/vscode/adapter.json::target_permission_contract",
                "install_scope": "targets/vscode/README.md"
              },
              "preserved_semantics": [
                "trigger",
                "workflow",
                "resources",
                "eval-plan",
                "risk",
                "governance",
                "runtime",
                "trust",
                "permissions"
              ],
              "native_surface": "VS Code/Copilot Agent Skills project or user scope"
            }
          },
          "permission_contract": {
            "schema_version": "1.0",
            "source": "reports/security_trust_report.json",
            "source_available": true,
            "declared_capabilities": [
              "network",
              "file_write",
              "subprocess"
            ],
            "review_required": true,
            "capabilities": {
              "network": {
                "required": true,
                "script_count": 3,
                "scripts": [
                  "scripts/check_update.py",
                  "scripts/github_benchmark_scan.py",
                  "scripts/provider_output_eval_runner.py"
                ],
                "review_reason": "Outbound hosts must match security/network_policy.json."
              },
              "file_write": {
                "required": true,
                "script_count": 67,
                "scripts": [
                  "scripts/adjudicate_output_review.py",
                  "scripts/build_confusion_matrix.py",
                  "scripts/build_skill_atlas.py",
                  "scripts/check_update.py",
                  "scripts/ci_test.py",
                  "scripts/collect_feedback.py",
                  "scripts/compile_skill.py",
                  "scripts/create_iteration_snapshot.py",
                  "scripts/cross_packager.py",
                  "scripts/emit_telemetry_event.py",
                  "scripts/export_skill_ir.py",
                  "scripts/github_benchmark_scan.py",
                  "scripts/import_telemetry_events.py",
                  "scripts/init_skill.py",
                  "scripts/prepare_output_review_kit.py",
                  "scripts/prepare_world_class_submission_kit.py",
                  "scripts/probe_runtime_permissions.py",
                  "scripts/promotion_checker.py",
                  "scripts/propose_adaptation.py",
                  "scripts/python_compat_check.py",
                  "scripts/registry_audit.py",
                  "scripts/render_adoption_drift_report.py",
                  "scripts/render_architecture_maintainability.py",
                  "scripts/render_artifact_design_profile.py",
                  "scripts/render_baseline_compare.py",
                  "scripts/render_benchmark_reproducibility.py",
                  "scripts/render_context_reports.py",
                  "scripts/render_description_drift_history.py",
                  "scripts/render_eval_dashboard.py",
                  "scripts/render_intent_confidence.py",
                  "scripts/render_intent_dialogue.py",
                  "scripts/render_iteration_directions.py",
                  "scripts/render_iteration_ledger.py",
                  "scripts/render_output_risk_profile.py",
                  "scripts/render_portability_report.py",
                  "scripts/render_prompt_quality_profile.py",
                  "scripts/render_reference_scan.py",
                  "scripts/render_reference_synthesis.py",
                  "scripts/render_regression_history.py",
                  "scripts/render_review_annotations.py",
                  "scripts/render_review_studio.py",
                  "scripts/render_review_viewer.py",
                  "scripts/render_review_waivers.py",
                  "scripts/render_skill_interpretation.py",
                  "scripts/render_skill_os2_audit.py",
                  "scripts/render_skill_os2_coverage.py",
                  "scripts/render_skill_overview.py",
                  "scripts/render_social_preview.py",
                  "scripts/render_system_model.py",
                  "scripts/render_telemetry_hook_recipes.py",
                  "scripts/render_world_class_claim_guard.py",
                  "scripts/render_world_class_evidence_intake.py",
                  "scripts/render_world_class_evidence_ledger.py",
                  "scripts/render_world_class_evidence_plan.py",
                  "scripts/render_world_class_operator_runbook.py",
                  "scripts/render_world_class_submission_review.py",
                  "scripts/run_conformance_suite.py",
                  "scripts/run_description_optimization_suite.py",
                  "scripts/run_output_eval.py",
                  "scripts/run_output_execution.py",
                  "scripts/simulate_install.py",
                  "scripts/summarize_user_signals.py",
                  "scripts/sync_local_install.py",
                  "scripts/telemetry_native_host.py",
                  "scripts/trust_check.py",
                  "scripts/upgrade_check.py",
                  "scripts/verify_package.py"
                ],
                "review_reason": "Scripts write local files or generated artifacts."
              },
              "subprocess": {
                "required": true,
                "script_count": 9,
                "scripts": [
                  "scripts/ci_test.py",
                  "scripts/render_benchmark_reproducibility.py",
                  "scripts/render_eval_dashboard.py",
                  "scripts/run_eval_suite.py",
                  "scripts/run_output_execution.py",
                  "scripts/sync_local_install.py",
                  "scripts/trust_check.py",
                  "scripts/yao.py",
                  "scripts/yao_cli_runtime.py"
                ],
                "review_reason": "Scripts spawn local commands and need operator review."
              },
              "interactive": {
                "required": false,
                "script_count": 0,
                "scripts": [],
                "review_reason": ""
              }
            },
            "network_policy": {
              "source": "security/network_policy.json",
              "covered_scripts": [
                "scripts/check_update.py",
                "scripts/github_benchmark_scan.py",
                "scripts/provider_output_eval_runner.py"
              ],
              "missing_scripts": [],
              "mismatches": []
            },
            "help_smoke": {
              "enabled": true,
              "checked_count": 80,
              "failed_count": 0,
              "failed_scripts": []
            },
            "trust_summary": {
              "secret_findings": 0,
              "network_script_count": 3,
              "file_write_script_count": 67,
              "subprocess_script_count": 9,
              "interactive_script_count": 0,
              "help_smoke_failed_count": 0
            }
          },
          "target_permission_contract": {
            "schema_version": "1.0",
            "target": "vscode",
            "permission_model": "vscode-workspace-trust-plus-metadata",
            "native_enforcement": false,
            "representation": "targets/vscode/adapter.json::target_permission_contract and targets/vscode/README.md install notes",
            "review_required": true,
            "declared_capabilities": [
              "network",
              "file_write",
              "subprocess"
            ],
            "capability_counts": {
              "network": 3,
              "file_write": 67,
              "subprocess": 9,
              "interactive": 0
            },
            "evidence": "reports/security_trust_report.json",
            "operator_note": "VS Code target relies on project or user skill installation plus VS Code workspace trust; Yao preserves permission metadata for reviewer and installer checks."
          },
          "target_native_contract": {
            "schema_version": "1.0",
            "target": "vscode",
            "native_surface": "VS Code/Copilot Agent Skills project or user scope",
            "activation": {
              "policy": "Use folder name plus SKILL.md name/description; keep description under platform limits.",
              "trigger_description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
              "manual_activation_supported": true,
              "automatic_activation_note": "Depends on the target client route/catalog implementation."
            },
            "resources": {
              "strategy": "Install as project or user scoped skill source, preserving relative references and scripts.",
              "counts": {
                "references": 34,
                "scripts": 80,
                "assets": 2,
                "reports": 43
              },
              "generated_files": [
                "targets/vscode/adapter.json",
                "targets/vscode/README.md"
              ]
            },
            "scripts": {
              "strategy": "Scripts require workspace trust and operator/client approval outside this compiler.",
              "script_count": 80,
              "help_smoke_failed_count": 0
            },
            "permissions": {
              "enforcement": "client-or-workspace-trust",
              "native_enforcement": false,
              "declared_capabilities": [
                "network",
                "file_write",
                "subprocess"
              ],
              "review_required": true
            },
            "review": {
              "artifacts": [
                "SKILL.md",
                "agents/interface.yaml",
                "reports/review-studio.html"
              ],
              "fallback_behavior": "If VS Code scope is not installed, use the neutral Agent Skills source.",
              "unsupported_native_features": [
                "automatic VS Code installation",
                "VS Code installation scope is documented but not installed by this compiler"
              ]
            },
            "install_scope": "VS Code user or project skills directory"
          },
          "target_transform": {
            "target": "vscode",
            "adapter_mode": "vscode-agent-skills-adapter",
            "generated_files": [
              "targets/vscode/adapter.json",
              "targets/vscode/README.md"
            ],
            "metadata_mapping": {
              "name": "folder-name-and-SKILL.md::frontmatter.name",
              "description": "SKILL.md::frontmatter.description",
              "interface": "agents/interface.yaml",
              "permissions": "targets/vscode/adapter.json::target_permission_contract",
              "install_scope": "targets/vscode/README.md"
            },
            "preserved_semantics": [
              "trigger",
              "workflow",
              "resources",
              "eval-plan",
              "risk",
              "governance",
              "runtime",
              "trust",
              "permissions"
            ],
            "degradation_strategy": "agent-skills-source-with-vscode-notes",
            "permission_representation": "targets/vscode/adapter.json::target_permission_contract and targets/vscode/README.md install notes",
            "native_surface": "VS Code/Copilot Agent Skills project or user scope",
            "activation_policy": "Use folder name plus SKILL.md name/description; keep description under platform limits.",
            "resource_strategy": "Install as project or user scoped skill source, preserving relative references and scripts.",
            "script_strategy": "Scripts require workspace trust and operator/client approval outside this compiler.",
            "permission_enforcement": "client-or-workspace-trust"
          },
          "unsupported_features": [
            "VS Code installation scope is documented but not installed by this compiler"
          ],
          "warnings": [],
          "failures": []
        }
      ],
      "failures": [],
      "warnings": [],
      "artifacts": {
        "json": "reports/compiled_targets.json",
        "markdown": "reports/compiled_targets.md"
      }
    },
    "conformance": {
      "ok": true,
      "skill": "yao-meta-skill",
      "targets": [
        {
          "target": "openai",
          "status": "pass",
          "checks": [
            "SKILL.md exists",
            "frontmatter name exists",
            "frontmatter description exists",
            "description length <= 1024",
            "name is runtime-safe",
            "manifest.name exists",
            "manifest.version exists",
            "manifest.owner exists",
            "manifest.status exists",
            "manifest.maturity_tier exists",
            "manifest.review_cadence exists",
            "manifest declares openai",
            "interface.display_name exists",
            "interface.short_description exists",
            "interface.default_prompt exists",
            "adapter target declares openai",
            "activation mode exists",
            "execution context exists",
            "execution shell exists",
            "trust source tier exists",
            "openai degradation note exists",
            "Skill IR schema_version is 2.0.0",
            "Skill IR name matches frontmatter",
            "Skill IR description matches frontmatter",
            "references resource resolves: references/artifact-design-doctrine.md",
            "references resource resolves: references/authoring-discipline.md",
            "references resource resolves: references/distribution-registry-method.md",
            "references resource resolves: references/eval-playbook.md",
            "references resource resolves: references/gate-selection.md",
            "references resource resolves: references/governance.md",
            "references resource resolves: references/human-review-template.md",
            "references resource resolves: references/intent-dialogue.md",
            "references resource resolves: references/iteration-philosophy.md",
            "references resource resolves: references/non-skill-decision-tree.md",
            "references resource resolves: references/operating-modes.md",
            "references resource resolves: references/output-eval-method.md"
          ],
          "failures": [],
          "warnings": []
        },
        {
          "target": "claude",
          "status": "pass",
          "checks": [
            "SKILL.md exists",
            "frontmatter name exists",
            "frontmatter description exists",
            "description length <= 1024",
            "name is runtime-safe",
            "manifest.name exists",
            "manifest.version exists",
            "manifest.owner exists",
            "manifest.status exists",
            "manifest.maturity_tier exists",
            "manifest.review_cadence exists",
            "manifest declares claude",
            "interface.display_name exists",
            "interface.short_description exists",
            "interface.default_prompt exists",
            "adapter target declares claude",
            "activation mode exists",
            "execution context exists",
            "execution shell exists",
            "trust source tier exists",
            "claude degradation note exists",
            "Skill IR schema_version is 2.0.0",
            "Skill IR name matches frontmatter",
            "Skill IR description matches frontmatter",
            "references resource resolves: references/artifact-design-doctrine.md",
            "references resource resolves: references/authoring-discipline.md",
            "references resource resolves: references/distribution-registry-method.md",
            "references resource resolves: references/eval-playbook.md",
            "references resource resolves: references/gate-selection.md",
            "references resource resolves: references/governance.md",
            "references resource resolves: references/human-review-template.md",
            "references resource resolves: references/intent-dialogue.md",
            "references resource resolves: references/iteration-philosophy.md",
            "references resource resolves: references/non-skill-decision-tree.md",
            "references resource resolves: references/operating-modes.md",
            "references resource resolves: references/output-eval-method.md"
          ],
          "failures": [],
          "warnings": []
        },
        {
          "target": "agent-skills",
          "status": "pass",
          "checks": [
            "SKILL.md exists",
            "frontmatter name exists",
            "frontmatter description exists",
            "description length <= 1024",
            "name is runtime-safe",
            "directory name matches skill name",
            "manifest.name exists",
            "manifest.version exists",
            "manifest.owner exists",
            "manifest.status exists",
            "manifest.maturity_tier exists",
            "manifest.review_cadence exists",
            "manifest declares agent-skills via agent-skills-compatible",
            "interface.display_name exists",
            "interface.short_description exists",
            "interface.default_prompt exists",
            "canonical format is agent-skills",
            "activation mode exists",
            "execution context exists",
            "execution shell exists",
            "trust source tier exists",
            "Skill IR schema_version is 2.0.0",
            "Skill IR name matches frontmatter",
            "Skill IR description matches frontmatter",
            "references resource resolves: references/artifact-design-doctrine.md",
            "references resource resolves: references/authoring-discipline.md",
            "references resource resolves: references/distribution-registry-method.md",
            "references resource resolves: references/eval-playbook.md",
            "references resource resolves: references/gate-selection.md",
            "references resource resolves: references/governance.md",
            "references resource resolves: references/human-review-template.md",
            "references resource resolves: references/intent-dialogue.md",
            "references resource resolves: references/iteration-philosophy.md",
            "references resource resolves: references/non-skill-decision-tree.md",
            "references resource resolves: references/operating-modes.md",
            "references resource resolves: references/output-eval-method.md"
          ],
          "failures": [],
          "warnings": [
            "agent-skills uses canonical Agent Skills metadata; provider-native execution transforms are not implemented in v0."
          ]
        },
        {
          "target": "vscode",
          "status": "pass",
          "checks": [
            "SKILL.md exists",
            "frontmatter name exists",
            "frontmatter description exists",
            "description length <= 1024",
            "name is runtime-safe",
            "directory name matches skill name",
            "manifest.name exists",
            "manifest.version exists",
            "manifest.owner exists",
            "manifest.status exists",
            "manifest.maturity_tier exists",
            "manifest.review_cadence exists",
            "manifest declares vscode",
            "interface.display_name exists",
            "interface.short_description exists",
            "interface.default_prompt exists",
            "canonical format is agent-skills",
            "activation mode exists",
            "execution context exists",
            "execution shell exists",
            "trust source tier exists",
            "Skill IR schema_version is 2.0.0",
            "Skill IR name matches frontmatter",
            "Skill IR description matches frontmatter",
            "references resource resolves: references/artifact-design-doctrine.md",
            "references resource resolves: references/authoring-discipline.md",
            "references resource resolves: references/distribution-registry-method.md",
            "references resource resolves: references/eval-playbook.md",
            "references resource resolves: references/gate-selection.md",
            "references resource resolves: references/governance.md",
            "references resource resolves: references/human-review-template.md",
            "references resource resolves: references/intent-dialogue.md",
            "references resource resolves: references/iteration-philosophy.md",
            "references resource resolves: references/non-skill-decision-tree.md",
            "references resource resolves: references/operating-modes.md",
            "references resource resolves: references/output-eval-method.md"
          ],
          "failures": [],
          "warnings": [
            "vscode uses canonical Agent Skills metadata; provider-native execution transforms are not implemented in v0."
          ]
        },
        {
          "target": "generic",
          "status": "pass",
          "checks": [
            "SKILL.md exists",
            "frontmatter name exists",
            "frontmatter description exists",
            "description length <= 1024",
            "name is runtime-safe",
            "manifest.name exists",
            "manifest.version exists",
            "manifest.owner exists",
            "manifest.status exists",
            "manifest.maturity_tier exists",
            "manifest.review_cadence exists",
            "manifest declares generic",
            "interface.display_name exists",
            "interface.short_description exists",
            "interface.default_prompt exists",
            "adapter target declares generic",
            "activation mode exists",
            "execution context exists",
            "execution shell exists",
            "trust source tier exists",
            "generic degradation note exists",
            "Skill IR schema_version is 2.0.0",
            "Skill IR name matches frontmatter",
            "Skill IR description matches frontmatter",
            "references resource resolves: references/artifact-design-doctrine.md",
            "references resource resolves: references/authoring-discipline.md",
            "references resource resolves: references/distribution-registry-method.md",
            "references resource resolves: references/eval-playbook.md",
            "references resource resolves: references/gate-selection.md",
            "references resource resolves: references/governance.md",
            "references resource resolves: references/human-review-template.md",
            "references resource resolves: references/intent-dialogue.md",
            "references resource resolves: references/iteration-philosophy.md",
            "references resource resolves: references/non-skill-decision-tree.md",
            "references resource resolves: references/operating-modes.md",
            "references resource resolves: references/output-eval-method.md"
          ],
          "failures": [],
          "warnings": []
        }
      ],
      "summary": {
        "target_count": 5,
        "pass_count": 5,
        "fail_count": 0
      },
      "artifacts": {
        "json": "reports/conformance_matrix.json",
        "markdown": "reports/conformance_matrix.md"
      }
    },
    "runtime_permissions": {
      "schema_version": "1.0",
      "ok": true,
      "skill_dir": ".",
      "package_dir": "tests/tmp_review_studio/dist",
      "expected_capabilities": [
        "file_write",
        "network",
        "subprocess"
      ],
      "summary": {
        "target_count": 4,
        "pass_count": 4,
        "fail_count": 0,
        "native_enforcement_count": 0,
        "metadata_fallback_count": 4,
        "residual_risk_count": 4,
        "required_capability_count": 3,
        "failure_count": 0,
        "installer_enforcement_source_status": "present",
        "installer_enforcement_target_count": 4,
        "installer_enforcement_pass_count": 4,
        "installer_permission_enforced_count": 12,
        "installer_permission_failure_count": 0,
        "installer_permission_capability_count": 3,
        "world_class_native_evidence_ready": false,
        "installer_enforcement_ready": true
      },
      "installer_enforcement": {
        "source": "reports/install_simulation.json",
        "source_status": "present",
        "package_dir_matches": true,
        "summary": {
          "installer_permission_enforced_count": 12,
          "installer_permission_failure_count": 0,
          "permission_target_count": 4,
          "permission_capability_count": 3,
          "failure_count": 0
        }
      },
      "targets": [
        {
          "target": "openai",
          "status": "pass",
          "adapter": "tests/tmp_review_studio/dist/targets/openai/adapter.json",
          "permission_model": "metadata-only",
          "native_enforcement": false,
          "metadata_fallback_explicit": true,
          "installer_enforcement": {
            "target": "openai",
            "source_status": "present",
            "enforced": true,
            "enforced_capabilities": [
              "file_write",
              "network",
              "subprocess"
            ],
            "missing_capabilities": [],
            "failure_details": []
          },
          "assurance": "metadata-fallback-explicit",
          "declared_capabilities": [
            "file_write",
            "network",
            "subprocess"
          ],
          "checks": [
            {
              "key": "adapter-present",
              "passed": true,
              "detail": "openai adapter.json is readable"
            },
            {
              "key": "permission-contract-present",
              "passed": true,
              "detail": "openai adapter includes permission_contract"
            },
            {
              "key": "target-contract-present",
              "passed": true,
              "detail": "openai adapter includes target_permission_contract"
            },
            {
              "key": "source-available",
              "passed": true,
              "detail": "openai permission_contract links to an available trust report"
            },
            {
              "key": "declared-capabilities-match",
              "passed": true,
              "detail": "openai target_permission_contract mirrors expected capabilities"
            },
            {
              "key": "capability-counts-present",
              "passed": true,
              "detail": "openai target_permission_contract includes capability_counts"
            },
            {
              "key": "native-enforcement-boolean",
              "passed": true,
              "detail": "openai target_permission_contract declares native_enforcement as a boolean"
            },
            {
              "key": "representation-present",
              "passed": true,
              "detail": "openai target_permission_contract declares where permission metadata is represented"
            },
            {
              "key": "operator-note-present",
              "passed": true,
              "detail": "openai target_permission_contract includes an operator_note"
            },
            {
              "key": "review-required-matches",
              "passed": true,
              "detail": "openai review_required matches whether capabilities are required"
            },
            {
              "key": "openai-yaml-present",
              "passed": true,
              "detail": "OpenAI permission metadata YAML is readable"
            },
            {
              "key": "openai-yaml-permissions",
              "passed": true,
              "detail": "OpenAI YAML permission contract mirrors expected capabilities"
            },
            {
              "key": "openai-yaml-native-flag",
              "passed": true,
              "detail": "OpenAI YAML declares native_enforcement as a boolean"
            }
          ],
          "failures": [],
          "residual_risks": [
            "Client-native permission enforcement is not provided by this target; installer or operator must honor metadata."
          ]
        },
        {
          "target": "claude",
          "status": "pass",
          "adapter": "tests/tmp_review_studio/dist/targets/claude/adapter.json",
          "permission_model": "neutral-source-plus-adapter",
          "native_enforcement": false,
          "metadata_fallback_explicit": true,
          "installer_enforcement": {
            "target": "claude",
            "source_status": "present",
            "enforced": true,
            "enforced_capabilities": [
              "file_write",
              "network",
              "subprocess"
            ],
            "missing_capabilities": [],
            "failure_details": []
          },
          "assurance": "metadata-fallback-explicit",
          "declared_capabilities": [
            "file_write",
            "network",
            "subprocess"
          ],
          "checks": [
            {
              "key": "adapter-present",
              "passed": true,
              "detail": "claude adapter.json is readable"
            },
            {
              "key": "permission-contract-present",
              "passed": true,
              "detail": "claude adapter includes permission_contract"
            },
            {
              "key": "target-contract-present",
              "passed": true,
              "detail": "claude adapter includes target_permission_contract"
            },
            {
              "key": "source-available",
              "passed": true,
              "detail": "claude permission_contract links to an available trust report"
            },
            {
              "key": "declared-capabilities-match",
              "passed": true,
              "detail": "claude target_permission_contract mirrors expected capabilities"
            },
            {
              "key": "capability-counts-present",
              "passed": true,
              "detail": "claude target_permission_contract includes capability_counts"
            },
            {
              "key": "native-enforcement-boolean",
              "passed": true,
              "detail": "claude target_permission_contract declares native_enforcement as a boolean"
            },
            {
              "key": "representation-present",
              "passed": true,
              "detail": "claude target_permission_contract declares where permission metadata is represented"
            },
            {
              "key": "operator-note-present",
              "passed": true,
              "detail": "claude target_permission_contract includes an operator_note"
            },
            {
              "key": "review-required-matches",
              "passed": true,
              "detail": "claude review_required matches whether capabilities are required"
            }
          ],
          "failures": [],
          "residual_risks": [
            "Client-native permission enforcement is not provided by this target; installer or operator must honor metadata."
          ]
        },
        {
          "target": "generic",
          "status": "pass",
          "adapter": "tests/tmp_review_studio/dist/targets/generic/adapter.json",
          "permission_model": "agent-skills-compatible-metadata",
          "native_enforcement": false,
          "metadata_fallback_explicit": true,
          "installer_enforcement": {
            "target": "generic",
            "source_status": "present",
            "enforced": true,
            "enforced_capabilities": [
              "file_write",
              "network",
              "subprocess"
            ],
            "missing_capabilities": [],
            "failure_details": []
          },
          "assurance": "metadata-fallback-explicit",
          "declared_capabilities": [
            "file_write",
            "network",
            "subprocess"
          ],
          "checks": [
            {
              "key": "adapter-present",
              "passed": true,
              "detail": "generic adapter.json is readable"
            },
            {
              "key": "permission-contract-present",
              "passed": true,
              "detail": "generic adapter includes permission_contract"
            },
            {
              "key": "target-contract-present",
              "passed": true,
              "detail": "generic adapter includes target_permission_contract"
            },
            {
              "key": "source-available",
              "passed": true,
              "detail": "generic permission_contract links to an available trust report"
            },
            {
              "key": "declared-capabilities-match",
              "passed": true,
              "detail": "generic target_permission_contract mirrors expected capabilities"
            },
            {
              "key": "capability-counts-present",
              "passed": true,
              "detail": "generic target_permission_contract includes capability_counts"
            },
            {
              "key": "native-enforcement-boolean",
              "passed": true,
              "detail": "generic target_permission_contract declares native_enforcement as a boolean"
            },
            {
              "key": "representation-present",
              "passed": true,
              "detail": "generic target_permission_contract declares where permission metadata is represented"
            },
            {
              "key": "operator-note-present",
              "passed": true,
              "detail": "generic target_permission_contract includes an operator_note"
            },
            {
              "key": "review-required-matches",
              "passed": true,
              "detail": "generic review_required matches whether capabilities are required"
            }
          ],
          "failures": [],
          "residual_risks": [
            "Client-native permission enforcement is not provided by this target; installer or operator must honor metadata."
          ]
        },
        {
          "target": "vscode",
          "status": "pass",
          "adapter": "tests/tmp_review_studio/dist/targets/vscode/adapter.json",
          "permission_model": "vscode-workspace-trust-plus-metadata",
          "native_enforcement": false,
          "metadata_fallback_explicit": true,
          "installer_enforcement": {
            "target": "vscode",
            "source_status": "present",
            "enforced": true,
            "enforced_capabilities": [
              "file_write",
              "network",
              "subprocess"
            ],
            "missing_capabilities": [],
            "failure_details": []
          },
          "assurance": "metadata-fallback-explicit",
          "declared_capabilities": [
            "file_write",
            "network",
            "subprocess"
          ],
          "checks": [
            {
              "key": "adapter-present",
              "passed": true,
              "detail": "vscode adapter.json is readable"
            },
            {
              "key": "permission-contract-present",
              "passed": true,
              "detail": "vscode adapter includes permission_contract"
            },
            {
              "key": "target-contract-present",
              "passed": true,
              "detail": "vscode adapter includes target_permission_contract"
            },
            {
              "key": "source-available",
              "passed": true,
              "detail": "vscode permission_contract links to an available trust report"
            },
            {
              "key": "declared-capabilities-match",
              "passed": true,
              "detail": "vscode target_permission_contract mirrors expected capabilities"
            },
            {
              "key": "capability-counts-present",
              "passed": true,
              "detail": "vscode target_permission_contract includes capability_counts"
            },
            {
              "key": "native-enforcement-boolean",
              "passed": true,
              "detail": "vscode target_permission_contract declares native_enforcement as a boolean"
            },
            {
              "key": "representation-present",
              "passed": true,
              "detail": "vscode target_permission_contract declares where permission metadata is represented"
            },
            {
              "key": "operator-note-present",
              "passed": true,
              "detail": "vscode target_permission_contract includes an operator_note"
            },
            {
              "key": "review-required-matches",
              "passed": true,
              "detail": "vscode review_required matches whether capabilities are required"
            }
          ],
          "failures": [],
          "residual_risks": [
            "Client-native permission enforcement is not provided by this target; installer or operator must honor metadata."
          ]
        }
      ],
      "failures": [],
      "artifacts": {
        "json": "reports/runtime_permission_probes.json",
        "markdown": "reports/runtime_permission_probes.md"
      }
    },
    "trust": {
      "ok": true,
      "skill_dir": ".",
      "summary": {
        "scanned_files": 193,
        "script_count": 106,
        "internal_module_count": 26,
        "secret_findings": 0,
        "dependency_files": [
          "requirements-ci.txt"
        ],
        "network_script_count": 3,
        "network_policy_covered_count": 3,
        "network_policy_missing_count": 0,
        "file_write_script_count": 67,
        "permission_required_count": 3,
        "permission_approved_count": 3,
        "permission_missing_count": 0,
        "permission_invalid_count": 0,
        "permission_expired_count": 0,
        "help_smoke_checked_count": 80,
        "help_smoke_failed_count": 0,
        "interactive_script_count": 0,
        "package_hash_scope": "source-contract-without-generated-reports",
        "package_hash_file_count": 193,
        "package_sha256": "28625ce8b3fcb3e214ef3b8ffc748d9cff551e4c5a1b78786c1a2b7d7005f679"
      },
      "failures": [],
      "warnings": [],
      "secrets": [],
      "scripts": [
        {
          "path": "scripts/adjudicate_output_review.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/build_confusion_matrix.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/build_skill_atlas.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/check_update.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": true,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [
            "https://raw.githubusercontent.com/yaojingang/yao-meta-skill/main/VERSION",
            "https://raw.githubusercontent.com/yaojingang/yao-meta-skill/main/manifest.json"
          ],
          "network_hosts": [
            "raw.githubusercontent.com"
          ]
        },
        {
          "path": "scripts/ci_test.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": true,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/collect_feedback.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/compile_skill.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/context_sizer.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/create_iteration_snapshot.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/cross_packager.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/diff_eval.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/emit_telemetry_event.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/export_skill_ir.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/github_benchmark_scan.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": true,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [
            "https://api.github.com"
          ],
          "network_hosts": [
            "api.github.com"
          ]
        },
        {
          "path": "scripts/governance_check.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/html_rendering.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Used by report renderers to escape HTML while preserving meaningful falsey values.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/import_telemetry_events.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/init_skill.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/judge_blind_eval.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/lint_skill.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/local_output_eval_runner.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/optimize_description.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/prepare_output_review_kit.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/prepare_world_class_submission_kit.py",
          "interface": "cli",
          "interface_declared": true,
          "interface_reason": "Prepares editable world-class evidence intake packets without counting drafts as accepted evidence.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/probe_runtime_permissions.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/promotion_checker.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/propose_adaptation.py",
          "interface": "cli",
          "interface_declared": true,
          "interface_reason": "Turns redacted repeated preference patterns into proposal-only adaptation plans.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/provider_output_eval_runner.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": true,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [
            "https://api.openai.com/v1/responses"
          ],
          "network_hosts": [
            "api.openai.com"
          ]
        },
        {
          "path": "scripts/python_compat_check.py",
          "interface": "cli",
          "interface_declared": true,
          "interface_reason": "Checks repository Python source for syntax that can pass locally but fail on the supported CI interpreter.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/registry_audit.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_adoption_drift_report.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_architecture_maintainability.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_artifact_design_profile.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_baseline_compare.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_benchmark_reproducibility.py",
          "interface": "cli",
          "interface_declared": true,
          "interface_reason": "Renders a release-facing benchmark reproducibility manifest and Markdown report.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": true,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_context_reports.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_description_drift_history.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_eval_dashboard.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": true,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_intent_confidence.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_intent_dialogue.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_iteration_directions.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_iteration_ledger.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_output_risk_profile.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_portability_report.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_prompt_quality_profile.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_reference_scan.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_reference_synthesis.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_regression_history.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_review_annotations.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_review_studio.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_review_viewer.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_review_waivers.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_skill_interpretation.py",
          "interface": "cli",
          "interface_declared": true,
          "interface_reason": "Renders the first-class skill interpretation report while reusing the Skill Overview v2 model and layout.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_skill_os2_audit.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_skill_os2_coverage.py",
          "interface": "cli",
          "interface_declared": true,
          "interface_reason": "Renders a Skill OS 2.0 blueprint-to-evidence coverage audit.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_skill_overview.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_social_preview.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [
            "http://www.w3.org/2000/svg"
          ],
          "network_hosts": [
            "www.w3.org"
          ]
        },
        {
          "path": "scripts/render_system_model.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_telemetry_hook_recipes.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_world_class_claim_guard.py",
          "interface": "cli",
          "interface_declared": true,
          "interface_reason": "Scans public claim surfaces so world-class completion is not claimed before accepted evidence exists.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_world_class_evidence_intake.py",
          "interface": "cli",
          "interface_declared": true,
          "interface_reason": "Validates world-class human and external evidence intake packets before ledger review.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_world_class_evidence_ledger.py",
          "interface": "cli",
          "interface_declared": true,
          "interface_reason": "Renders a machine-checkable ledger for world-class external and human evidence gaps.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_world_class_evidence_plan.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_world_class_operator_runbook.py",
          "interface": "cli",
          "interface_declared": true,
          "interface_reason": "Renders an operator runbook for collecting pending world-class evidence without accepting evidence.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/render_world_class_submission_review.py",
          "interface": "cli",
          "interface_declared": true,
          "interface_reason": "Renders a read-only review queue for world-class evidence submissions before ledger acceptance.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/resource_boundary_check.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/review_studio_action_evidence.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by review_studio_actions.py to keep world-class evidence action cards out of generic Review Studio action wiring.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/review_studio_actions.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by render_review_studio.py to keep Review Studio action guidance and source refs out of HTML rendering.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/review_studio_data.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by render_review_studio.py to load Review Studio source reports and metric cards.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/review_studio_formatting.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by render_review_studio.py to format report dictionaries as audit UI panels.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/review_studio_gates.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by render_review_studio.py to keep Review Studio gate evaluation separate from HTML rendering.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/review_studio_layout.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by render_review_studio.py to keep Review Studio layout and CSS out of gate logic.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/review_studio_output_review.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by render_review_studio.py to render output review checklist cards.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/review_studio_waivers.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by render_review_studio.py to keep waiver candidate layout out of the main renderer.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/review_studio_world_class.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by render_review_studio.py to render world-class evidence cards.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/review_viewer_data.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by render_review_viewer.py to assemble Review Viewer data before HTML rendering.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/run_conformance_suite.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/run_description_optimization_suite.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/run_eval_suite.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": true,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/run_output_eval.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/run_output_execution.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": true,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/simulate_install.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/skill_report_charts.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by render_skill_overview.py to render inline SVG report charts.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/skill_report_i18n.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by render_skill_overview.py to keep bilingual report copy and fallback rules out of HTML rendering.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/skill_report_layout.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by render_skill_overview.py to keep overview report layout and CSS out of data rendering.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/skill_report_metrics.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by skill_report_model.py to calculate overview report metrics.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/skill_report_model.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by render_skill_overview.py to build the v2 report data model.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/skill_report_world_class.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by skill_report_model.py to summarize world-class evidence readiness and roadmap actions.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/summarize_user_signals.py",
          "interface": "cli",
          "interface_declared": true,
          "interface_reason": "Scans an explicit local source file and summarizes redacted repeated user preference signals.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/sync_local_install.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": true,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/telemetry_native_host.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/trigger_eval.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/trust_check.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": true,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/upgrade_check.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/validate_skill.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/verify_package.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": true,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/world_class_evidence_contract.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by world-class evidence reports to share intake validation and artifact integrity checks.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/world_class_source_checks.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by world-class evidence reports to keep source-evidence readiness checks consistent.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/yao.py",
          "interface": "cli",
          "interface_declared": false,
          "interface_reason": "Default CLI classification; add SCRIPT_INTERFACE for internal modules.",
          "has_argparse": true,
          "has_main_guard": true,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": true,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/yao_cli_adaptation_commands.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by yao.py to keep adaptive scan/proposal command handlers outside the thin CLI orchestrator.",
          "has_argparse": true,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/yao_cli_config.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by yao.py for CLI target maps and side-effect-free shaping helpers.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/yao_cli_create_commands.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by yao.py to keep skill creation and quickstart command handlers out of the CLI orchestrator.",
          "has_argparse": true,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/yao_cli_parser.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by yao.py to keep CLI parser declarations separate from command orchestration.",
          "has_argparse": true,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/yao_cli_report_commands.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by yao.py to keep report and evidence command handlers out of the CLI orchestrator.",
          "has_argparse": true,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/yao_cli_runtime.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by yao.py and command modules for shared subprocess execution and JSON payload parsing.",
          "has_argparse": false,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": true,
          "network_urls": [],
          "network_hosts": []
        },
        {
          "path": "scripts/yao_cli_telemetry.py",
          "interface": "internal-module",
          "interface_declared": true,
          "interface_reason": "Imported by yao.py to record opt-in metadata-only CLI run telemetry.",
          "has_argparse": true,
          "has_main_guard": false,
          "uses_input": false,
          "uses_network": false,
          "uses_file_write": false,
          "uses_subprocess": false,
          "network_urls": [],
          "network_hosts": []
        }
      ],
      "dependencies": {
        "present": [
          "requirements-ci.txt"
        ],
        "pinned": [
          "PyYAML==6.0.3"
        ],
        "unpinned": []
      },
      "network_policy": {
        "present": true,
        "path": "security/network_policy.json",
        "schema_version": "1.0",
        "network_script_count": 3,
        "covered_scripts": [
          "scripts/check_update.py",
          "scripts/github_benchmark_scan.py",
          "scripts/provider_output_eval_runner.py"
        ],
        "missing_scripts": [],
        "mismatches": [],
        "default_policy": {
          "require_https": true,
          "custom_hosts": "deny-by-default",
          "review_rule": "Network-capable scripts must declare allowed_hosts and justify any explicit custom-host override."
        }
      },
      "help_smoke": {
        "enabled": true,
        "timeout_seconds": 5.0,
        "candidate_count": 80,
        "checked_count": 80,
        "passed_count": 80,
        "failed_count": 0,
        "skipped_count": 26,
        "failed_scripts": [],
        "results": [
          {
            "path": "scripts/adjudicate_output_review.py",
            "command": "python3 scripts/adjudicate_output_review.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: adjudicate_output_review.py [-h] [--blind-pack BLIND_PACK]\n                                   [--answer-key ANSWER_KEY]\n                                   [--decisions DECISIONS]\n                                   [--output-json OUTP",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/build_confusion_matrix.py",
            "command": "python3 scripts/build_confusion_matrix.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: build_confusion_matrix.py [-h] [--cases CASES]\n                                 [--output-json OUTPUT_JSON]\n                                 [--output-md OUTPUT_MD]\n                                 [--history-snapshot-output HISTORY_",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/build_skill_atlas.py",
            "command": "python3 scripts/build_skill_atlas.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: build_skill_atlas.py [-h] [--workspace-root WORKSPACE_ROOT]\n                            [--output-dir OUTPUT_DIR]\n                            [--report-html REPORT_HTML]\n                            [--report-json REPORT_JSON]\n       ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/check_update.py",
            "command": "python3 scripts/check_update.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: check_update.py [-h] [--root ROOT] [--cache-path CACHE_PATH]\n                       [--version-url VERSION_URL]\n                       [--manifest-url MANIFEST_URL] [--timeout TIMEOUT]\n                       [--max-age-days MAX_AGE_D",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/ci_test.py",
            "command": "python3 scripts/ci_test.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: ci_test.py [-h] [--tail-lines TAIL_LINES] [targets ...]\n\nRun CI test targets with compact logging.\n\npositional arguments:\n  targets               Optional target override.\n\noptions:\n  -h, --help            show this help message and ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/collect_feedback.py",
            "command": "python3 scripts/collect_feedback.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: collect_feedback.py [-h] [--note NOTE] [--rating RATING]\n                           [--category CATEGORY]\n                           [--recommended-action RECOMMENDED_ACTION]\n                           [--output-json OUTPUT_JSON] [--",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/compile_skill.py",
            "command": "python3 scripts/compile_skill.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: compile_skill.py [-h] [--target TARGET] [--output-json OUTPUT_JSON]\n                        [--output-md OUTPUT_MD] [--generated-at GENERATED_AT]\n                        [skill_dir]\n\nCompile Skill IR into target-specific semantic con",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/context_sizer.py",
            "command": "python3 scripts/context_sizer.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: context_sizer.py [-h] [--json] skill_dir\n\nEstimate context size for a skill package.\n\npositional arguments:\n  skill_dir   Path to the skill directory\n\noptions:\n  -h, --help  show this help message and exit\n  --json      Emit machine-",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/create_iteration_snapshot.py",
            "command": "python3 scripts/create_iteration_snapshot.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: create_iteration_snapshot.py [-h] --target TARGET [--label LABEL]\n                                    [--promotion-decisions PROMOTION_DECISIONS]\n                                    [--route-scorecard ROUTE_SCORECARD]\n               ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/cross_packager.py",
            "command": "python3 scripts/cross_packager.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: cross_packager.py [-h] [--platform PLATFORM] [--output-dir OUTPUT_DIR]\n                         [--expectations EXPECTATIONS] [--zip]\n                         skill_dir\n\nGenerate lightweight cross-platform packaging artifacts.\n\nposit",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/diff_eval.py",
            "command": "python3 scripts/diff_eval.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: diff_eval.py [-h] before after\n\nDiff two eval reports.\n\npositional arguments:\n  before\n  after\n\noptions:\n  -h, --help  show this help message and exit",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/emit_telemetry_event.py",
            "command": "python3 scripts/emit_telemetry_event.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: emit_telemetry_event.py [-h] [--output-jsonl OUTPUT_JSONL]\n                               [--event {review_event,script_run,skill_activation,skill_output}]\n                               [--activation-type {explicit,implicit,manual,u",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/export_skill_ir.py",
            "command": "python3 scripts/export_skill_ir.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: export_skill_ir.py [-h] [--output-json OUTPUT_JSON] [--validate-only]\n                          [skill_dir]\n\nExport a platform-neutral Skill IR document from a skill package.\n\npositional arguments:\n  skill_dir\n\noptions:\n  -h, --help ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/github_benchmark_scan.py",
            "command": "python3 scripts/github_benchmark_scan.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: github_benchmark_scan.py [-h] --query QUERY [--top-n TOP_N]\n                                [--fixture-dir FIXTURE_DIR]\n                                [--output-md OUTPUT_MD]\n                                [--output-json OUTPUT_JSO",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/governance_check.py",
            "command": "python3 scripts/governance_check.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: governance_check.py [-h] [--require-manifest] skill_dir\n\nCheck skill governance metadata and lifecycle readiness.\n\npositional arguments:\n  skill_dir\n\noptions:\n  -h, --help          show this help message and exit\n  --require-manifest",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/import_telemetry_events.py",
            "command": "python3 scripts/import_telemetry_events.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: import_telemetry_events.py [-h] --input-jsonl INPUT_JSONL\n                                  [--events-jsonl EVENTS_JSONL]\n                                  [--output-json OUTPUT_JSON]\n                                  [--output-md OU",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/init_skill.py",
            "command": "python3 scripts/init_skill.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: init_skill.py [-h] [--description DESCRIPTION] [--title TITLE]\n                     [--output-dir OUTPUT_DIR]\n                     [--mode {governed,library,production,scaffold}]\n                     [--archetype {governed,library,pr",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/judge_blind_eval.py",
            "command": "python3 scripts/judge_blind_eval.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: judge_blind_eval.py [-h] [--description DESCRIPTION]\n                           [--description-file DESCRIPTION_FILE] --cases CASES\n                           [--semantic-config SEMANTIC_CONFIG]\n\nRun a rubric-based blind trigger judg",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/lint_skill.py",
            "command": "python3 scripts/lint_skill.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: lint_skill.py [-h] skill_dir\n\nLint a skill package for basic structure issues.\n\npositional arguments:\n  skill_dir\n\noptions:\n  -h, --help  show this help message and exit",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/local_output_eval_runner.py",
            "command": "python3 scripts/local_output_eval_runner.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: local_output_eval_runner.py [-h] [--execution-kind {command,model}]\n                                   [--provider PROVIDER] [--model MODEL]\n\nLocal deterministic output-eval runner. It executes the runner contract\nwithout claiming pr",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/optimize_description.py",
            "command": "python3 scripts/optimize_description.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: optimize_description.py [-h] --description-file DESCRIPTION_FILE\n                               [--baseline-description-file BASELINE_DESCRIPTION_FILE]\n                               --dev-cases DEV_CASES\n                            ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/prepare_output_review_kit.py",
            "command": "python3 scripts/prepare_output_review_kit.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: prepare_output_review_kit.py [-h] [--blind-pack-json BLIND_PACK_JSON]\n                                    [--blind-pack-md BLIND_PACK_MD]\n                                    [--decisions DECISIONS]\n                                   ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/prepare_world_class_submission_kit.py",
            "command": "python3 scripts/prepare_world_class_submission_kit.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: prepare_world_class_submission_kit.py [-h] [--output-dir OUTPUT_DIR]\n                                             [--evidence-key EVIDENCE_KEY]\n                                             [--overwrite]\n                              ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/probe_runtime_permissions.py",
            "command": "python3 scripts/probe_runtime_permissions.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: probe_runtime_permissions.py [-h] [--package-dir PACKAGE_DIR]\n                                    [--target {openai,claude,generic,vscode}]\n                                    [--output-json OUTPUT_JSON]\n                             ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/promotion_checker.py",
            "command": "python3 scripts/promotion_checker.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: promotion_checker.py [-h] [--optimization-suite OPTIMIZATION_SUITE]\n                            [--route-scorecard ROUTE_SCORECARD]\n                            [--output-json OUTPUT_JSON]\n                            [--output-md OUTP",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/propose_adaptation.py",
            "command": "python3 scripts/propose_adaptation.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: propose_adaptation.py [-h] [--patterns-json PATTERNS_JSON]\n                             [--output-json OUTPUT_JSON]\n                             [--output-md OUTPUT_MD]\n                             [--generated-at GENERATED_AT]\n     ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/provider_output_eval_runner.py",
            "command": "python3 scripts/provider_output_eval_runner.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: provider_output_eval_runner.py [-h] [--provider PROVIDER]\n                                      [--base-url BASE_URL] [--model MODEL]\n                                      [--api-key-env API_KEY_ENV]\n                                 ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/python_compat_check.py",
            "command": "python3 scripts/python_compat_check.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: python_compat_check.py [-h] [--path PATH]\n                              [--target-python TARGET_PYTHON]\n                              [--output-json OUTPUT_JSON]\n                              [--output-md OUTPUT_MD]\n                 ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/registry_audit.py",
            "command": "python3 scripts/registry_audit.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: registry_audit.py [-h] [--registry-dir REGISTRY_DIR]\n                         [--output-json OUTPUT_JSON] [--output-md OUTPUT_MD]\n                         [--generated-at GENERATED_AT]\n                         [skill_dir]\n\nBuild and ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_adoption_drift_report.py",
            "command": "python3 scripts/render_adoption_drift_report.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_adoption_drift_report.py [-h] [--events-jsonl EVENTS_JSONL]\n                                       [--output-json OUTPUT_JSON]\n                                       [--output-md OUTPUT_MD]\n                                    ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_architecture_maintainability.py",
            "command": "python3 scripts/render_architecture_maintainability.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_architecture_maintainability.py [-h] [--output-json OUTPUT_JSON]\n                                              [--output-md OUTPUT_MD]\n                                              [--warn-lines WARN_LINES]\n                   ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_artifact_design_profile.py",
            "command": "python3 scripts/render_artifact_design_profile.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_artifact_design_profile.py [-h] [--output-md OUTPUT_MD]\n                                         [--output-json OUTPUT_JSON]\n                                         [skill_dir]\n\nRender artifact design direction and visual qua",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_baseline_compare.py",
            "command": "python3 scripts/render_baseline_compare.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_baseline_compare.py [-h] --entry ENTRY\n                                  [--output-json OUTPUT_JSON]\n                                  [--output-md OUTPUT_MD]\n\nRender a baseline comparison report from description optimization ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_benchmark_reproducibility.py",
            "command": "python3 scripts/render_benchmark_reproducibility.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_benchmark_reproducibility.py [-h] [--output-json OUTPUT_JSON]\n                                           [--output-md OUTPUT_MD]\n                                           [--generated-at GENERATED_AT]\n                        ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_context_reports.py",
            "command": "python3 scripts/render_context_reports.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_context_reports.py [-h] [--generated-at GENERATED_AT]\n\nRender context budget reports for root and example skills.\n\noptions:\n  -h, --help            show this help message and exit\n  --generated-at GENERATED_AT\n                ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_description_drift_history.py",
            "command": "python3 scripts/render_description_drift_history.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_description_drift_history.py [-h] [--history-dir HISTORY_DIR]\n                                           [--output OUTPUT]\n\nRender description optimization drift history.\n\noptions:\n  -h, --help            show this help messag",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_eval_dashboard.py",
            "command": "python3 scripts/render_eval_dashboard.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_eval_dashboard.py [-h] [--eval-dir EVAL_DIR]\n                                [--description-file DESCRIPTION_FILE]\n                                [--baseline-description-file BASELINE_DESCRIPTION_FILE]\n                       ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_intent_confidence.py",
            "command": "python3 scripts/render_intent_confidence.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_intent_confidence.py [-h] [--context-json CONTEXT_JSON]\n                                   [--output-md OUTPUT_MD]\n                                   [--output-json OUTPUT_JSON]\n                                   [skill_dir]\n\n",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_intent_dialogue.py",
            "command": "python3 scripts/render_intent_dialogue.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_intent_dialogue.py [-h] [--output-md OUTPUT_MD]\n                                 [--output-json OUTPUT_JSON]\n                                 [skill_dir]\n\nRender an intent dialogue guide for a skill package.\n\npositional argume",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_iteration_directions.py",
            "command": "python3 scripts/render_iteration_directions.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_iteration_directions.py [-h] [--output-md OUTPUT_MD]\n                                      [--output-json OUTPUT_JSON]\n                                      [skill_dir]\n\nRender the top three next iteration directions for a ski",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_iteration_ledger.py",
            "command": "python3 scripts/render_iteration_ledger.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_iteration_ledger.py [-h] [--history-dir HISTORY_DIR]\n                                  [--description-history-dir DESCRIPTION_HISTORY_DIR]\n                                  [--route-scorecard ROUTE_SCORECARD]\n                 ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_output_risk_profile.py",
            "command": "python3 scripts/render_output_risk_profile.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_output_risk_profile.py [-h] [--output-md OUTPUT_MD]\n                                     [--output-json OUTPUT_JSON]\n                                     [skill_dir]\n\nRender predicted output failure modes and quality constrain",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_portability_report.py",
            "command": "python3 scripts/render_portability_report.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_portability_report.py [-h] [--output-json OUTPUT_JSON]\n                                    [--output-md OUTPUT_MD]\n\nRender a portability score from neutral metadata, contracts, and snapshots.\n\noptions:\n  -h, --help            ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_prompt_quality_profile.py",
            "command": "python3 scripts/render_prompt_quality_profile.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_prompt_quality_profile.py [-h] [--output-md OUTPUT_MD]\n                                        [--output-json OUTPUT_JSON]\n                                        [skill_dir]\n\nRender prompt behavior quality, RTF mapping, and n",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_reference_scan.py",
            "command": "python3 scripts/render_reference_scan.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_reference_scan.py [-h] [--external-reference EXTERNAL_REFERENCE]\n                                [--user-reference USER_REFERENCE]\n                                [--local-constraint LOCAL_CONSTRAINT]\n                         ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_reference_synthesis.py",
            "command": "python3 scripts/render_reference_synthesis.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_reference_synthesis.py [-h] [--output-md OUTPUT_MD]\n                                     [--output-json OUTPUT_JSON]\n                                     [skill_dir]\n\nRender a multi-source reference synthesis report for a skil",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_regression_history.py",
            "command": "python3 scripts/render_regression_history.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_regression_history.py [-h] [--history-dir HISTORY_DIR]\n                                    [--output OUTPUT]\n\nRender regression history from milestone snapshots.\n\noptions:\n  -h, --help            show this help message and exi",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_review_annotations.py",
            "command": "python3 scripts/render_review_annotations.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_review_annotations.py [-h] [--annotations-json ANNOTATIONS_JSON]\n                                    [--output-json OUTPUT_JSON]\n                                    [--output-md OUTPUT_MD] [--write-template]\n                  ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_review_studio.py",
            "command": "python3 scripts/render_review_studio.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_review_studio.py [-h] [--output-html OUTPUT_HTML]\n                               [--output-json OUTPUT_JSON]\n                               [skill_dir]\n\nRender Review Studio 2.0 for a skill package.\n\npositional arguments:\n  sk",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_review_viewer.py",
            "command": "python3 scripts/render_review_viewer.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_review_viewer.py [-h] [--output-html OUTPUT_HTML]\n                               [--output-json OUTPUT_JSON]\n                               [skill_dir]\n\nRender a compact HTML review viewer for a skill package.\n\npositional argu",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_review_waivers.py",
            "command": "python3 scripts/render_review_waivers.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_review_waivers.py [-h] [--waivers-json WAIVERS_JSON]\n                                [--output-json OUTPUT_JSON]\n                                [--output-md OUTPUT_MD]\n                                [--generated-at GENERATED",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_skill_interpretation.py",
            "command": "python3 scripts/render_skill_interpretation.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_skill_interpretation.py [-h] [--output-html OUTPUT_HTML]\n                                      [--output-json OUTPUT_JSON]\n                                      [skill_dir]\n\nRender the first-class HTML skill interpretation rep",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_skill_os2_audit.py",
            "command": "python3 scripts/render_skill_os2_audit.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_skill_os2_audit.py [-h] [--output-json OUTPUT_JSON]\n                                 [--output-md OUTPUT_MD]\n                                 [--generated-at GENERATED_AT]\n                                 [skill_dir]\n\nRender a",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_skill_os2_coverage.py",
            "command": "python3 scripts/render_skill_os2_coverage.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_skill_os2_coverage.py [-h] [--output-json OUTPUT_JSON]\n                                    [--output-md OUTPUT_MD]\n                                    [--generated-at GENERATED_AT]\n                                    [skill_di",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_skill_overview.py",
            "command": "python3 scripts/render_skill_overview.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_skill_overview.py [-h] [--output-html OUTPUT_HTML]\n                                [--output-json OUTPUT_JSON]\n                                [skill_dir]\n\nRender the HTML skill report for a skill package.\n\npositional argument",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_social_preview.py",
            "command": "python3 scripts/render_social_preview.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_social_preview.py [-h] [--format {all,png,svg}]\n\nRender the repository social preview image assets.\n\noptions:\n  -h, --help            show this help message and exit\n  --format {all,png,svg}\n                        Asset forma",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_system_model.py",
            "command": "python3 scripts/render_system_model.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_system_model.py [-h] [--output-md OUTPUT_MD]\n                              [--output-json OUTPUT_JSON]\n                              [skill_dir]\n\nRender a systems-thinking model for a skill package.\n\npositional arguments:\n  sk",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_telemetry_hook_recipes.py",
            "command": "python3 scripts/render_telemetry_hook_recipes.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_telemetry_hook_recipes.py [-h] [--output-json OUTPUT_JSON]\n                                        [--output-md OUTPUT_MD]\n                                        [--output-jsonl OUTPUT_JSONL]\n                                 ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_world_class_claim_guard.py",
            "command": "python3 scripts/render_world_class_claim_guard.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_world_class_claim_guard.py [-h] [--claim-surface CLAIM_SURFACE]\n                                         [--output-json OUTPUT_JSON]\n                                         [--output-md OUTPUT_MD]\n                            ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_world_class_evidence_intake.py",
            "command": "python3 scripts/render_world_class_evidence_intake.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_world_class_evidence_intake.py [-h]\n                                             [--submissions-dir SUBMISSIONS_DIR]\n                                             [--output-json OUTPUT_JSON]\n                                    ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_world_class_evidence_ledger.py",
            "command": "python3 scripts/render_world_class_evidence_ledger.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_world_class_evidence_ledger.py [-h] [--output-json OUTPUT_JSON]\n                                             [--output-md OUTPUT_MD]\n                                             [--submissions-dir SUBMISSIONS_DIR]\n            ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_world_class_evidence_plan.py",
            "command": "python3 scripts/render_world_class_evidence_plan.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_world_class_evidence_plan.py [-h] [--output-json OUTPUT_JSON]\n                                           [--output-md OUTPUT_MD]\n                                           [--generated-at GENERATED_AT]\n                        ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_world_class_operator_runbook.py",
            "command": "python3 scripts/render_world_class_operator_runbook.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_world_class_operator_runbook.py [-h]\n                                              [--submissions-dir SUBMISSIONS_DIR]\n                                              [--output-json OUTPUT_JSON]\n                                 ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/render_world_class_submission_review.py",
            "command": "python3 scripts/render_world_class_submission_review.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: render_world_class_submission_review.py [-h]\n                                               [--submissions-dir SUBMISSIONS_DIR]\n                                               [--output-json OUTPUT_JSON]\n                              ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/resource_boundary_check.py",
            "command": "python3 scripts/resource_boundary_check.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: resource_boundary_check.py [-h]\n                                  [--max-initial-tokens MAX_INITIAL_TOKENS]\n                                  [--warn-skill-body-tokens WARN_SKILL_BODY_TOKENS]\n                                  skill_d",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/run_conformance_suite.py",
            "command": "python3 scripts/run_conformance_suite.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: run_conformance_suite.py [-h]\n                                [--target {openai,claude,agent-skills,vscode,generic}]\n                                [--output-json OUTPUT_JSON]\n                                [--output-md OUTPUT_MD]\n",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/run_description_optimization_suite.py",
            "command": "python3 scripts/run_description_optimization_suite.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: run_description_optimization_suite.py [-h]\n                                             [--history-snapshot-output HISTORY_SNAPSHOT_OUTPUT]\n                                             [--snapshot-date SNAPSHOT_DATE]\n                ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/run_eval_suite.py",
            "command": "python3 scripts/run_eval_suite.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: run_eval_suite.py [-h] [--eval-dir EVAL_DIR]\n                         [--description-file DESCRIPTION_FILE]\n                         [--baseline-description-file BASELINE_DESCRIPTION_FILE]\n                         [--output-file OUTP",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/run_output_eval.py",
            "command": "python3 scripts/run_output_eval.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: run_output_eval.py [-h] [--cases CASES] [--output-json OUTPUT_JSON]\n                          [--output-md OUTPUT_MD]\n                          [--blind-pack-json BLIND_PACK_JSON]\n                          [--blind-pack-md BLIND_PACK",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/run_output_execution.py",
            "command": "python3 scripts/run_output_execution.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: run_output_execution.py [-h] [--cases CASES]\n                               [--output-json OUTPUT_JSON]\n                               [--output-md OUTPUT_MD]\n                               [--runner-command RUNNER_COMMAND]\n         ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/simulate_install.py",
            "command": "python3 scripts/simulate_install.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: simulate_install.py [-h] [--package-dir PACKAGE_DIR]\n                           [--install-root INSTALL_ROOT]\n                           [--output-json OUTPUT_JSON] [--output-md OUTPUT_MD]\n                           [--generated-at G",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/summarize_user_signals.py",
            "command": "python3 scripts/summarize_user_signals.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: summarize_user_signals.py [-h] --source SOURCE\n                                 [--output-json OUTPUT_JSON]\n                                 [--output-md OUTPUT_MD]\n                                 [--min-support MIN_SUPPORT]\n       ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/sync_local_install.py",
            "command": "python3 scripts/sync_local_install.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: sync_local_install.py [-h] [--root ROOT] [--install-dir INSTALL_DIR]\n                             [--package-dir PACKAGE_DIR]\n                             [--generated-at GENERATED_AT]\n                             [--skip-install-pre",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/telemetry_native_host.py",
            "command": "python3 scripts/telemetry_native_host.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: telemetry_native_host.py [-h] [--output-jsonl OUTPUT_JSONL]\n                                [--message-json MESSAGE_JSON] [--stdio]\n                                [--dry-run] [--write-manifest WRITE_MANIFEST]\n                       ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/trigger_eval.py",
            "command": "python3 scripts/trigger_eval.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: trigger_eval.py [-h] [--description DESCRIPTION]\n                       [--description-file DESCRIPTION_FILE]\n                       [--baseline-description BASELINE_DESCRIPTION]\n                       [--baseline-description-file BA",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/trust_check.py",
            "command": "python3 scripts/trust_check.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: trust_check.py [-h] [--output-json OUTPUT_JSON] [--output-md OUTPUT_MD]\n                      [--skip-help-smoke]\n                      [--help-smoke-timeout HELP_SMOKE_TIMEOUT]\n                      [skill_dir]\n\nRun Skill OS trust a",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/upgrade_check.py",
            "command": "python3 scripts/upgrade_check.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: upgrade_check.py [-h] --previous-package-json PREVIOUS_PACKAGE_JSON\n                        [--current-package-json CURRENT_PACKAGE_JSON]\n                        [--output-json OUTPUT_JSON] [--output-md OUTPUT_MD]\n                   ",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/validate_skill.py",
            "command": "python3 scripts/validate_skill.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: validate_skill.py [-h] skill_dir\n\nValidate a skill package.\n\npositional arguments:\n  skill_dir\n\noptions:\n  -h, --help  show this help message and exit",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/verify_package.py",
            "command": "python3 scripts/verify_package.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: verify_package.py [-h] [--package-dir PACKAGE_DIR]\n                         [--expectations EXPECTATIONS]\n                         [--registry-json REGISTRY_JSON]\n                         [--output-json OUTPUT_JSON] [--output-md OUTP",
            "stderr_excerpt": ""
          },
          {
            "path": "scripts/yao.py",
            "command": "python3 scripts/yao.py --help",
            "returncode": 0,
            "timed_out": false,
            "passed": true,
            "has_help_text": true,
            "stdout_excerpt": "usage: yao.py [-h] [--record-cli-telemetry] [--no-cli-telemetry]\n              [--telemetry-events-jsonl TELEMETRY_EVENTS_JSONL]\n              {init,quickstart,validate,optimize-description,promote-check,python-compat,architecture-audit,rev",
            "stderr_excerpt": ""
          }
        ],
        "skipped": [
          {
            "path": "scripts/html_rendering.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/review_studio_action_evidence.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/review_studio_actions.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/review_studio_data.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/review_studio_formatting.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/review_studio_gates.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/review_studio_layout.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/review_studio_output_review.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/review_studio_waivers.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/review_studio_world_class.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/review_viewer_data.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/skill_report_charts.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/skill_report_i18n.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/skill_report_layout.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/skill_report_metrics.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/skill_report_model.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/skill_report_world_class.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/world_class_evidence_contract.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/world_class_source_checks.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/yao_cli_adaptation_commands.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/yao_cli_config.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/yao_cli_create_commands.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/yao_cli_parser.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/yao_cli_report_commands.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/yao_cli_runtime.py",
            "reason": "internal module"
          },
          {
            "path": "scripts/yao_cli_telemetry.py",
            "reason": "internal module"
          }
        ]
      },
      "permission_governance": {
        "present": true,
        "path": "security/permission_policy.json",
        "schema_version": "1.0",
        "reviewed_at": "2026-06-13",
        "required_capabilities": [
          "file_write",
          "network",
          "subprocess"
        ],
        "approved_capabilities": [
          "file_write",
          "network",
          "subprocess"
        ],
        "missing_capabilities": [],
        "invalid_capabilities": [],
        "expired_capabilities": [],
        "approval_count": 3,
        "required_count": 3,
        "missing_count": 0,
        "invalid_count": 0,
        "expired_count": 0,
        "approvals": [
          {
            "capability": "network",
            "status": "approved",
            "scripts": [
              "scripts/check_update.py",
              "scripts/github_benchmark_scan.py",
              "scripts/provider_output_eval_runner.py"
            ],
            "reviewer": "Yao Team",
            "scope": "Only scripts declared in security/network_policy.json may perform outbound requests.",
            "reason": "Network use is bounded to public GitHub metadata and benchmark discovery, with allowed hosts reviewed in security/network_policy.json.",
            "expires_at": "2026-09-30",
            "evidence": [
              "security/network_policy.json",
              "reports/security_trust_report.md"
            ],
            "target_enforcement": {
              "openai": "metadata-only permission_contract in openai.yaml plus adapter.json",
              "claude": "adapter.json target_permission_contract and README note",
              "generic": "adapter.json target_permission_contract",
              "vscode": "adapter.json target_permission_contract plus VS Code workspace-trust note"
            },
            "validation": []
          },
          {
            "capability": "file_write",
            "status": "approved",
            "scripts": [
              "scripts/adjudicate_output_review.py",
              "scripts/build_confusion_matrix.py",
              "scripts/build_skill_atlas.py",
              "scripts/check_update.py",
              "scripts/ci_test.py",
              "scripts/collect_feedback.py",
              "scripts/compile_skill.py",
              "scripts/create_iteration_snapshot.py",
              "scripts/cross_packager.py",
              "scripts/emit_telemetry_event.py",
              "scripts/export_skill_ir.py",
              "scripts/github_benchmark_scan.py",
              "scripts/import_telemetry_events.py",
              "scripts/init_skill.py",
              "scripts/prepare_output_review_kit.py",
              "scripts/prepare_world_class_submission_kit.py",
              "scripts/probe_runtime_permissions.py",
              "scripts/promotion_checker.py",
              "scripts/propose_adaptation.py",
              "scripts/python_compat_check.py",
              "scripts/registry_audit.py",
              "scripts/render_adoption_drift_report.py",
              "scripts/render_architecture_maintainability.py",
              "scripts/render_artifact_design_profile.py",
              "scripts/render_baseline_compare.py",
              "scripts/render_benchmark_reproducibility.py",
              "scripts/render_context_reports.py",
              "scripts/render_description_drift_history.py",
              "scripts/render_eval_dashboard.py",
              "scripts/render_intent_confidence.py",
              "scripts/render_intent_dialogue.py",
              "scripts/render_iteration_directions.py",
              "scripts/render_iteration_ledger.py",
              "scripts/render_output_risk_profile.py",
              "scripts/render_portability_report.py",
              "scripts/render_prompt_quality_profile.py",
              "scripts/render_reference_scan.py",
              "scripts/render_reference_synthesis.py",
              "scripts/render_regression_history.py",
              "scripts/render_review_annotations.py",
              "scripts/render_review_studio.py",
              "scripts/render_review_viewer.py",
              "scripts/render_review_waivers.py",
              "scripts/render_skill_interpretation.py",
              "scripts/render_skill_os2_audit.py",
              "scripts/render_skill_os2_coverage.py",
              "scripts/render_skill_overview.py",
              "scripts/render_social_preview.py",
              "scripts/render_system_model.py",
              "scripts/render_telemetry_hook_recipes.py",
              "scripts/render_world_class_claim_guard.py",
              "scripts/render_world_class_evidence_intake.py",
              "scripts/render_world_class_evidence_ledger.py",
              "scripts/render_world_class_evidence_plan.py",
              "scripts/render_world_class_operator_runbook.py",
              "scripts/render_world_class_submission_review.py",
              "scripts/run_conformance_suite.py",
              "scripts/run_description_optimization_suite.py",
              "scripts/run_output_eval.py",
              "scripts/run_output_execution.py",
              "scripts/simulate_install.py",
              "scripts/summarize_user_signals.py",
              "scripts/sync_local_install.py",
              "scripts/telemetry_native_host.py",
              "scripts/trust_check.py",
              "scripts/upgrade_check.py",
              "scripts/verify_package.py"
            ],
            "reviewer": "Yao Team",
            "scope": "Local generated reports, registry metadata, temporary test outputs, and package artifacts under the skill workspace.",
            "reason": "File writes are required to create auditable reports, compiled target contracts, package artifacts, and local test fixtures; package safety checks exclude generated temp outputs from archives.",
            "expires_at": "2026-09-30",
            "evidence": [
              "reports/package_verification.md",
              "reports/install_simulation.md",
              "security/permission_policy.md"
            ],
            "target_enforcement": {
              "openai": "metadata-only permission_contract in openai.yaml plus adapter.json",
              "claude": "adapter.json target_permission_contract and README note",
              "generic": "adapter.json target_permission_contract",
              "vscode": "adapter.json target_permission_contract plus VS Code workspace-trust note"
            },
            "validation": []
          },
          {
            "capability": "subprocess",
            "status": "approved",
            "scripts": [
              "scripts/ci_test.py",
              "scripts/render_benchmark_reproducibility.py",
              "scripts/render_eval_dashboard.py",
              "scripts/run_eval_suite.py",
              "scripts/run_output_execution.py",
              "scripts/sync_local_install.py",
              "scripts/trust_check.py",
              "scripts/yao.py",
              "scripts/yao_cli_runtime.py"
            ],
            "reviewer": "Yao Team",
            "scope": "Local deterministic validation, packaging, install simulation, and CI orchestration commands.",
            "reason": "Subprocess use is limited to local verification and packaging flows that are surfaced through CLI help smoke tests and CI targets.",
            "expires_at": "2026-09-30",
            "evidence": [
              "reports/security_trust_report.md",
              "reports/review-studio.html"
            ],
            "target_enforcement": {
              "openai": "metadata-only permission_contract in openai.yaml plus adapter.json",
              "claude": "adapter.json target_permission_contract and README note",
              "generic": "adapter.json target_permission_contract",
              "vscode": "adapter.json target_permission_contract plus VS Code workspace-trust note"
            },
            "validation": []
          }
        ]
      },
      "trust_metadata": {
        "source_tier": "local",
        "remote_inline_execution": "forbid",
        "remote_metadata_policy": "allow-metadata-only"
      },
      "artifacts": {
        "json": "reports/security_trust_report.json",
        "markdown": "reports/security_trust_report.md"
      }
    },
    "python_compatibility": {
      "schema_version": "1.0",
      "ok": true,
      "generated_at": "2026-06-13",
      "root": ".",
      "summary": {
        "target_python": "3.11",
        "file_count": 171,
        "issue_count": 0,
        "syntax_error_count": 0,
        "fstring_311_violation_count": 0,
        "decision": "pass"
      },
      "rules": [
        {
          "key": "current-python-syntax",
          "reason": "Every scanned Python source file must compile under the running interpreter."
        },
        {
          "key": "fstring-expression-backslash",
          "reason": "Python 3.11 rejects backslashes inside f-string expressions; keep escaping outside the expression."
        }
      ],
      "files": [
        {
          "path": "examples/complex-release-orchestrator/generated-skill/scripts/build_release_packet.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "examples/governed-incident-command/generated-skill/scripts/build_incident_packet.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "geo-ranking-article-generator/scripts/build_html_index.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/adjudicate_output_review.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/build_confusion_matrix.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/build_skill_atlas.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/check_update.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/ci_test.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/collect_feedback.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/compile_skill.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/context_sizer.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/create_iteration_snapshot.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/cross_packager.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/diff_eval.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/emit_telemetry_event.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/export_skill_ir.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/github_benchmark_scan.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/governance_check.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/html_rendering.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/import_telemetry_events.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/init_skill.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/judge_blind_eval.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/lint_skill.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/local_output_eval_runner.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/optimize_description.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/prepare_output_review_kit.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/prepare_world_class_submission_kit.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/probe_runtime_permissions.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/promotion_checker.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/propose_adaptation.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/provider_output_eval_runner.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/python_compat_check.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/registry_audit.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_adoption_drift_report.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_architecture_maintainability.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_artifact_design_profile.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_baseline_compare.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_benchmark_reproducibility.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_context_reports.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_description_drift_history.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_eval_dashboard.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_intent_confidence.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_intent_dialogue.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_iteration_directions.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_iteration_ledger.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_output_risk_profile.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_portability_report.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_prompt_quality_profile.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_reference_scan.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_reference_synthesis.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_regression_history.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_review_annotations.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_review_studio.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_review_viewer.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_review_waivers.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_skill_interpretation.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_skill_os2_audit.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_skill_os2_coverage.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_skill_overview.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_social_preview.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_system_model.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_telemetry_hook_recipes.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_world_class_claim_guard.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_world_class_evidence_intake.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_world_class_evidence_ledger.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_world_class_evidence_plan.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_world_class_operator_runbook.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/render_world_class_submission_review.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/resource_boundary_check.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/review_studio_action_evidence.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/review_studio_actions.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/review_studio_data.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/review_studio_formatting.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/review_studio_gates.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/review_studio_layout.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/review_studio_output_review.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/review_studio_waivers.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/review_studio_world_class.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/review_viewer_data.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/run_conformance_suite.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/run_description_optimization_suite.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/run_eval_suite.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/run_output_eval.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/run_output_execution.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/simulate_install.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/skill_report_charts.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/skill_report_i18n.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/skill_report_layout.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/skill_report_metrics.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/skill_report_model.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/skill_report_world_class.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/summarize_user_signals.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/sync_local_install.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/telemetry_native_host.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/trigger_eval.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/trust_check.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/upgrade_check.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/validate_skill.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/verify_package.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/world_class_evidence_contract.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/world_class_source_checks.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/yao.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/yao_cli_adaptation_commands.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/yao_cli_config.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/yao_cli_create_commands.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/yao_cli_parser.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/yao_cli_report_commands.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/yao_cli_runtime.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "scripts/yao_cli_telemetry.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_adaptation_safety.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_adapter_snapshots.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_adoption_drift.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_architecture_maintainability.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_artifact_design_profile.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_baseline_compare.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_benchmark_reproducibility.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_compile_skill.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_conformance_suite.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_description_optimization.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_failure_regressions.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_feedback.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_github_benchmark_scan.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_html_rendering.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_install_simulation.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_intent_confidence.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_iteration_directions.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_local_install_sync.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_output_eval_lab.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_output_execution_runs.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_output_review_adjudication.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_output_review_kit.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_output_risk_profile.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_package_verification.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_packager_failures.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_portability_report.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_promotion_checker.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_prompt_quality_profile.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_python_compat_check.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_quality_checks.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_reference_scan.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_reference_synthesis.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_registry_audit.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_review_annotations.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_review_studio.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_review_viewer.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_review_waivers.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_route_confusion.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_runtime_permission_probes.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_security_boundaries.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_skill_atlas.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_skill_interpretation.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_skill_ir.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_skill_os2_audit.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_skill_os2_coverage.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_skill_overview.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_skill_report_charts.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_skill_report_metrics.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_system_model.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_telemetry_emit.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_telemetry_hooks.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_telemetry_import.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_telemetry_native_host.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_trust_check.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_upgrade_check.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_world_class_claim_guard.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_world_class_evidence_intake.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_world_class_evidence_ledger.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_world_class_evidence_plan.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_world_class_operator_runbook.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_world_class_submission_review.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        },
        {
          "path": "tests/verify_yao_cli.py",
          "ok": true,
          "issue_count": 0,
          "issues": []
        }
      ],
      "issues": [],
      "artifacts": {
        "json": "reports/python_compatibility.json",
        "markdown": "reports/python_compatibility.md"
      }
    },
    "architecture_maintainability": {
      "schema_version": "1.0",
      "ok": true,
      "generated_at": "2026-06-13",
      "skill_dir": ".",
      "summary": {
        "python_file_count": 168,
        "script_file_count": 106,
        "test_file_count": 62,
        "internal_module_count": 29,
        "cli_script_count": 79,
        "command_handler_count": 34,
        "warn_line_threshold": 900,
        "block_line_threshold": 1500,
        "largest_file_lines": 886,
        "hotspot_count": 0,
        "blocker_count": 0,
        "decision": "pass"
      },
      "largest_files": [
        {
          "path": "scripts/yao.py",
          "lines": 886,
          "kind": "cli-script",
          "severity": "pass",
          "recommendation": "Split command handlers by domain while keeping scripts/yao.py as the thin CLI orchestrator."
        },
        {
          "path": "tests/verify_yao_cli.py",
          "lines": 886,
          "kind": "test",
          "severity": "pass",
          "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
        },
        {
          "path": "scripts/skill_report_layout.py",
          "lines": 808,
          "kind": "internal-module",
          "severity": "pass",
          "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
        },
        {
          "path": "scripts/skill_report_model.py",
          "lines": 800,
          "kind": "internal-module",
          "severity": "pass",
          "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
        },
        {
          "path": "scripts/yao_cli_parser.py",
          "lines": 774,
          "kind": "internal-module",
          "severity": "pass",
          "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
        },
        {
          "path": "tests/verify_review_studio.py",
          "lines": 751,
          "kind": "test",
          "severity": "pass",
          "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
        },
        {
          "path": "scripts/compile_skill.py",
          "lines": 734,
          "kind": "cli-script",
          "severity": "pass",
          "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
        },
        {
          "path": "scripts/build_skill_atlas.py",
          "lines": 730,
          "kind": "cli-script",
          "severity": "pass",
          "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
        },
        {
          "path": "scripts/optimize_description.py",
          "lines": 723,
          "kind": "cli-script",
          "severity": "pass",
          "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
        },
        {
          "path": "scripts/trust_check.py",
          "lines": 714,
          "kind": "internal-module",
          "severity": "pass",
          "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
        },
        {
          "path": "scripts/review_studio_layout.py",
          "lines": 694,
          "kind": "internal-module",
          "severity": "pass",
          "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
        },
        {
          "path": "scripts/render_review_viewer.py",
          "lines": 685,
          "kind": "cli-script",
          "severity": "pass",
          "recommendation": "Split viewer data assembly from HTML section rendering."
        }
      ],
      "hotspots": [],
      "actions": [],
      "artifacts": {
        "json": "reports/architecture_maintainability.json",
        "markdown": "reports/architecture_maintainability.md"
      }
    },
    "context_budget": {
      "ok": true,
      "failures": [],
      "warnings": [],
      "stats": {
        "context_budget_tier": "production",
        "context_budget_limit": 1000,
        "skill_body_tokens": 767,
        "other_text_tokens": 1307850,
        "estimated_initial_load_tokens": 960,
        "estimated_total_text_tokens": 1308617,
        "deferred_resource_tokens": 416415,
        "deferred_resource_warn_threshold": 120000,
        "deferred_resource_dirs": [
          {
            "path": "scripts",
            "estimated_tokens": 367825,
            "file_count": 106
          },
          {
            "path": "references",
            "estimated_tokens": 26755,
            "file_count": 34
          },
          {
            "path": "evals",
            "estimated_tokens": 21835,
            "file_count": 27
          }
        ],
        "large_deferred_resource_dirs": [
          {
            "path": "scripts",
            "estimated_tokens": 367825,
            "file_count": 106
          }
        ],
        "deferred_resource_governance": {
          "status": "governed",
          "large_dir_count": 1,
          "governed_large_dir_count": 1,
          "directories": [
            {
              "status": "governed",
              "evidence": [
                "reports/security_trust_report.json",
                "reports/architecture_maintainability.json",
                "reports/python_compatibility.json"
              ],
              "reasons": [
                "trust report covers scripts",
                "architecture report has no script hotspots or blockers",
                "Python compatibility report has no issues"
              ],
              "missing": [],
              "path": "scripts",
              "estimated_tokens": 367825,
              "file_count": 106,
              "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
            }
          ],
          "summary": "Large deferred resources are indexed and backed by evidence."
        },
        "relevant_file_count": 544,
        "unused_resource_dirs": [],
        "quality_signal_points": 130,
        "quality_density": 135.4
      }
    },
    "promotion": {
      "ok": true,
      "summary": {
        "promote": 0,
        "keep_current": 3,
        "blocked": 0
      },
      "targets": [
        {
          "name": "yao-meta-skill",
          "winner_label": "Current",
          "winner_description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
          "winner_tokens": 65,
          "current_tokens": 65,
          "winner_holdout_fp": 0,
          "winner_holdout_fn": 0,
          "current_holdout_fp": 0,
          "current_holdout_fn": 0,
          "baseline_holdout_fp": 0,
          "baseline_holdout_fn": 0,
          "winner_blind_holdout_fp": 0,
          "winner_blind_holdout_fn": 0,
          "current_blind_holdout_fp": 0,
          "current_blind_holdout_fn": 0,
          "baseline_blind_holdout_fp": 0,
          "baseline_blind_holdout_fn": 0,
          "winner_blind_holdout_total_errors": 0,
          "winner_judge_blind_holdout_fp": 0,
          "winner_judge_blind_holdout_fn": 0,
          "current_judge_blind_holdout_fp": 0,
          "current_judge_blind_holdout_fn": 0,
          "baseline_judge_blind_holdout_fp": 0,
          "baseline_judge_blind_holdout_fn": 0,
          "winner_judge_blind_holdout_total_errors": 0,
          "winner_adversarial_holdout_fp": 0,
          "winner_adversarial_holdout_fn": 0,
          "current_adversarial_holdout_fp": 0,
          "current_adversarial_holdout_fn": 0,
          "baseline_adversarial_holdout_fp": 0,
          "baseline_adversarial_holdout_fn": 0,
          "winner_adversarial_holdout_total_errors": 0,
          "calibration": {
            "holdout": {
              "threshold": 0.33,
              "mean_positive_score": 0.673,
              "mean_non_trigger_score": 0.0,
              "mean_near_neighbor_score": 0.0,
              "min_positive_score": 0.468,
              "max_non_trigger_score": 0.0,
              "score_gap": 0.468,
              "threshold_margin": 0.138,
              "positive_threshold_buffer": 0.138,
              "negative_threshold_buffer": 0.33,
              "boundary_case_count": 0,
              "boundary_case_rate": 0.0,
              "risk_band": "healthy"
            },
            "blind_holdout": {
              "threshold": 0.33,
              "mean_positive_score": 0.399,
              "mean_non_trigger_score": 0.013,
              "mean_near_neighbor_score": 0.013,
              "min_positive_score": 0.392,
              "max_non_trigger_score": 0.028,
              "score_gap": 0.364,
              "threshold_margin": 0.062,
              "positive_threshold_buffer": 0.062,
              "negative_threshold_buffer": 0.302,
              "boundary_case_count": 2,
              "boundary_case_rate": 0.333,
              "risk_band": "watch"
            },
            "adversarial_holdout": {
              "threshold": 0.33,
              "mean_positive_score": 0.838,
              "mean_non_trigger_score": 0.0,
              "mean_near_neighbor_score": 0.0,
              "min_positive_score": 0.834,
              "max_non_trigger_score": 0.0,
              "score_gap": 0.834,
              "threshold_margin": 0.33,
              "positive_threshold_buffer": 0.504,
              "negative_threshold_buffer": 0.33,
              "boundary_case_count": 0,
              "boundary_case_rate": 0.0,
              "risk_band": "healthy"
            }
          },
          "judge_blind": {
            "winner": {
              "agreement_rate": 1.0,
              "mean_confidence": 0.66,
              "rubric_version": "blind-v1"
            },
            "current": {
              "agreement_rate": 1.0,
              "mean_confidence": 0.66,
              "rubric_version": "blind-v1"
            },
            "baseline": {
              "agreement_rate": 1.0,
              "mean_confidence": 0.66,
              "rubric_version": "blind-v1"
            }
          },
          "family_health": {
            "holdout": {
              "family_count": 12,
              "clean_family_count": 12,
              "failing_families": [],
              "weakest_family": {
                "family": "workflow_to_skill",
                "pass_rate": 1.0,
                "errors": 0
              }
            },
            "blind_holdout": {
              "family_count": 6,
              "clean_family_count": 6,
              "failing_families": [],
              "weakest_family": {
                "family": "blind_operationalize",
                "pass_rate": 1.0,
                "errors": 0
              }
            },
            "judge_blind_holdout": {
              "family_count": 6,
              "clean_family_count": 6,
              "failing_families": [],
              "weakest_family": {
                "family": "blind_operationalize",
                "pass_rate": 1.0,
                "errors": 0
              }
            },
            "adversarial_holdout": {
              "family_count": 6,
              "clean_family_count": 6,
              "failing_families": [],
              "weakest_family": {
                "family": "adversarial_summary_translation_collision",
                "pass_rate": 1.0,
                "errors": 0
              }
            }
          },
          "drift_note": "blind, judge-backed blind, adversarial, and calibration gates active",
          "ok": true,
          "promotion": {
            "decision": "keep_current",
            "winner_changed": false,
            "all_gates_pass": true,
            "route_clean": true,
            "judge_agreement_ok": true,
            "causes": [
              "no_candidate_outperformed_current"
            ],
            "next_action": "Keep the current description and open a new candidate only when fresh route evidence appears.",
            "gate_status": {
              "visible_holdout_non_regression": true,
              "blind_holdout_non_regression": true,
              "judge_blind_non_regression": true,
              "judge_blind_agreement": true,
              "adversarial_non_regression": true,
              "adversarial_risk_ok": true,
              "route_confusion_clean": true,
              "family_stability": true
            },
            "route_metrics": {
              "precision": 1.0,
              "recall": 1.0,
              "average_margin": 0.611,
              "misroute_count": 0,
              "ambiguous_case_count": 0
            }
          },
          "registry": [
            {
              "name": "yao-meta-skill",
              "role": "baseline",
              "label": "Baseline",
              "ranking_state": "reference",
              "promotion_state": "reference",
              "description": "Create and improve agent skills.",
              "tokens": 8,
              "dev_errors": 1,
              "holdout_errors": 0
            },
            {
              "name": "yao-meta-skill",
              "role": "current",
              "label": "Current",
              "ranking_state": "selected_by_dev",
              "promotion_state": "kept_current",
              "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
              "tokens": 65,
              "dev_errors": 0,
              "holdout_errors": 0,
              "reason_tags": []
            },
            {
              "name": "yao-meta-skill",
              "role": "candidate",
              "label": "Minimal",
              "ranking_state": "not_selected",
              "promotion_state": "blocked",
              "description": "Create, refactor, evaluate, and package agent skills. Use when asked to create a skill, turn a repeated process into a reusable skill, or improve an existing skill.",
              "tokens": 41,
              "dev_errors": 2,
              "holdout_errors": 0,
              "reason_tags": [
                "weaker_dev_fit"
              ]
            },
            {
              "name": "yao-meta-skill",
              "role": "candidate",
              "label": "Guardrail",
              "ranking_state": "not_selected",
              "promotion_state": "blocked",
              "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, notes, 流程, 提示词, 对话记录, 文档, or 笔记. Do not use for summary-only requests, translation-only requests, or plain documentation tasks.",
              "tokens": 56,
              "dev_errors": 2,
              "holdout_errors": 0,
              "reason_tags": [
                "weaker_dev_fit"
              ]
            },
            {
              "name": "yao-meta-skill",
              "role": "candidate",
              "label": "Balanced",
              "ranking_state": "not_selected",
              "promotion_state": "blocked",
              "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, notes, 流程, 提示词, 对话记录, 文档, or 笔记. Use when asked to create a skill, turn a repeated process into a reusable skill, or improve an existing skill.",
              "tokens": 60,
              "dev_errors": 2,
              "holdout_errors": 0,
              "reason_tags": [
                "weaker_dev_fit"
              ]
            },
            {
              "name": "yao-meta-skill",
              "role": "candidate",
              "label": "Artifact Aware",
              "ranking_state": "not_selected",
              "promotion_state": "blocked",
              "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, notes, 流程, 提示词, 对话记录, 文档, or 笔记. Trigger when requests mention workflows, prompts, transcripts, or docs and the job is to create a skill, turn a repeated process into a reusable skill, or improve an existing skill.",
              "tokens": 77,
              "dev_errors": 2,
              "holdout_errors": 0,
              "reason_tags": [
                "weaker_dev_fit",
                "longer_without_gain"
              ]
            },
            {
              "name": "yao-meta-skill",
              "role": "candidate",
              "label": "Boundary",
              "ranking_state": "not_selected",
              "promotion_state": "blocked",
              "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, notes, 流程, 提示词, 对话记录, 文档, or 笔记. Use when asked to create a skill, turn a repeated process into a reusable skill, or improve an existing skill. Do not use for summary-only requests, translation-only requests, or plain documentation tasks.",
              "tokens": 83,
              "dev_errors": 2,
              "holdout_errors": 0,
              "reason_tags": [
                "weaker_dev_fit",
                "longer_without_gain"
              ]
            }
          ],
          "decision": "keep_current"
        },
        {
          "name": "team-frontend-review",
          "winner_label": "Current",
          "winner_description": "Review frontend code for accessibility, UI security, missing states, and UX regressions. Use when asked to review React components, run a pre-merge frontend review, or check a11y and unsafe rendering.",
          "winner_tokens": 50,
          "current_tokens": 50,
          "winner_holdout_fp": 0,
          "winner_holdout_fn": 0,
          "current_holdout_fp": 0,
          "current_holdout_fn": 0,
          "baseline_holdout_fp": 0,
          "baseline_holdout_fn": 0,
          "winner_blind_holdout_fp": 0,
          "winner_blind_holdout_fn": 0,
          "current_blind_holdout_fp": 0,
          "current_blind_holdout_fn": 0,
          "baseline_blind_holdout_fp": 0,
          "baseline_blind_holdout_fn": 0,
          "winner_blind_holdout_total_errors": 0,
          "winner_judge_blind_holdout_fp": 0,
          "winner_judge_blind_holdout_fn": 0,
          "current_judge_blind_holdout_fp": 0,
          "current_judge_blind_holdout_fn": 0,
          "baseline_judge_blind_holdout_fp": 0,
          "baseline_judge_blind_holdout_fn": 0,
          "winner_judge_blind_holdout_total_errors": 0,
          "winner_adversarial_holdout_fp": 0,
          "winner_adversarial_holdout_fn": 0,
          "current_adversarial_holdout_fp": 0,
          "current_adversarial_holdout_fn": 0,
          "baseline_adversarial_holdout_fp": 0,
          "baseline_adversarial_holdout_fn": 0,
          "winner_adversarial_holdout_total_errors": 0,
          "calibration": {
            "holdout": {
              "threshold": 0.48,
              "mean_positive_score": 0.685,
              "mean_non_trigger_score": 0.089,
              "mean_near_neighbor_score": 0.045,
              "min_positive_score": 0.496,
              "max_non_trigger_score": 0.211,
              "score_gap": 0.285,
              "threshold_margin": 0.016,
              "positive_threshold_buffer": 0.016,
              "negative_threshold_buffer": 0.269,
              "boundary_case_count": 1,
              "boundary_case_rate": 0.167,
              "risk_band": "tight"
            },
            "blind_holdout": {
              "threshold": 0.48,
              "mean_positive_score": 0.685,
              "mean_non_trigger_score": 0.177,
              "mean_near_neighbor_score": 0.226,
              "min_positive_score": 0.504,
              "max_non_trigger_score": 0.416,
              "score_gap": 0.088,
              "threshold_margin": 0.024,
              "positive_threshold_buffer": 0.024,
              "negative_threshold_buffer": 0.064,
              "boundary_case_count": 2,
              "boundary_case_rate": 0.333,
              "risk_band": "tight"
            },
            "adversarial_holdout": {
              "threshold": 0.34,
              "mean_positive_score": 0.71,
              "mean_non_trigger_score": 0.009,
              "mean_near_neighbor_score": 0.018,
              "min_positive_score": 0.544,
              "max_non_trigger_score": 0.035,
              "score_gap": 0.509,
              "threshold_margin": 0.204,
              "positive_threshold_buffer": 0.204,
              "negative_threshold_buffer": 0.305,
              "boundary_case_count": 0,
              "boundary_case_rate": 0.0,
              "risk_band": "healthy"
            }
          },
          "judge_blind": {
            "winner": {
              "agreement_rate": 1.0,
              "mean_confidence": 0.703,
              "rubric_version": "blind-v1"
            },
            "current": {
              "agreement_rate": 1.0,
              "mean_confidence": 0.703,
              "rubric_version": "blind-v1"
            },
            "baseline": {
              "agreement_rate": 1.0,
              "mean_confidence": 0.703,
              "rubric_version": "blind-v1"
            }
          },
          "family_health": {
            "holdout": {
              "family_count": 6,
              "clean_family_count": 6,
              "failing_families": [],
              "weakest_family": {
                "family": "security_and_a11y",
                "pass_rate": 1.0,
                "errors": 0
              }
            },
            "blind_holdout": {
              "family_count": 6,
              "clean_family_count": 6,
              "failing_families": [],
              "weakest_family": {
                "family": "blind_premerge",
                "pass_rate": 1.0,
                "errors": 0
              }
            },
            "judge_blind_holdout": {
              "family_count": 6,
              "clean_family_count": 6,
              "failing_families": [],
              "weakest_family": {
                "family": "blind_premerge",
                "pass_rate": 1.0,
                "errors": 0
              }
            },
            "adversarial_holdout": {
              "family_count": 6,
              "clean_family_count": 6,
              "failing_families": [],
              "weakest_family": {
                "family": "adversarial_quality_gate_review",
                "pass_rate": 1.0,
                "errors": 0
              }
            }
          },
          "drift_note": "blind, judge-backed blind, adversarial, and calibration gates active",
          "ok": true,
          "promotion": {
            "decision": "keep_current",
            "winner_changed": false,
            "all_gates_pass": true,
            "route_clean": true,
            "judge_agreement_ok": true,
            "causes": [
              "no_candidate_outperformed_current",
              "current_holdout_risk"
            ],
            "next_action": "Keep the current description and open a new candidate only when fresh route evidence appears.",
            "gate_status": {
              "visible_holdout_non_regression": true,
              "blind_holdout_non_regression": true,
              "judge_blind_non_regression": true,
              "judge_blind_agreement": true,
              "adversarial_non_regression": true,
              "adversarial_risk_ok": true,
              "route_confusion_clean": true,
              "family_stability": true
            },
            "route_metrics": {
              "precision": 1.0,
              "recall": 1.0,
              "average_margin": 0.805,
              "misroute_count": 0,
              "ambiguous_case_count": 0
            }
          },
          "registry": [
            {
              "name": "team-frontend-review",
              "role": "baseline",
              "label": "Baseline",
              "ranking_state": "reference",
              "promotion_state": "reference",
              "description": "Review frontend code for accessibility, risky UI security issues, missing states, and common UX regressions. Use when asked to review React, UI, frontend components, forms, a11y, or pre-merge frontend quality.",
              "tokens": 52,
              "dev_errors": 3,
              "holdout_errors": 0
            },
            {
              "name": "team-frontend-review",
              "role": "current",
              "label": "Current",
              "ranking_state": "selected_by_dev",
              "promotion_state": "kept_current",
              "description": "Review frontend code for accessibility, UI security, missing states, and UX regressions. Use when asked to review React components, run a pre-merge frontend review, or check a11y and unsafe rendering.",
              "tokens": 50,
              "dev_errors": 3,
              "holdout_errors": 0,
              "reason_tags": []
            },
            {
              "name": "team-frontend-review",
              "role": "candidate",
              "label": "Guardrail",
              "ranking_state": "not_selected",
              "promotion_state": "blocked",
              "description": "Review frontend code for accessibility, UI security, missing states, and UX regressions from React components, forms, frontend diffs, or UI code. Do not use for building a new page from scratch, backend-only review, or explaining frontend concepts.",
              "tokens": 62,
              "dev_errors": 3,
              "holdout_errors": 0,
              "reason_tags": [
                "longer_without_gain"
              ]
            },
            {
              "name": "team-frontend-review",
              "role": "candidate",
              "label": "Balanced",
              "ranking_state": "not_selected",
              "promotion_state": "blocked",
              "description": "Review frontend code for accessibility, UI security, missing states, and UX regressions from React components, forms, frontend diffs, or UI code. Use when asked to review React components, run a pre-merge frontend review, or check a11y and unsafe rendering.",
              "tokens": 64,
              "dev_errors": 3,
              "holdout_errors": 0,
              "reason_tags": [
                "longer_without_gain"
              ]
            },
            {
              "name": "team-frontend-review",
              "role": "candidate",
              "label": "Artifact Aware",
              "ranking_state": "not_selected",
              "promotion_state": "blocked",
              "description": "Review frontend code for accessibility, UI security, missing states, and UX regressions from React components, forms, frontend diffs, or UI code. Trigger when requests mention React components, forms, frontend diffs, or UI code and the job is to review React components, run a pre-merge frontend review, or check a11y and unsafe rendering.",
              "tokens": 84,
              "dev_errors": 3,
              "holdout_errors": 0,
              "reason_tags": [
                "longer_without_gain"
              ]
            },
            {
              "name": "team-frontend-review",
              "role": "candidate",
              "label": "Boundary",
              "ranking_state": "not_selected",
              "promotion_state": "blocked",
              "description": "Review frontend code for accessibility, UI security, missing states, and UX regressions from React components, forms, frontend diffs, or UI code. Use when asked to review React components, run a pre-merge frontend review, or check a11y and unsafe rendering. Do not use for building a new page from scratch, backend-only review, or explaining frontend concepts.",
              "tokens": 90,
              "dev_errors": 3,
              "holdout_errors": 0,
              "reason_tags": [
                "longer_without_gain"
              ]
            }
          ],
          "decision": "keep_current"
        },
        {
          "name": "governed-incident-command",
          "winner_label": "Current",
          "winner_description": "Build governed incident command packets. Use when asked to standardize incident review, run severity assessment, or assemble incident communication.",
          "winner_tokens": 37,
          "current_tokens": 37,
          "winner_holdout_fp": 0,
          "winner_holdout_fn": 1,
          "current_holdout_fp": 0,
          "current_holdout_fn": 1,
          "baseline_holdout_fp": 0,
          "baseline_holdout_fn": 2,
          "winner_blind_holdout_fp": 0,
          "winner_blind_holdout_fn": 0,
          "current_blind_holdout_fp": 0,
          "current_blind_holdout_fn": 0,
          "baseline_blind_holdout_fp": 0,
          "baseline_blind_holdout_fn": 1,
          "winner_blind_holdout_total_errors": 0,
          "winner_judge_blind_holdout_fp": 0,
          "winner_judge_blind_holdout_fn": 0,
          "current_judge_blind_holdout_fp": 0,
          "current_judge_blind_holdout_fn": 0,
          "baseline_judge_blind_holdout_fp": 0,
          "baseline_judge_blind_holdout_fn": 0,
          "winner_judge_blind_holdout_total_errors": 0,
          "winner_adversarial_holdout_fp": 0,
          "winner_adversarial_holdout_fn": 0,
          "current_adversarial_holdout_fp": 0,
          "current_adversarial_holdout_fn": 0,
          "baseline_adversarial_holdout_fp": 0,
          "baseline_adversarial_holdout_fn": 0,
          "winner_adversarial_holdout_total_errors": 0,
          "calibration": {
            "holdout": {
              "threshold": 0.48,
              "mean_positive_score": 0.37,
              "mean_non_trigger_score": 0.019,
              "mean_near_neighbor_score": 0.037,
              "min_positive_score": 0.08,
              "max_non_trigger_score": 0.057,
              "score_gap": 0.023,
              "threshold_margin": -0.4,
              "positive_threshold_buffer": -0.4,
              "negative_threshold_buffer": 0.423,
              "boundary_case_count": 0,
              "boundary_case_rate": 0.0,
              "risk_band": "overlap"
            },
            "blind_holdout": {
              "threshold": 0.48,
              "mean_positive_score": 0.902,
              "mean_non_trigger_score": 0.168,
              "mean_near_neighbor_score": 0.138,
              "min_positive_score": 0.804,
              "max_non_trigger_score": 0.386,
              "score_gap": 0.418,
              "threshold_margin": 0.094,
              "positive_threshold_buffer": 0.324,
              "negative_threshold_buffer": 0.094,
              "boundary_case_count": 1,
              "boundary_case_rate": 0.167,
              "risk_band": "healthy"
            },
            "adversarial_holdout": {
              "threshold": 0.34,
              "mean_positive_score": 0.827,
              "mean_non_trigger_score": 0.027,
              "mean_near_neighbor_score": 0.011,
              "min_positive_score": 0.654,
              "max_non_trigger_score": 0.056,
              "score_gap": 0.598,
              "threshold_margin": 0.284,
              "positive_threshold_buffer": 0.314,
              "negative_threshold_buffer": 0.284,
              "boundary_case_count": 0,
              "boundary_case_rate": 0.0,
              "risk_band": "healthy"
            }
          },
          "judge_blind": {
            "winner": {
              "agreement_rate": 1.0,
              "mean_confidence": 0.657,
              "rubric_version": "blind-v1"
            },
            "current": {
              "agreement_rate": 1.0,
              "mean_confidence": 0.657,
              "rubric_version": "blind-v1"
            },
            "baseline": {
              "agreement_rate": 1.0,
              "mean_confidence": 0.69,
              "rubric_version": "blind-v1"
            }
          },
          "family_health": {
            "holdout": {
              "family_count": 6,
              "clean_family_count": 5,
              "failing_families": [
                {
                  "family": "packet_assembly",
                  "errors": 1,
                  "pass_rate": 0.0
                }
              ],
              "weakest_family": {
                "family": "packet_assembly",
                "pass_rate": 0.0,
                "errors": 1
              }
            },
            "blind_holdout": {
              "family_count": 6,
              "clean_family_count": 6,
              "failing_families": [],
              "weakest_family": {
                "family": "blind_summary_only",
                "pass_rate": 1.0,
                "errors": 0
              }
            },
            "judge_blind_holdout": {
              "family_count": 6,
              "clean_family_count": 6,
              "failing_families": [],
              "weakest_family": {
                "family": "blind_summary_only",
                "pass_rate": 1.0,
                "errors": 0
              }
            },
            "adversarial_holdout": {
              "family_count": 6,
              "clean_family_count": 6,
              "failing_families": [],
              "weakest_family": {
                "family": "adversarial_single_update_collision",
                "pass_rate": 1.0,
                "errors": 0
              }
            }
          },
          "drift_note": "blind, judge-backed blind, adversarial, and calibration gates active",
          "ok": true,
          "promotion": {
            "decision": "keep_current",
            "winner_changed": false,
            "all_gates_pass": true,
            "route_clean": true,
            "judge_agreement_ok": true,
            "causes": [
              "no_candidate_outperformed_current",
              "current_holdout_gap_present",
              "current_holdout_risk"
            ],
            "next_action": "Keep the current description and open a new candidate only when fresh route evidence appears.",
            "gate_status": {
              "visible_holdout_non_regression": true,
              "blind_holdout_non_regression": true,
              "judge_blind_non_regression": true,
              "judge_blind_agreement": true,
              "adversarial_non_regression": true,
              "adversarial_risk_ok": true,
              "route_confusion_clean": true,
              "family_stability": true
            },
            "route_metrics": {
              "precision": 1.0,
              "recall": 1.0,
              "average_margin": 0.659,
              "misroute_count": 0,
              "ambiguous_case_count": 0
            }
          },
          "registry": [
            {
              "name": "governed-incident-command",
              "role": "baseline",
              "label": "Baseline",
              "ranking_state": "reference",
              "promotion_state": "reference",
              "description": "Build governed incident command packets from alerts, incident notes, transcripts, and stakeholder requirements. Use when asked to standardize incident review, severity assessment, incident communication, or incident packet assembly into one reusable operational skill. Do not use for generic debugging, one-off incident explanations, or brainstorming possible response ideas.",
              "tokens": 93,
              "dev_errors": 1,
              "holdout_errors": 2
            },
            {
              "name": "governed-incident-command",
              "role": "current",
              "label": "Current",
              "ranking_state": "selected_by_dev",
              "promotion_state": "kept_current",
              "description": "Build governed incident command packets. Use when asked to standardize incident review, run severity assessment, or assemble incident communication.",
              "tokens": 37,
              "dev_errors": 1,
              "holdout_errors": 1,
              "reason_tags": []
            },
            {
              "name": "governed-incident-command",
              "role": "candidate",
              "label": "Guardrail",
              "ranking_state": "not_selected",
              "promotion_state": "blocked",
              "description": "Build governed incident command packets from alerts, incident notes, transcripts, or stakeholder requirements. Do not use for generic debugging, one-off incident explanations, or drafting a single update.",
              "tokens": 51,
              "dev_errors": 1,
              "holdout_errors": 2,
              "reason_tags": [
                "visible_holdout_regression",
                "longer_without_gain"
              ]
            },
            {
              "name": "governed-incident-command",
              "role": "candidate",
              "label": "Balanced",
              "ranking_state": "not_selected",
              "promotion_state": "blocked",
              "description": "Build governed incident command packets from alerts, incident notes, transcripts, or stakeholder requirements. Use when asked to standardize incident review, run severity assessment, or assemble incident communication.",
              "tokens": 54,
              "dev_errors": 1,
              "holdout_errors": 1,
              "reason_tags": [
                "longer_without_gain"
              ]
            },
            {
              "name": "governed-incident-command",
              "role": "candidate",
              "label": "Boundary",
              "ranking_state": "not_selected",
              "promotion_state": "blocked",
              "description": "Build governed incident command packets from alerts, incident notes, transcripts, or stakeholder requirements. Use when asked to standardize incident review, run severity assessment, or assemble incident communication. Do not use for generic debugging, one-off incident explanations, or drafting a single update.",
              "tokens": 78,
              "dev_errors": 1,
              "holdout_errors": 1,
              "reason_tags": [
                "longer_without_gain"
              ]
            },
            {
              "name": "governed-incident-command",
              "role": "candidate",
              "label": "Artifact Aware",
              "ranking_state": "not_selected",
              "promotion_state": "blocked",
              "description": "Build governed incident command packets from alerts, incident notes, transcripts, or stakeholder requirements. Trigger when requests mention alerts, incident notes, transcripts, or stakeholder requirements and the job is to standardize incident review, run severity assessment, or assemble incident communication.",
              "tokens": 78,
              "dev_errors": 1,
              "holdout_errors": 1,
              "reason_tags": [
                "longer_without_gain"
              ]
            }
          ],
          "decision": "keep_current"
        }
      ]
    },
    "atlas": {
      "ok": true,
      "workspace_root": ".",
      "summary": {
        "skill_count": 12,
        "actionable_skill_count": 1,
        "route_collision_count": 5,
        "actionable_route_collision_count": 0,
        "owner_gap_count": 9,
        "actionable_owner_gap_count": 0,
        "stale_count": 10,
        "actionable_stale_count": 0,
        "shared_resource_count": 0,
        "no_route_opportunity_count": 0,
        "telemetry_report_count": 1,
        "drift_signal_count": 0,
        "actionable_drift_signal_count": 0,
        "non_actionable_issue_count": 24
      },
      "scope_policy": {
        "present": true,
        "path": "skill_atlas/policy.json",
        "schema_version": "1.0",
        "rules": [
          {
            "path_prefix": "examples/",
            "scope": "example",
            "actionable": false,
            "reason": "Generated examples and evolution snapshots are portfolio evidence, not release-actionable library skills for the root package."
          },
          {
            "path_prefix": "tests/fixtures/",
            "scope": "test-fixture",
            "actionable": false,
            "reason": "Fixtures intentionally include invalid or broken skills to verify validators and packagers."
          },
          {
            "path_prefix": "geo-ranking-article-generator",
            "scope": "embedded-generated-skill",
            "actionable": false,
            "reason": "This nested generated skill is retained as local evidence and should not gate the root Meta Skill release."
          }
        ]
      },
      "catalog": {
        "workspace_root": ".",
        "generated_at": "2026-06-13",
        "skills": [
          {
            "name": "yao-meta-skill",
            "path": ".",
            "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
            "owner": "Yao Team",
            "version": "1.1.0",
            "status": "active",
            "maturity": "governed",
            "updated_at": "2026-03-31",
            "review_cadence": "quarterly",
            "targets": [
              "openai",
              "claude",
              "generic",
              "agent-skills-compatible",
              "vscode"
            ],
            "resources": [
              "scripts/adjudicate_output_review.py",
              "scripts/build_confusion_matrix.py",
              "scripts/build_skill_atlas.py",
              "scripts/check_update.py",
              "scripts/ci_test.py",
              "scripts/collect_feedback.py",
              "scripts/compile_skill.py",
              "scripts/context_sizer.py",
              "scripts/create_iteration_snapshot.py",
              "scripts/cross_packager.py",
              "scripts/diff_eval.py",
              "scripts/emit_telemetry_event.py",
              "scripts/export_skill_ir.py",
              "scripts/github_benchmark_scan.py",
              "scripts/governance_check.py",
              "scripts/html_rendering.py",
              "scripts/import_telemetry_events.py",
              "scripts/init_skill.py",
              "scripts/judge_blind_eval.py",
              "scripts/lint_skill.py",
              "scripts/local_output_eval_runner.py",
              "scripts/optimize_description.py",
              "scripts/prepare_output_review_kit.py",
              "scripts/prepare_world_class_submission_kit.py",
              "scripts/probe_runtime_permissions.py",
              "scripts/promotion_checker.py",
              "scripts/propose_adaptation.py",
              "scripts/provider_output_eval_runner.py",
              "scripts/python_compat_check.py",
              "scripts/registry_audit.py",
              "scripts/render_adoption_drift_report.py",
              "scripts/render_architecture_maintainability.py",
              "scripts/render_artifact_design_profile.py",
              "scripts/render_baseline_compare.py",
              "scripts/render_benchmark_reproducibility.py",
              "scripts/render_context_reports.py",
              "scripts/render_description_drift_history.py",
              "scripts/render_eval_dashboard.py",
              "scripts/render_intent_confidence.py",
              "scripts/render_intent_dialogue.py",
              "scripts/render_iteration_directions.py",
              "scripts/render_iteration_ledger.py",
              "scripts/render_output_risk_profile.py",
              "scripts/render_portability_report.py",
              "scripts/render_prompt_quality_profile.py",
              "scripts/render_reference_scan.py",
              "scripts/render_reference_synthesis.py",
              "scripts/render_regression_history.py",
              "scripts/render_review_annotations.py",
              "scripts/render_review_studio.py",
              "scripts/render_review_viewer.py",
              "scripts/render_review_waivers.py",
              "scripts/render_skill_interpretation.py",
              "scripts/render_skill_os2_audit.py",
              "scripts/render_skill_os2_coverage.py",
              "scripts/render_skill_overview.py",
              "scripts/render_social_preview.py",
              "scripts/render_system_model.py",
              "scripts/render_telemetry_hook_recipes.py",
              "scripts/render_world_class_claim_guard.py",
              "scripts/render_world_class_evidence_intake.py",
              "scripts/render_world_class_evidence_ledger.py",
              "scripts/render_world_class_evidence_plan.py",
              "scripts/render_world_class_operator_runbook.py",
              "scripts/render_world_class_submission_review.py",
              "scripts/resource_boundary_check.py",
              "scripts/review_studio_action_evidence.py",
              "scripts/review_studio_actions.py",
              "scripts/review_studio_data.py",
              "scripts/review_studio_formatting.py",
              "scripts/review_studio_gates.py",
              "scripts/review_studio_layout.py",
              "scripts/review_studio_output_review.py",
              "scripts/review_studio_waivers.py",
              "scripts/review_studio_world_class.py",
              "scripts/review_viewer_data.py",
              "scripts/run_conformance_suite.py",
              "scripts/run_description_optimization_suite.py",
              "scripts/run_eval_suite.py",
              "scripts/run_output_eval.py",
              "scripts/run_output_execution.py",
              "scripts/simulate_install.py",
              "scripts/skill_report_charts.py",
              "scripts/skill_report_i18n.py",
              "scripts/skill_report_layout.py",
              "scripts/skill_report_metrics.py",
              "scripts/skill_report_model.py",
              "scripts/skill_report_world_class.py",
              "scripts/summarize_user_signals.py",
              "scripts/sync_local_install.py",
              "scripts/telemetry_native_host.py",
              "scripts/trigger_eval.py",
              "scripts/trust_check.py",
              "scripts/upgrade_check.py",
              "scripts/validate_skill.py",
              "scripts/verify_package.py",
              "scripts/world_class_evidence_contract.py",
              "scripts/world_class_source_checks.py",
              "scripts/yao.py",
              "scripts/yao_cli_adaptation_commands.py",
              "scripts/yao_cli_config.py",
              "scripts/yao_cli_create_commands.py",
              "scripts/yao_cli_parser.py",
              "scripts/yao_cli_report_commands.py",
              "scripts/yao_cli_runtime.py",
              "scripts/yao_cli_telemetry.py",
              "references/artifact-design-doctrine.md",
              "references/authoring-discipline.md",
              "references/autonomous-adaptation.md",
              "references/distribution-registry-method.md",
              "references/eval-playbook.md",
              "references/gate-selection.md",
              "references/governance.md",
              "references/human-review-template.md",
              "references/intent-dialogue.md",
              "references/iteration-philosophy.md",
              "references/non-skill-decision-tree.md",
              "references/operating-modes.md",
              "references/output-eval-method.md",
              "references/output-quality-risk.md",
              "references/output-visual-quality.md",
              "references/packaging-contracts.md",
              "references/pattern-extraction-doctrine.md",
              "references/platform-capability-matrix.md",
              "references/prompt-engineering-doctrine.md",
              "references/qa-ladder.md",
              "references/reference-scan.md",
              "references/regression-cause-taxonomy.md",
              "references/resource-boundaries.md",
              "references/review-studio-method.md",
              "references/review-waiver-method.md",
              "references/runtime-conformance-method.md",
              "references/skill-archetypes.md",
              "references/skill-atlas-method.md",
              "references/skill-engineering-method.md",
              "references/skill-ir-method.md",
              "references/systems-thinking-doctrine.md",
              "references/telemetry-drift-method.md",
              "references/trust-security-method.md",
              "references/user-memory-policy.md",
              "templates/basic_skill.md.j2",
              "templates/complex_skill.md.j2"
            ],
            "token_set": [
              "add",
              "asked",
              "docs",
              "evals",
              "evaluate",
              "existing",
              "improve",
              "notes",
              "or",
              "package",
              "process",
              "prompts",
              "refactor",
              "repeated",
              "reuse",
              "team",
              "transcripts",
              "workflows"
            ],
            "atlas_scope": "release",
            "actionable": true,
            "scope_reason": "default release-actionable skill",
            "telemetry": {
              "report_present": true,
              "report": "reports/adoption_drift_report.json",
              "risk_band": "low",
              "event_count": 1,
              "adoption_sample_count": 1,
              "adoption_rate": 100.0,
              "candidate_count": 0
            }
          },
          {
            "name": "release-orchestrator",
            "path": "examples/complex-release-orchestrator/generated-skill",
            "description": "Coordinate software release preparation, rollout readiness, migration notes, rollback planning, stakeholder communication, and final go/no-go release packets. Use when asked to prepare a release packet, review release readiness, or turn scattered launch notes into one reusable release workflow. Do not use for generic project planning, one-off announcement drafting, or high-level release theory.",
            "owner": "Yao Team",
            "version": "1.0.0",
            "status": "active",
            "maturity": "production",
            "updated_at": "2026-03-31",
            "review_cadence": "quarterly",
            "targets": [],
            "resources": [
              "scripts/build_release_packet.py",
              "references/migration-template.md",
              "references/release-checklist.md",
              "references/risk-matrix.md",
              "references/stakeholder-comms.md"
            ],
            "token_set": [
              "announcement",
              "asked",
              "communication",
              "coordinate",
              "do",
              "drafting",
              "final",
              "generic",
              "go",
              "high-level",
              "launch",
              "migration",
              "no-go",
              "not",
              "notes",
              "one",
              "one-off",
              "or",
              "packet",
              "packets",
              "planning",
              "preparation",
              "prepare",
              "project",
              "readiness",
              "release",
              "review",
              "rollback",
              "rollout",
              "scattered",
              "software",
              "stakeholder",
              "theory",
              "workflow"
            ],
            "atlas_scope": "example",
            "actionable": false,
            "scope_reason": "Generated examples and evolution snapshots are portfolio evidence, not release-actionable library skills for the root package.",
            "telemetry": {
              "report_present": false,
              "report": "examples/complex-release-orchestrator/generated-skill/reports/adoption_drift_report.json",
              "risk_band": "missing",
              "event_count": 0,
              "adoption_sample_count": 0,
              "adoption_rate": 0,
              "candidate_count": 0
            }
          },
          {
            "name": "frontend-review",
            "path": "examples/evolution-frontend-review/final",
            "description": "Review frontend code for accessibility, risky UI security issues, missing states, and common UX regressions. Use when asked to review React, UI, frontend components, forms, a11y, or pre-merge frontend quality.",
            "owner": "",
            "version": "",
            "status": "",
            "maturity": "",
            "updated_at": "",
            "review_cadence": "",
            "targets": [],
            "resources": [],
            "token_set": [
              "a11y",
              "accessibility",
              "asked",
              "code",
              "common",
              "components",
              "forms",
              "frontend",
              "issues",
              "missing",
              "or",
              "pre-merge",
              "quality",
              "react",
              "regressions",
              "review",
              "risky",
              "security",
              "states",
              "ui",
              "ux"
            ],
            "atlas_scope": "example",
            "actionable": false,
            "scope_reason": "Generated examples and evolution snapshots are portfolio evidence, not release-actionable library skills for the root package.",
            "telemetry": {
              "report_present": false,
              "report": "examples/evolution-frontend-review/final/reports/adoption_drift_report.json",
              "risk_band": "missing",
              "event_count": 0,
              "adoption_sample_count": 0,
              "adoption_rate": 0,
              "candidate_count": 0
            }
          },
          {
            "name": "frontend-review",
            "path": "examples/evolution-frontend-review/v0",
            "description": "Review frontend code before merge.",
            "owner": "",
            "version": "",
            "status": "",
            "maturity": "",
            "updated_at": "",
            "review_cadence": "",
            "targets": [],
            "resources": [],
            "token_set": [
              "before",
              "code",
              "frontend",
              "merge",
              "review"
            ],
            "atlas_scope": "example",
            "actionable": false,
            "scope_reason": "Generated examples and evolution snapshots are portfolio evidence, not release-actionable library skills for the root package.",
            "telemetry": {
              "report_present": false,
              "report": "examples/evolution-frontend-review/v0/reports/adoption_drift_report.json",
              "risk_band": "missing",
              "event_count": 0,
              "adoption_sample_count": 0,
              "adoption_rate": 0,
              "candidate_count": 0
            }
          },
          {
            "name": "frontend-review",
            "path": "examples/evolution-frontend-review/v1",
            "description": "Review frontend code for accessibility, risky UI security issues, missing loading and error states, and pre-merge regressions. Use when asked to review React, UI, forms, frontend components, or merge-readiness for the frontend.",
            "owner": "",
            "version": "",
            "status": "",
            "maturity": "",
            "updated_at": "",
            "review_cadence": "",
            "targets": [],
            "resources": [],
            "token_set": [
              "accessibility",
              "asked",
              "code",
              "components",
              "error",
              "forms",
              "frontend",
              "issues",
              "loading",
              "merge-readiness",
              "missing",
              "or",
              "pre-merge",
              "react",
              "regressions",
              "review",
              "risky",
              "security",
              "states",
              "ui"
            ],
            "atlas_scope": "example",
            "actionable": false,
            "scope_reason": "Generated examples and evolution snapshots are portfolio evidence, not release-actionable library skills for the root package.",
            "telemetry": {
              "report_present": false,
              "report": "examples/evolution-frontend-review/v1/reports/adoption_drift_report.json",
              "risk_band": "missing",
              "event_count": 0,
              "adoption_sample_count": 0,
              "adoption_rate": 0,
              "candidate_count": 0
            }
          },
          {
            "name": "incident-command-governor",
            "path": "examples/governed-incident-command/generated-skill",
            "description": "Build governed incident command packets. Use when asked to standardize incident review, run severity assessment, or assemble incident communication.",
            "owner": "Incident Operations Team",
            "version": "1.0.0",
            "status": "active",
            "maturity": "governed",
            "updated_at": "2026-03-31",
            "review_cadence": "monthly",
            "targets": [
              "openai",
              "claude",
              "generic"
            ],
            "resources": [
              "scripts/build_incident_packet.py",
              "references/comms-policy.md",
              "references/review-policy.md",
              "references/severity-matrix.md"
            ],
            "token_set": [
              "asked",
              "assemble",
              "assessment",
              "build",
              "command",
              "communication",
              "governed",
              "incident",
              "or",
              "packets",
              "review",
              "run",
              "severity",
              "standardize"
            ],
            "atlas_scope": "example",
            "actionable": false,
            "scope_reason": "Generated examples and evolution snapshots are portfolio evidence, not release-actionable library skills for the root package.",
            "telemetry": {
              "report_present": false,
              "report": "examples/governed-incident-command/generated-skill/reports/adoption_drift_report.json",
              "risk_band": "missing",
              "event_count": 0,
              "adoption_sample_count": 0,
              "adoption_rate": 0,
              "candidate_count": 0
            }
          },
          {
            "name": "note-cleanup",
            "path": "examples/simple-note-cleanup/generated-skill",
            "description": "Clean messy meeting notes into structured markdown summaries. Use when asked to organize meeting notes, extract action items, separate decisions from open questions, or turn rough notes into a clean recap.",
            "owner": "",
            "version": "",
            "status": "",
            "maturity": "",
            "updated_at": "",
            "review_cadence": "",
            "targets": [],
            "resources": [],
            "token_set": [
              "action",
              "asked",
              "clean",
              "decisions",
              "extract",
              "items",
              "markdown",
              "meeting",
              "messy",
              "notes",
              "open",
              "or",
              "organize",
              "questions",
              "recap",
              "rough",
              "separate",
              "structured",
              "summaries"
            ],
            "atlas_scope": "example",
            "actionable": false,
            "scope_reason": "Generated examples and evolution snapshots are portfolio evidence, not release-actionable library skills for the root package.",
            "telemetry": {
              "report_present": false,
              "report": "examples/simple-note-cleanup/generated-skill/reports/adoption_drift_report.json",
              "risk_band": "missing",
              "event_count": 0,
              "adoption_sample_count": 0,
              "adoption_rate": 0,
              "candidate_count": 0
            }
          },
          {
            "name": "frontend-review",
            "path": "examples/team-frontend-review/generated-skill",
            "description": "Review frontend code for accessibility, UI security, missing states, and UX regressions. Use when asked to review React components, run a pre-merge frontend review, or check a11y and unsafe rendering.",
            "owner": "",
            "version": "",
            "status": "",
            "maturity": "",
            "updated_at": "",
            "review_cadence": "",
            "targets": [],
            "resources": [
              "references/checklist.md"
            ],
            "token_set": [
              "a11y",
              "accessibility",
              "asked",
              "check",
              "code",
              "components",
              "frontend",
              "missing",
              "or",
              "pre-merge",
              "react",
              "regressions",
              "rendering",
              "review",
              "run",
              "security",
              "states",
              "ui",
              "unsafe",
              "ux"
            ],
            "atlas_scope": "example",
            "actionable": false,
            "scope_reason": "Generated examples and evolution snapshots are portfolio evidence, not release-actionable library skills for the root package.",
            "telemetry": {
              "report_present": false,
              "report": "examples/team-frontend-review/generated-skill/reports/adoption_drift_report.json",
              "risk_band": "missing",
              "event_count": 0,
              "adoption_sample_count": 0,
              "adoption_rate": 0,
              "candidate_count": 0
            }
          },
          {
            "name": "geo-ranking-article-generator",
            "path": "geo-ranking-article-generator",
            "description": "Create GEO ranking-article packs from brand briefs. Use when asked to research a brand, find GEO or 生成式引擎优化 keywords and five competitors, generate timely titles, write five ~2000-character articles, and save them to a fixed knowledge-base folder with an HTML index. Do not use for generic SEO advice, one-off copy, or writing without competitor research.",
            "owner": "",
            "version": "",
            "status": "",
            "maturity": "",
            "updated_at": "",
            "review_cadence": "",
            "targets": [],
            "resources": [
              "scripts/build_html_index.py",
              "references/article-blueprint.md",
              "references/feishu-benchmark-patterns.md",
              "references/geo-research-playbook.md",
              "templates/brand-brief-template.md"
            ],
            "token_set": [
              "2000-character",
              "advice",
              "articles",
              "asked",
              "brand",
              "briefs",
              "competitor",
              "competitors",
              "copy",
              "do",
              "find",
              "five",
              "fixed",
              "folder",
              "generate",
              "generic",
              "geo",
              "html",
              "index",
              "keywords",
              "knowledge-base",
              "not",
              "one-off",
              "or",
              "packs",
              "ranking-article",
              "research",
              "save",
              "seo",
              "them",
              "timely",
              "titles",
              "without",
              "write",
              "writing",
              "生成式引擎优化"
            ],
            "atlas_scope": "embedded-generated-skill",
            "actionable": false,
            "scope_reason": "This nested generated skill is retained as local evidence and should not gate the root Meta Skill release.",
            "telemetry": {
              "report_present": false,
              "report": "geo-ranking-article-generator/reports/adoption_drift_report.json",
              "risk_band": "missing",
              "event_count": 0,
              "adoption_sample_count": 0,
              "adoption_rate": 0,
              "candidate_count": 0
            }
          },
          {
            "name": "invalid-governance-skill",
            "path": "tests/fixtures/governance_invalid_manifest",
            "description": "Test fixture for governance validation.",
            "owner": "",
            "version": "1.0.0",
            "status": "frozen",
            "maturity": "governed",
            "updated_at": "2026/03/31",
            "review_cadence": "",
            "targets": [],
            "resources": [],
            "token_set": [
              "fixture",
              "governance",
              "test",
              "validation"
            ],
            "atlas_scope": "test-fixture",
            "actionable": false,
            "scope_reason": "Fixtures intentionally include invalid or broken skills to verify validators and packagers.",
            "telemetry": {
              "report_present": false,
              "report": "tests/fixtures/governance_invalid_manifest/reports/adoption_drift_report.json",
              "risk_band": "missing",
              "event_count": 0,
              "adoption_sample_count": 0,
              "adoption_rate": 0,
              "candidate_count": 0
            }
          },
          {
            "name": "broken-yaml-skill",
            "path": "tests/fixtures/package_invalid_yaml",
            "description": "Broken YAML fixture for packager failure testing.",
            "owner": "",
            "version": "",
            "status": "",
            "maturity": "",
            "updated_at": "",
            "review_cadence": "",
            "targets": [],
            "resources": [],
            "token_set": [
              "broken",
              "failure",
              "fixture",
              "packager",
              "testing",
              "yaml"
            ],
            "atlas_scope": "test-fixture",
            "actionable": false,
            "scope_reason": "Fixtures intentionally include invalid or broken skills to verify validators and packagers.",
            "telemetry": {
              "report_present": false,
              "report": "tests/fixtures/package_invalid_yaml/reports/adoption_drift_report.json",
              "risk_band": "missing",
              "event_count": 0,
              "adoption_sample_count": 0,
              "adoption_rate": 0,
              "candidate_count": 0
            }
          },
          {
            "name": "broken-skill",
            "path": "tests/fixtures/package_missing_interface_field",
            "description": "Broken fixture for packager failure testing.",
            "owner": "",
            "version": "",
            "status": "",
            "maturity": "",
            "updated_at": "",
            "review_cadence": "",
            "targets": [],
            "resources": [],
            "token_set": [
              "broken",
              "failure",
              "fixture",
              "packager",
              "testing"
            ],
            "atlas_scope": "test-fixture",
            "actionable": false,
            "scope_reason": "Fixtures intentionally include invalid or broken skills to verify validators and packagers.",
            "telemetry": {
              "report_present": false,
              "report": "tests/fixtures/package_missing_interface_field/reports/adoption_drift_report.json",
              "risk_band": "missing",
              "event_count": 0,
              "adoption_sample_count": 0,
              "adoption_rate": 0,
              "candidate_count": 0
            }
          }
        ],
        "summary": {
          "skill_count": 12,
          "actionable_skill_count": 1,
          "route_collision_count": 5,
          "actionable_route_collision_count": 0,
          "owner_gap_count": 9,
          "actionable_owner_gap_count": 0,
          "stale_count": 10,
          "actionable_stale_count": 0,
          "shared_resource_count": 0,
          "no_route_opportunity_count": 0,
          "telemetry_report_count": 1,
          "drift_signal_count": 0,
          "actionable_drift_signal_count": 0,
          "non_actionable_issue_count": 24
        }
      },
      "route_collisions": [
        {
          "skill_a": "frontend-review",
          "skill_b": "frontend-review",
          "path_a": "examples/evolution-frontend-review/final",
          "path_b": "examples/evolution-frontend-review/v1",
          "score": 0.708,
          "status": "collision",
          "actionable": false,
          "scope_a": "example",
          "scope_b": "example"
        },
        {
          "skill_a": "frontend-review",
          "skill_b": "frontend-review",
          "path_a": "examples/evolution-frontend-review/final",
          "path_b": "examples/team-frontend-review/generated-skill",
          "score": 0.64,
          "status": "collision",
          "actionable": false,
          "scope_a": "example",
          "scope_b": "example"
        },
        {
          "skill_a": "frontend-review",
          "skill_b": "frontend-review",
          "path_a": "examples/evolution-frontend-review/v1",
          "path_b": "examples/team-frontend-review/generated-skill",
          "score": 0.538,
          "status": "collision",
          "actionable": false,
          "scope_a": "example",
          "scope_b": "example"
        },
        {
          "skill_a": "broken-yaml-skill",
          "skill_b": "broken-skill",
          "path_a": "tests/fixtures/package_invalid_yaml",
          "path_b": "tests/fixtures/package_missing_interface_field",
          "score": 0.833,
          "status": "collision",
          "actionable": false,
          "scope_a": "test-fixture",
          "scope_b": "test-fixture"
        },
        {
          "skill_a": "frontend-review",
          "skill_b": "frontend-review",
          "path_a": "examples/evolution-frontend-review/final",
          "path_b": "examples/evolution-frontend-review/v0",
          "score": 1.0,
          "status": "duplicate-name",
          "actionable": false,
          "scope_a": "example",
          "scope_b": "example"
        }
      ],
      "actionable_route_collisions": [],
      "dependency_graph": {
        "nodes": [
          {
            "name": "yao-meta-skill",
            "path": "."
          },
          {
            "name": "release-orchestrator",
            "path": "examples/complex-release-orchestrator/generated-skill"
          },
          {
            "name": "frontend-review",
            "path": "examples/evolution-frontend-review/final"
          },
          {
            "name": "frontend-review",
            "path": "examples/evolution-frontend-review/v0"
          },
          {
            "name": "frontend-review",
            "path": "examples/evolution-frontend-review/v1"
          },
          {
            "name": "incident-command-governor",
            "path": "examples/governed-incident-command/generated-skill"
          },
          {
            "name": "note-cleanup",
            "path": "examples/simple-note-cleanup/generated-skill"
          },
          {
            "name": "frontend-review",
            "path": "examples/team-frontend-review/generated-skill"
          },
          {
            "name": "geo-ranking-article-generator",
            "path": "geo-ranking-article-generator"
          },
          {
            "name": "invalid-governance-skill",
            "path": "tests/fixtures/governance_invalid_manifest"
          },
          {
            "name": "broken-yaml-skill",
            "path": "tests/fixtures/package_invalid_yaml"
          },
          {
            "name": "broken-skill",
            "path": "tests/fixtures/package_missing_interface_field"
          }
        ],
        "shared_resources": []
      },
      "stale_skills": [
        {
          "name": "frontend-review",
          "path": "examples/evolution-frontend-review/final",
          "reason": "missing updated_at",
          "actionable": false,
          "scope": "example"
        },
        {
          "name": "frontend-review",
          "path": "examples/evolution-frontend-review/v0",
          "reason": "missing updated_at",
          "actionable": false,
          "scope": "example"
        },
        {
          "name": "frontend-review",
          "path": "examples/evolution-frontend-review/v1",
          "reason": "missing updated_at",
          "actionable": false,
          "scope": "example"
        },
        {
          "name": "incident-command-governor",
          "path": "examples/governed-incident-command/generated-skill",
          "reason": "review overdue by cadence monthly",
          "age_days": 74,
          "allowed_days": 31,
          "actionable": false,
          "scope": "example"
        },
        {
          "name": "note-cleanup",
          "path": "examples/simple-note-cleanup/generated-skill",
          "reason": "missing updated_at",
          "actionable": false,
          "scope": "example"
        },
        {
          "name": "frontend-review",
          "path": "examples/team-frontend-review/generated-skill",
          "reason": "missing updated_at",
          "actionable": false,
          "scope": "example"
        },
        {
          "name": "geo-ranking-article-generator",
          "path": "geo-ranking-article-generator",
          "reason": "missing updated_at",
          "actionable": false,
          "scope": "embedded-generated-skill"
        },
        {
          "name": "invalid-governance-skill",
          "path": "tests/fixtures/governance_invalid_manifest",
          "reason": "missing updated_at",
          "actionable": false,
          "scope": "test-fixture"
        },
        {
          "name": "broken-yaml-skill",
          "path": "tests/fixtures/package_invalid_yaml",
          "reason": "missing updated_at",
          "actionable": false,
          "scope": "test-fixture"
        },
        {
          "name": "broken-skill",
          "path": "tests/fixtures/package_missing_interface_field",
          "reason": "missing updated_at",
          "actionable": false,
          "scope": "test-fixture"
        }
      ],
      "actionable_stale_skills": [],
      "owner_review_gaps": [
        {
          "name": "frontend-review",
          "path": "examples/evolution-frontend-review/final",
          "missing": [
            "owner",
            "review_cadence",
            "maturity"
          ],
          "actionable": false,
          "scope": "example"
        },
        {
          "name": "frontend-review",
          "path": "examples/evolution-frontend-review/v0",
          "missing": [
            "owner",
            "review_cadence",
            "maturity"
          ],
          "actionable": false,
          "scope": "example"
        },
        {
          "name": "frontend-review",
          "path": "examples/evolution-frontend-review/v1",
          "missing": [
            "owner",
            "review_cadence",
            "maturity"
          ],
          "actionable": false,
          "scope": "example"
        },
        {
          "name": "note-cleanup",
          "path": "examples/simple-note-cleanup/generated-skill",
          "missing": [
            "owner",
            "review_cadence",
            "maturity"
          ],
          "actionable": false,
          "scope": "example"
        },
        {
          "name": "frontend-review",
          "path": "examples/team-frontend-review/generated-skill",
          "missing": [
            "owner",
            "review_cadence",
            "maturity"
          ],
          "actionable": false,
          "scope": "example"
        },
        {
          "name": "geo-ranking-article-generator",
          "path": "geo-ranking-article-generator",
          "missing": [
            "owner",
            "review_cadence",
            "maturity"
          ],
          "actionable": false,
          "scope": "embedded-generated-skill"
        },
        {
          "name": "invalid-governance-skill",
          "path": "tests/fixtures/governance_invalid_manifest",
          "missing": [
            "owner",
            "review_cadence"
          ],
          "actionable": false,
          "scope": "test-fixture"
        },
        {
          "name": "broken-yaml-skill",
          "path": "tests/fixtures/package_invalid_yaml",
          "missing": [
            "owner",
            "review_cadence",
            "maturity"
          ],
          "actionable": false,
          "scope": "test-fixture"
        },
        {
          "name": "broken-skill",
          "path": "tests/fixtures/package_missing_interface_field",
          "missing": [
            "owner",
            "review_cadence",
            "maturity"
          ],
          "actionable": false,
          "scope": "test-fixture"
        }
      ],
      "actionable_owner_review_gaps": [],
      "drift_signals": [],
      "actionable_drift_signals": [],
      "no_route_opportunities": [],
      "artifacts": {
        "catalog": "skill_atlas/catalog.json",
        "route_overlap_matrix": "skill_atlas/route_overlap_matrix.csv",
        "dependency_graph": "skill_atlas/dependency_graph.json",
        "stale_skills": "skill_atlas/stale_skills.json",
        "owner_review_gaps": "skill_atlas/owner_review_gaps.json",
        "drift_signals": "skill_atlas/drift_signals.json",
        "no_route_opportunities": "skill_atlas/no_route_opportunities.json",
        "report_json": "reports/skill_atlas.json",
        "report_html": "reports/skill_atlas.html"
      }
    },
    "adoption_drift": {
      "ok": true,
      "schema_version": "2.0",
      "generated_at": "2026-06-15T13:28:42Z",
      "skill_dir": ".",
      "privacy_contract": {
        "storage": "local-first",
        "event_scope": "metadata-only",
        "raw_content_allowed": false,
        "raw_event_log_packaged": false,
        "blocked_fields": [
          "content",
          "input",
          "inputs",
          "message",
          "messages",
          "note",
          "output",
          "outputs",
          "prompt",
          "raw",
          "text",
          "transcript"
        ]
      },
      "summary": {
        "event_count": 1,
        "adoption_sample_count": 1,
        "activation_count": 1,
        "accepted_count": 1,
        "edited_count": 0,
        "rejected_count": 0,
        "missed_count": 0,
        "failed_count": 0,
        "adoption_rate": 100.0,
        "missed_trigger_count": 0,
        "wrong_trigger_count": 0,
        "bad_output_count": 0,
        "script_error_count": 0,
        "missing_resource_count": 0,
        "review_overdue_count": 0,
        "risk_band": "low",
        "event_types": {
          "skill_activation": 1
        },
        "failure_types": {},
        "source_types": {
          "manual": 1
        },
        "command_counts": {}
      },
      "adoption_by_skill": [
        {
          "skill": "yao-meta-skill",
          "events": 1,
          "adoption_events": 1,
          "accepted": 1,
          "edited": 0,
          "rejected": 0,
          "missed": 0,
          "adoption_rate": 100.0
        }
      ],
      "next_iteration_candidates": [],
      "recent_events": [
        {
          "command": "unknown",
          "event": "skill_activation",
          "skill": "yao-meta-skill",
          "source": "manual",
          "version": "1.1.0",
          "activation_type": "explicit",
          "outcome": "accepted",
          "failure_type": "none",
          "timestamp": "2026-06-13T10:00:00Z"
        }
      ],
      "failures": [],
      "artifacts": {
        "events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl",
        "json": "reports/adoption_drift_report.json",
        "markdown": "reports/adoption_drift_report.md"
      }
    },
    "review_waivers": {
      "schema_version": "1.0",
      "ok": true,
      "skill_dir": ".",
      "generated_at": "2026-06-13",
      "summary": {
        "waiver_count": 0,
        "active_count": 0,
        "expired_count": 0,
        "invalid_count": 0,
        "covered_gate_count": 0,
        "covered_gate_keys": [],
        "waiver_candidate_count": 2,
        "waiverable_open_count": 1,
        "non_waivable_count": 1
      },
      "policy": {
        "blocker_waivers_allowed": false,
        "minimum_reason_chars": 20,
        "expires_required": true,
        "known_gate_keys": [
          "context-budget",
          "intent-canvas",
          "operations-loop",
          "output-lab",
          "permission-gates",
          "permission-runtime",
          "registry-audit",
          "release-notes",
          "runtime-matrix",
          "skill-atlas",
          "trigger-lab",
          "trust-report"
        ]
      },
      "waivers": [],
      "waiver_candidates": [
        {
          "gate_key": "output-lab",
          "label": "Output Lab",
          "status": "needs-reviewer-decision",
          "waiver_allowed": true,
          "decision_options": [
            "accepted-risk",
            "false-positive",
            "temporary-exception"
          ],
          "risk_summary": "review pending 5; model-executed 0; output failures 0",
          "required_review": [
            "Reviewer confirms this release does not claim provider-backed or human-adjudicated output superiority.",
            "Reviewer names the release scope and expiry date.",
            "Reviewer links output_review_adjudication or output_execution evidence."
          ],
          "suggested_evidence": "reports/output_review_adjudication.md",
          "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"<reviewer>\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md",
          "world_class_boundary": "Does not count as provider, human, or public world-class completion evidence."
        },
        {
          "gate_key": "world-class-evidence",
          "label": "World-Class Evidence",
          "status": "cannot-waive",
          "waiver_allowed": false,
          "risk_summary": "4 pending evidence entries; 1 human pending; 3 external pending",
          "required_review": [
            "Do not use a waiver to claim public world-class readiness.",
            "Either submit accepted ledger evidence or state that this release does not claim world-class completion.",
            "Keep claim guard active until ledger summary.ready_to_claim_world_class is true."
          ],
          "suggested_evidence": "reports/world_class_evidence_ledger.md",
          "suggested_command": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-claim-guard .",
          "world_class_boundary": "Non-waivable completion boundary."
        }
      ],
      "failures": [],
      "warnings": [],
      "artifacts": {
        "json": "reports/review_waivers.json",
        "markdown": "reports/review_waivers.md"
      }
    },
    "review_annotations": {
      "schema_version": "1.0",
      "ok": true,
      "skill_dir": ".",
      "source": "tests/tmp_review_studio/empty_review_annotations_input.json",
      "summary": {
        "annotation_count": 0,
        "open_count": 0,
        "resolved_count": 0,
        "deferred_count": 0,
        "open_blocker_count": 0,
        "open_warning_count": 0,
        "linked_gate_count": 0,
        "target_missing_count": 0,
        "failure_count": 0
      },
      "annotations": [],
      "failures": [],
      "template_written": false,
      "artifacts": {
        "json": "reports/review_annotations.json",
        "markdown": "reports/review_annotations.md"
      }
    },
    "world_class_evidence_ledger": {
      "schema_version": "1.0",
      "ok": true,
      "generated_at": "2026-06-13",
      "skill_dir": ".",
      "summary": {
        "ledger_entry_count": 4,
        "source_accepted_count": 0,
        "accepted_count": 0,
        "pending_count": 4,
        "human_pending_count": 1,
        "external_pending_count": 3,
        "submitted_entry_count": 0,
        "missing_submission_count": 4,
        "invalid_submission_count": 0,
        "source_check_count": 13,
        "source_pass_count": 7,
        "source_blocked_count": 6,
        "submitted_but_pending_count": 0,
        "source_accepted_without_valid_submission_count": 0,
        "overclaim_guard_active": true,
        "ready_to_claim_world_class": false,
        "decision": "evidence-pending"
      },
      "entries": [
        {
          "key": "provider-holdout",
          "label": "Provider Holdout",
          "category": "external",
          "owner": "operator with provider credentials",
          "status": "pending",
          "source_status": "external_required",
          "source_accepted": false,
          "current": "model-executed 0; token-observed 0",
          "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
          "runbook": [
            "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
            "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
            "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
            "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
          ],
          "provenance_requirements": [
            "provider-backed model run",
            "observed timing",
            "observed token metadata"
          ],
          "success_checks": [
            "reports/output_execution_runs.json summary.model_executed_count > 0",
            "reports/output_execution_runs.json summary.timing_observed_count > 0",
            "reports/output_execution_runs.json summary.token_observed_count > 0",
            "reports/skill_os2_audit.json item provider-holdout status becomes pass"
          ],
          "evidence_artifacts": [
            "reports/output_execution_runs.json",
            "reports/output_execution_runs.md",
            "reports/skill_os2_audit.json",
            "evidence/world_class/intake.schema.json",
            "evidence/world_class/templates/provider-holdout.intake.json",
            "reports/world_class_evidence_intake.json",
            "reports/world_class_evidence_intake.md"
          ],
          "privacy_contract": [
            "Do not commit provider credentials or environment dumps.",
            "The output execution report records output hashes and aggregate run metadata, not raw provider prompts."
          ],
          "observed_state": {
            "model_executed_count": 0,
            "timing_observed_count": 10,
            "token_observed_count": 0,
            "accepted": false
          },
          "source_checklist": [
            {
              "evidence_key": "provider-holdout",
              "label": "Provider model run",
              "field": "model_executed_count",
              "expected": ">0",
              "actual": 0,
              "status": "blocked",
              "source_accepted": false,
              "next_action": "Run provider-backed output-exec with real credentials."
            },
            {
              "evidence_key": "provider-holdout",
              "label": "Timing observed",
              "field": "timing_observed_count",
              "expected": ">0",
              "actual": 10,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Provider execution should record timing metadata."
            },
            {
              "evidence_key": "provider-holdout",
              "label": "Token usage observed",
              "field": "token_observed_count",
              "expected": ">0",
              "actual": 0,
              "status": "blocked",
              "source_accepted": false,
              "next_action": "Provider execution should return non-estimated token usage."
            }
          ],
          "source_check_count": 3,
          "source_pass_count": 1,
          "source_blocked_count": 2,
          "submission_state": {
            "status": "missing",
            "path": "evidence/world_class/submissions/provider-holdout.json",
            "artifact_ref_count": 0,
            "attested_real_evidence": false,
            "privacy_contract_satisfied": false,
            "ledger_counts_as_completion": false
          },
          "anti_overclaim": {
            "planned_work_counts_as_evidence": false,
            "metadata_fallback_counts_as_native_enforcement": false,
            "pending_review_counts_as_human_decision": false,
            "local_command_runner_counts_as_provider_model": false
          },
          "next_action": "Run provider-backed holdout cases with real credentials and commit only aggregate evidence."
        },
        {
          "key": "human-adjudication",
          "label": "Human Adjudication",
          "category": "human",
          "owner": "human reviewer",
          "status": "pending",
          "source_status": "human_required",
          "source_accepted": false,
          "current": "0/5 decisions; pending 5",
          "objective": "Record real blind A/B reviewer decisions before claiming human output review completion.",
          "runbook": [
            "python3 scripts/yao.py output-review-kit --write-template",
            "Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.",
            "python3 scripts/adjudicate_output_review.py --write-template",
            "Edit reports/output_review_decisions.json with winner_variant values and reviewer metadata.",
            "python3 scripts/yao.py output-review",
            "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
            "Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.",
            "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
          ],
          "provenance_requirements": [
            "real reviewer identity",
            "blind A/B decisions",
            "answer key unopened until decisions exist"
          ],
          "success_checks": [
            "reports/output_review_adjudication.json summary.pending_count == 0",
            "reports/output_review_adjudication.json summary.judgment_count == summary.pair_count",
            "reports/output_review_adjudication.json summary.invalid_decision_count == 0",
            "reports/skill_os2_audit.json item human-adjudication status becomes pass"
          ],
          "evidence_artifacts": [
            "reports/output_blind_review_pack.md",
            "reports/output_review_kit.md",
            "reports/output_review_decisions.json",
            "reports/output_review_adjudication.json",
            "reports/output_review_adjudication.md",
            "evidence/world_class/intake.schema.json",
            "evidence/world_class/templates/human-adjudication.intake.json",
            "reports/world_class_evidence_intake.json",
            "reports/world_class_evidence_intake.md"
          ],
          "privacy_contract": [
            "Reviewer decisions should not include raw user data or private customer detail.",
            "Keep the answer key separate until after decisions are recorded."
          ],
          "observed_state": {
            "pair_count": 5,
            "judgment_count": 0,
            "pending_count": 5,
            "invalid_decision_count": 0,
            "answer_revealed_count": 0,
            "accepted": false
          },
          "source_checklist": [
            {
              "evidence_key": "human-adjudication",
              "label": "Review pairs exist",
              "field": "pair_count",
              "expected": ">0",
              "actual": 5,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Generate the blind A/B review pack."
            },
            {
              "evidence_key": "human-adjudication",
              "label": "No pending decisions",
              "field": "pending_count",
              "expected": "==0",
              "actual": 5,
              "status": "blocked",
              "source_accepted": false,
              "next_action": "Record a reviewer choice for every pair."
            },
            {
              "evidence_key": "human-adjudication",
              "label": "Judgments complete",
              "field": "judgment_count",
              "expected": "==pair_count",
              "actual": 0,
              "status": "blocked",
              "source_accepted": false,
              "next_action": "Every pair needs one valid human judgment."
            },
            {
              "evidence_key": "human-adjudication",
              "label": "No invalid decisions",
              "field": "invalid_decision_count",
              "expected": "==0",
              "actual": 0,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Fix malformed winner/confidence entries."
            }
          ],
          "source_check_count": 4,
          "source_pass_count": 2,
          "source_blocked_count": 2,
          "submission_state": {
            "status": "missing",
            "path": "evidence/world_class/submissions/human-adjudication.json",
            "artifact_ref_count": 0,
            "attested_real_evidence": false,
            "privacy_contract_satisfied": false,
            "ledger_counts_as_completion": false
          },
          "anti_overclaim": {
            "planned_work_counts_as_evidence": false,
            "metadata_fallback_counts_as_native_enforcement": false,
            "pending_review_counts_as_human_decision": false,
            "local_command_runner_counts_as_provider_model": false
          },
          "next_action": "Record real A/B choices in the decision template, then regenerate adjudication."
        },
        {
          "key": "native-permission-enforcement",
          "label": "Native Permission Enforcement",
          "category": "external",
          "owner": "target client or installer integrator",
          "status": "pending",
          "source_status": "external_required",
          "source_accepted": false,
          "current": "native-enforced targets 0; installer-enforced targets 4",
          "objective": "Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.",
          "runbook": [
            "Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.",
            "Update the generated target adapter only when the guard is actually enforced by that target.",
            "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip",
            "python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation",
            "python3 scripts/yao.py runtime-permissions . --package-dir dist",
            "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
            "Copy evidence/world_class/templates/native-permission-enforcement.intake.json to evidence/world_class/submissions/native-permission-enforcement.json and fill only real evidence fields.",
            "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
          ],
          "provenance_requirements": [
            "real target client or external installer runtime guard",
            "native enforcement flag or externally accepted guard proof",
            "residual risk retained for fallback targets"
          ],
          "success_checks": [
            "reports/runtime_permission_probes.json summary.native_enforcement_count > 0",
            "reports/runtime_permission_probes.json summary.failure_count == 0",
            "reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence",
            "reports/skill_os2_audit.json item native-permission-enforcement status becomes pass"
          ],
          "evidence_artifacts": [
            "dist/targets/*/adapter.json",
            "reports/runtime_permission_probes.json",
            "reports/runtime_permission_probes.md",
            "reports/install_simulation.json",
            "reports/install_simulation.md",
            "security/permission_policy.json",
            "evidence/world_class/intake.schema.json",
            "evidence/world_class/templates/native-permission-enforcement.intake.json",
            "reports/world_class_evidence_intake.json",
            "reports/world_class_evidence_intake.md"
          ],
          "privacy_contract": [
            "Do not mark native_enforcement true for metadata-only fallbacks.",
            "Keep residual risks visible for targets that still rely on operator enforcement."
          ],
          "observed_state": {
            "native_enforcement_count": 0,
            "metadata_fallback_count": 4,
            "installer_enforcement_pass_count": 4,
            "installer_permission_failure_count": 0,
            "installer_enforcement_ready": true,
            "residual_risk_count": 4,
            "failure_count": 0,
            "accepted": false
          },
          "source_checklist": [
            {
              "evidence_key": "native-permission-enforcement",
              "label": "Native enforcement",
              "field": "native_enforcement_count",
              "expected": ">0",
              "actual": 0,
              "status": "blocked",
              "source_accepted": false,
              "next_action": "Collect real target-client or external runtime guard proof."
            },
            {
              "evidence_key": "native-permission-enforcement",
              "label": "Probe failures",
              "field": "failure_count",
              "expected": "==0",
              "actual": 0,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Runtime permission probes must stay clean."
            },
            {
              "evidence_key": "native-permission-enforcement",
              "label": "Installer support",
              "field": "installer_enforcement_ready",
              "expected": "true",
              "actual": true,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Installer enforcement is supporting evidence, not native proof."
            }
          ],
          "source_check_count": 3,
          "source_pass_count": 2,
          "source_blocked_count": 1,
          "submission_state": {
            "status": "missing",
            "path": "evidence/world_class/submissions/native-permission-enforcement.json",
            "artifact_ref_count": 0,
            "attested_real_evidence": false,
            "privacy_contract_satisfied": false,
            "ledger_counts_as_completion": false
          },
          "anti_overclaim": {
            "planned_work_counts_as_evidence": false,
            "metadata_fallback_counts_as_native_enforcement": false,
            "pending_review_counts_as_human_decision": false,
            "local_command_runner_counts_as_provider_model": false
          },
          "next_action": "Integrate a real target-client or external installer runtime guard before claiming native permission enforcement."
        },
        {
          "key": "native-client-telemetry",
          "label": "Native Client Telemetry",
          "category": "external",
          "owner": "Browser/Chrome/IDE/provider client integrator",
          "status": "pending",
          "source_status": "external_required",
          "source_accepted": false,
          "current": "external source events 0; adoption samples 1",
          "objective": "Import production metadata-only events from a real external client into the local drift loop.",
          "runbook": [
            "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
            "Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.",
            "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl",
            "python3 scripts/yao.py skill-atlas --workspace-root .",
            "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
            "Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.",
            "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
          ],
          "provenance_requirements": [
            "real external client source",
            "metadata-only event",
            "local-first import path"
          ],
          "success_checks": [
            "reports/adoption_drift_report.json summary.source_types.external > 0",
            "reports/adoption_drift_report.json summary.adoption_sample_count > 0",
            "reports/skill_os2_audit.json item native-client-telemetry status becomes pass"
          ],
          "evidence_artifacts": [
            "reports/adoption_drift_report.json",
            "reports/adoption_drift_report.md",
            "reports/telemetry_hook_recipes.json",
            "scripts/telemetry_native_host.py",
            "evidence/world_class/intake.schema.json",
            "evidence/world_class/templates/native-client-telemetry.intake.json",
            "reports/world_class_evidence_intake.json",
            "reports/world_class_evidence_intake.md"
          ],
          "privacy_contract": [
            "Telemetry must remain metadata-only and local-first.",
            "Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field."
          ],
          "observed_state": {
            "external_source_events": 0,
            "adoption_sample_count": 1,
            "raw_content_allowed": false,
            "risk_band": "low",
            "accepted": false
          },
          "source_checklist": [
            {
              "evidence_key": "native-client-telemetry",
              "label": "External events",
              "field": "external_source_events",
              "expected": ">0",
              "actual": 0,
              "status": "blocked",
              "source_accepted": false,
              "next_action": "Import at least one metadata-only event from a real client."
            },
            {
              "evidence_key": "native-client-telemetry",
              "label": "Adoption sample",
              "field": "adoption_sample_count",
              "expected": ">0",
              "actual": 1,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Telemetry must include adoption outcome evidence."
            },
            {
              "evidence_key": "native-client-telemetry",
              "label": "Raw content blocked",
              "field": "raw_content_allowed",
              "expected": "false",
              "actual": false,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Telemetry must stay metadata-only."
            }
          ],
          "source_check_count": 3,
          "source_pass_count": 2,
          "source_blocked_count": 1,
          "submission_state": {
            "status": "missing",
            "path": "evidence/world_class/submissions/native-client-telemetry.json",
            "artifact_ref_count": 0,
            "attested_real_evidence": false,
            "privacy_contract_satisfied": false,
            "ledger_counts_as_completion": false
          },
          "anti_overclaim": {
            "planned_work_counts_as_evidence": false,
            "metadata_fallback_counts_as_native_enforcement": false,
            "pending_review_counts_as_human_decision": false,
            "local_command_runner_counts_as_provider_model": false
          },
          "next_action": "Install a real client against the native host and import production metadata-only events."
        }
      ],
      "source_plan": {
        "json": "reports/world_class_evidence_plan.json",
        "markdown": "reports/world_class_evidence_plan.md",
        "task_count": 4,
        "evidence_requirement_count": 4
      },
      "submissions": {
        "directory": "evidence/world_class/submissions",
        "ledger_counts_submission_as_completion": false,
        "source_pass_requires_valid_submission": true
      },
      "artifacts": {
        "json": "reports/world_class_evidence_ledger.json",
        "markdown": "reports/world_class_evidence_ledger.md",
        "intake": "reports/world_class_evidence_intake.md"
      }
    },
    "world_class_evidence_intake": {
      "schema_version": "1.0",
      "ok": true,
      "generated_at": "2026-06-13",
      "skill_dir": ".",
      "summary": {
        "schema_present": true,
        "ledger_entry_count": 4,
        "template_count": 4,
        "template_pass_count": 4,
        "submission_count": 0,
        "valid_submission_count": 0,
        "invalid_submission_count": 0,
        "operator_checklist_count": 4,
        "operator_checklist_ready_count": 0,
        "valid_packet_source_incomplete_count": 0,
        "ready_for_external_collection": true,
        "ready_for_ledger_review": false,
        "ready_to_claim_world_class": false,
        "overclaim_guard_active": true,
        "decision": "awaiting-submissions"
      },
      "schema": "evidence/world_class/intake.schema.json",
      "templates": [
        {
          "path": "evidence/world_class/templates/provider-holdout.intake.json",
          "evidence_key": "provider-holdout",
          "status": "pass",
          "template_only": true,
          "artifact_integrity": {
            "artifact_ref_count": 1,
            "artifact_existing_count": 0,
            "artifact_sha256_verified_count": 0,
            "required_artifact_count": 0,
            "required_artifact_verified_count": 0
          },
          "errors": []
        },
        {
          "path": "evidence/world_class/templates/human-adjudication.intake.json",
          "evidence_key": "human-adjudication",
          "status": "pass",
          "template_only": true,
          "artifact_integrity": {
            "artifact_ref_count": 2,
            "artifact_existing_count": 0,
            "artifact_sha256_verified_count": 0,
            "required_artifact_count": 0,
            "required_artifact_verified_count": 0
          },
          "errors": []
        },
        {
          "path": "evidence/world_class/templates/native-permission-enforcement.intake.json",
          "evidence_key": "native-permission-enforcement",
          "status": "pass",
          "template_only": true,
          "artifact_integrity": {
            "artifact_ref_count": 3,
            "artifact_existing_count": 0,
            "artifact_sha256_verified_count": 0,
            "required_artifact_count": 0,
            "required_artifact_verified_count": 0
          },
          "errors": []
        },
        {
          "path": "evidence/world_class/templates/native-client-telemetry.intake.json",
          "evidence_key": "native-client-telemetry",
          "status": "pass",
          "template_only": true,
          "artifact_integrity": {
            "artifact_ref_count": 2,
            "artifact_existing_count": 0,
            "artifact_sha256_verified_count": 0,
            "required_artifact_count": 0,
            "required_artifact_verified_count": 0
          },
          "errors": []
        }
      ],
      "submissions": [],
      "operator_checklist": [
        {
          "evidence_key": "provider-holdout",
          "label": "Provider Holdout",
          "category": "external",
          "owner": "operator with provider credentials",
          "readiness": "awaiting-submission",
          "blocking_reason": "No real evidence submission has been provided yet.",
          "template_status": "pass",
          "submission_status": "missing",
          "source_accepted": false,
          "observed_state": {
            "model_executed_count": 0,
            "timing_observed_count": 10,
            "token_observed_count": 0,
            "accepted": false
          },
          "template_path": "evidence/world_class/templates/provider-holdout.intake.json",
          "submission_path": "evidence/world_class/submissions/provider-holdout.json",
          "commands": {
            "prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions",
            "validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
            "submission_review": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",
            "refresh_ledger": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions",
            "guard_claim": "python3 scripts/yao.py world-class-claim-guard ."
          },
          "must_collect": {
            "provenance_requirements": [
              "provider-backed model run",
              "observed timing",
              "observed token metadata"
            ],
            "runbook": [
              "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
              "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
              "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
              "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
            ],
            "success_checks": [
              "reports/output_execution_runs.json summary.model_executed_count > 0",
              "reports/output_execution_runs.json summary.timing_observed_count > 0",
              "reports/output_execution_runs.json summary.token_observed_count > 0",
              "reports/skill_os2_audit.json item provider-holdout status becomes pass"
            ],
            "evidence_artifacts": [
              "reports/output_execution_runs.json",
              "reports/output_execution_runs.md",
              "reports/skill_os2_audit.json",
              "evidence/world_class/intake.schema.json",
              "evidence/world_class/templates/provider-holdout.intake.json",
              "reports/world_class_evidence_intake.json",
              "reports/world_class_evidence_intake.md"
            ],
            "privacy_contract": [
              "Do not commit provider credentials or environment dumps.",
              "The output execution report records output hashes and aggregate run metadata, not raw provider prompts."
            ]
          },
          "anti_overclaim": {
            "planned_work_counts_as_evidence": false,
            "metadata_fallback_counts_as_native_enforcement": false,
            "pending_review_counts_as_human_decision": false,
            "local_command_runner_counts_as_provider_model": false
          },
          "next_action": "Run provider-backed holdout cases with real credentials and commit only aggregate evidence."
        },
        {
          "evidence_key": "human-adjudication",
          "label": "Human Adjudication",
          "category": "human",
          "owner": "human reviewer",
          "readiness": "awaiting-submission",
          "blocking_reason": "No real evidence submission has been provided yet.",
          "template_status": "pass",
          "submission_status": "missing",
          "source_accepted": false,
          "observed_state": {
            "pair_count": 5,
            "judgment_count": 0,
            "pending_count": 5,
            "invalid_decision_count": 0,
            "answer_revealed_count": 0,
            "accepted": false
          },
          "template_path": "evidence/world_class/templates/human-adjudication.intake.json",
          "submission_path": "evidence/world_class/submissions/human-adjudication.json",
          "commands": {
            "prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions",
            "validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
            "submission_review": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",
            "refresh_ledger": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions",
            "guard_claim": "python3 scripts/yao.py world-class-claim-guard ."
          },
          "must_collect": {
            "provenance_requirements": [
              "real reviewer identity",
              "blind A/B decisions",
              "answer key unopened until decisions exist"
            ],
            "runbook": [
              "python3 scripts/yao.py output-review-kit --write-template",
              "Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.",
              "python3 scripts/adjudicate_output_review.py --write-template",
              "Edit reports/output_review_decisions.json with winner_variant values and reviewer metadata.",
              "python3 scripts/yao.py output-review",
              "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
              "Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.",
              "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
            ],
            "success_checks": [
              "reports/output_review_adjudication.json summary.pending_count == 0",
              "reports/output_review_adjudication.json summary.judgment_count == summary.pair_count",
              "reports/output_review_adjudication.json summary.invalid_decision_count == 0",
              "reports/skill_os2_audit.json item human-adjudication status becomes pass"
            ],
            "evidence_artifacts": [
              "reports/output_blind_review_pack.md",
              "reports/output_review_kit.md",
              "reports/output_review_decisions.json",
              "reports/output_review_adjudication.json",
              "reports/output_review_adjudication.md",
              "evidence/world_class/intake.schema.json",
              "evidence/world_class/templates/human-adjudication.intake.json",
              "reports/world_class_evidence_intake.json",
              "reports/world_class_evidence_intake.md"
            ],
            "privacy_contract": [
              "Reviewer decisions should not include raw user data or private customer detail.",
              "Keep the answer key separate until after decisions are recorded."
            ]
          },
          "anti_overclaim": {
            "planned_work_counts_as_evidence": false,
            "metadata_fallback_counts_as_native_enforcement": false,
            "pending_review_counts_as_human_decision": false,
            "local_command_runner_counts_as_provider_model": false
          },
          "next_action": "Record real A/B choices in the decision template, then regenerate adjudication."
        },
        {
          "evidence_key": "native-permission-enforcement",
          "label": "Native Permission Enforcement",
          "category": "external",
          "owner": "target client or installer integrator",
          "readiness": "awaiting-submission",
          "blocking_reason": "No real evidence submission has been provided yet.",
          "template_status": "pass",
          "submission_status": "missing",
          "source_accepted": false,
          "observed_state": {
            "native_enforcement_count": 0,
            "metadata_fallback_count": 4,
            "installer_enforcement_pass_count": 4,
            "installer_permission_failure_count": 0,
            "installer_enforcement_ready": true,
            "residual_risk_count": 4,
            "failure_count": 0,
            "accepted": false
          },
          "template_path": "evidence/world_class/templates/native-permission-enforcement.intake.json",
          "submission_path": "evidence/world_class/submissions/native-permission-enforcement.json",
          "commands": {
            "prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions",
            "validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
            "submission_review": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",
            "refresh_ledger": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions",
            "guard_claim": "python3 scripts/yao.py world-class-claim-guard ."
          },
          "must_collect": {
            "provenance_requirements": [
              "real target client or external installer runtime guard",
              "native enforcement flag or externally accepted guard proof",
              "residual risk retained for fallback targets"
            ],
            "runbook": [
              "Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.",
              "Update the generated target adapter only when the guard is actually enforced by that target.",
              "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip",
              "python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation",
              "python3 scripts/yao.py runtime-permissions . --package-dir dist",
              "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
              "Copy evidence/world_class/templates/native-permission-enforcement.intake.json to evidence/world_class/submissions/native-permission-enforcement.json and fill only real evidence fields.",
              "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
            ],
            "success_checks": [
              "reports/runtime_permission_probes.json summary.native_enforcement_count > 0",
              "reports/runtime_permission_probes.json summary.failure_count == 0",
              "reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence",
              "reports/skill_os2_audit.json item native-permission-enforcement status becomes pass"
            ],
            "evidence_artifacts": [
              "dist/targets/*/adapter.json",
              "reports/runtime_permission_probes.json",
              "reports/runtime_permission_probes.md",
              "reports/install_simulation.json",
              "reports/install_simulation.md",
              "security/permission_policy.json",
              "evidence/world_class/intake.schema.json",
              "evidence/world_class/templates/native-permission-enforcement.intake.json",
              "reports/world_class_evidence_intake.json",
              "reports/world_class_evidence_intake.md"
            ],
            "privacy_contract": [
              "Do not mark native_enforcement true for metadata-only fallbacks.",
              "Keep residual risks visible for targets that still rely on operator enforcement."
            ]
          },
          "anti_overclaim": {
            "planned_work_counts_as_evidence": false,
            "metadata_fallback_counts_as_native_enforcement": false,
            "pending_review_counts_as_human_decision": false,
            "local_command_runner_counts_as_provider_model": false
          },
          "next_action": "Integrate a real target-client or external installer runtime guard before claiming native permission enforcement."
        },
        {
          "evidence_key": "native-client-telemetry",
          "label": "Native Client Telemetry",
          "category": "external",
          "owner": "Browser/Chrome/IDE/provider client integrator",
          "readiness": "awaiting-submission",
          "blocking_reason": "No real evidence submission has been provided yet.",
          "template_status": "pass",
          "submission_status": "missing",
          "source_accepted": false,
          "observed_state": {
            "external_source_events": 0,
            "adoption_sample_count": 1,
            "raw_content_allowed": false,
            "risk_band": "low",
            "accepted": false
          },
          "template_path": "evidence/world_class/templates/native-client-telemetry.intake.json",
          "submission_path": "evidence/world_class/submissions/native-client-telemetry.json",
          "commands": {
            "prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions",
            "validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
            "submission_review": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",
            "refresh_ledger": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions",
            "guard_claim": "python3 scripts/yao.py world-class-claim-guard ."
          },
          "must_collect": {
            "provenance_requirements": [
              "real external client source",
              "metadata-only event",
              "local-first import path"
            ],
            "runbook": [
              "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
              "Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.",
              "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl",
              "python3 scripts/yao.py skill-atlas --workspace-root .",
              "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
              "Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.",
              "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
            ],
            "success_checks": [
              "reports/adoption_drift_report.json summary.source_types.external > 0",
              "reports/adoption_drift_report.json summary.adoption_sample_count > 0",
              "reports/skill_os2_audit.json item native-client-telemetry status becomes pass"
            ],
            "evidence_artifacts": [
              "reports/adoption_drift_report.json",
              "reports/adoption_drift_report.md",
              "reports/telemetry_hook_recipes.json",
              "scripts/telemetry_native_host.py",
              "evidence/world_class/intake.schema.json",
              "evidence/world_class/templates/native-client-telemetry.intake.json",
              "reports/world_class_evidence_intake.json",
              "reports/world_class_evidence_intake.md"
            ],
            "privacy_contract": [
              "Telemetry must remain metadata-only and local-first.",
              "Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field."
            ]
          },
          "anti_overclaim": {
            "planned_work_counts_as_evidence": false,
            "metadata_fallback_counts_as_native_enforcement": false,
            "pending_review_counts_as_human_decision": false,
            "local_command_runner_counts_as_provider_model": false
          },
          "next_action": "Install a real client against the native host and import production metadata-only events."
        }
      ],
      "source_ledger": {
        "json": "reports/world_class_evidence_ledger.json",
        "markdown": "reports/world_class_evidence_ledger.md",
        "pending_count": 4
      },
      "artifacts": {
        "json": "reports/world_class_evidence_intake.json",
        "markdown": "reports/world_class_evidence_intake.md"
      }
    },
    "world_class_submission_review": {
      "schema_version": "1.0",
      "ok": true,
      "generated_at": "2026-06-13",
      "skill_dir": ".",
      "summary": {
        "review_item_count": 4,
        "accepted_count": 0,
        "awaiting_submission_count": 4,
        "valid_packet_source_incomplete_count": 0,
        "ready_for_ledger_review_count": 0,
        "fix_submission_count": 0,
        "unmatched_submission_count": 0,
        "invalid_submission_count": 0,
        "source_check_count": 13,
        "source_pass_count": 7,
        "source_blocked_count": 6,
        "ready_to_claim_world_class": false,
        "review_counts_submission_as_completion": false,
        "decision": "awaiting-submissions"
      },
      "submissions": {
        "directory": "evidence/world_class/submissions",
        "review_counts_submission_as_completion": false
      },
      "items": [
        {
          "evidence_key": "provider-holdout",
          "label": "Provider Holdout",
          "category": "external",
          "owner": "operator with provider credentials",
          "ledger_status": "pending",
          "submission_status": "missing",
          "intake_status": "missing",
          "source_accepted": false,
          "review_state": "awaiting-submission",
          "blocking_reason": "No evidence packet has been submitted for review.",
          "submission_path": "evidence/world_class/submissions/provider-holdout.json",
          "submitted_by": "",
          "submitted_at": "",
          "artifact_ref_count": 0,
          "intake_errors": [],
          "observed_state": {
            "model_executed_count": 0,
            "timing_observed_count": 10,
            "token_observed_count": 0,
            "accepted": false
          },
          "source_checklist": [
            {
              "evidence_key": "provider-holdout",
              "label": "Provider model run",
              "field": "model_executed_count",
              "expected": ">0",
              "actual": 0,
              "status": "blocked",
              "source_accepted": false,
              "next_action": "Run provider-backed output-exec with real credentials."
            },
            {
              "evidence_key": "provider-holdout",
              "label": "Timing observed",
              "field": "timing_observed_count",
              "expected": ">0",
              "actual": 10,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Provider execution should record timing metadata."
            },
            {
              "evidence_key": "provider-holdout",
              "label": "Token usage observed",
              "field": "token_observed_count",
              "expected": ">0",
              "actual": 0,
              "status": "blocked",
              "source_accepted": false,
              "next_action": "Provider execution should return non-estimated token usage."
            }
          ],
          "source_check_count": 3,
          "source_pass_count": 1,
          "source_blocked_count": 2,
          "success_checks": [
            "reports/output_execution_runs.json summary.model_executed_count > 0",
            "reports/output_execution_runs.json summary.timing_observed_count > 0",
            "reports/output_execution_runs.json summary.token_observed_count > 0",
            "reports/skill_os2_audit.json item provider-holdout status becomes pass"
          ],
          "privacy_contract": [
            "Do not commit provider credentials or environment dumps.",
            "The output execution report records output hashes and aggregate run metadata, not raw provider prompts."
          ],
          "next_action": "Run provider-backed holdout cases with real credentials and commit only aggregate evidence."
        },
        {
          "evidence_key": "human-adjudication",
          "label": "Human Adjudication",
          "category": "human",
          "owner": "human reviewer",
          "ledger_status": "pending",
          "submission_status": "missing",
          "intake_status": "missing",
          "source_accepted": false,
          "review_state": "awaiting-submission",
          "blocking_reason": "No evidence packet has been submitted for review.",
          "submission_path": "evidence/world_class/submissions/human-adjudication.json",
          "submitted_by": "",
          "submitted_at": "",
          "artifact_ref_count": 0,
          "intake_errors": [],
          "observed_state": {
            "pair_count": 5,
            "judgment_count": 0,
            "pending_count": 5,
            "invalid_decision_count": 0,
            "answer_revealed_count": 0,
            "accepted": false
          },
          "source_checklist": [
            {
              "evidence_key": "human-adjudication",
              "label": "Review pairs exist",
              "field": "pair_count",
              "expected": ">0",
              "actual": 5,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Generate the blind A/B review pack."
            },
            {
              "evidence_key": "human-adjudication",
              "label": "No pending decisions",
              "field": "pending_count",
              "expected": "==0",
              "actual": 5,
              "status": "blocked",
              "source_accepted": false,
              "next_action": "Record a reviewer choice for every pair."
            },
            {
              "evidence_key": "human-adjudication",
              "label": "Judgments complete",
              "field": "judgment_count",
              "expected": "==pair_count",
              "actual": 0,
              "status": "blocked",
              "source_accepted": false,
              "next_action": "Every pair needs one valid human judgment."
            },
            {
              "evidence_key": "human-adjudication",
              "label": "No invalid decisions",
              "field": "invalid_decision_count",
              "expected": "==0",
              "actual": 0,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Fix malformed winner/confidence entries."
            }
          ],
          "source_check_count": 4,
          "source_pass_count": 2,
          "source_blocked_count": 2,
          "success_checks": [
            "reports/output_review_adjudication.json summary.pending_count == 0",
            "reports/output_review_adjudication.json summary.judgment_count == summary.pair_count",
            "reports/output_review_adjudication.json summary.invalid_decision_count == 0",
            "reports/skill_os2_audit.json item human-adjudication status becomes pass"
          ],
          "privacy_contract": [
            "Reviewer decisions should not include raw user data or private customer detail.",
            "Keep the answer key separate until after decisions are recorded."
          ],
          "next_action": "Record real A/B choices in the decision template, then regenerate adjudication."
        },
        {
          "evidence_key": "native-permission-enforcement",
          "label": "Native Permission Enforcement",
          "category": "external",
          "owner": "target client or installer integrator",
          "ledger_status": "pending",
          "submission_status": "missing",
          "intake_status": "missing",
          "source_accepted": false,
          "review_state": "awaiting-submission",
          "blocking_reason": "No evidence packet has been submitted for review.",
          "submission_path": "evidence/world_class/submissions/native-permission-enforcement.json",
          "submitted_by": "",
          "submitted_at": "",
          "artifact_ref_count": 0,
          "intake_errors": [],
          "observed_state": {
            "native_enforcement_count": 0,
            "metadata_fallback_count": 4,
            "installer_enforcement_pass_count": 4,
            "installer_permission_failure_count": 0,
            "installer_enforcement_ready": true,
            "residual_risk_count": 4,
            "failure_count": 0,
            "accepted": false
          },
          "source_checklist": [
            {
              "evidence_key": "native-permission-enforcement",
              "label": "Native enforcement",
              "field": "native_enforcement_count",
              "expected": ">0",
              "actual": 0,
              "status": "blocked",
              "source_accepted": false,
              "next_action": "Collect real target-client or external runtime guard proof."
            },
            {
              "evidence_key": "native-permission-enforcement",
              "label": "Probe failures",
              "field": "failure_count",
              "expected": "==0",
              "actual": 0,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Runtime permission probes must stay clean."
            },
            {
              "evidence_key": "native-permission-enforcement",
              "label": "Installer support",
              "field": "installer_enforcement_ready",
              "expected": "true",
              "actual": true,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Installer enforcement is supporting evidence, not native proof."
            }
          ],
          "source_check_count": 3,
          "source_pass_count": 2,
          "source_blocked_count": 1,
          "success_checks": [
            "reports/runtime_permission_probes.json summary.native_enforcement_count > 0",
            "reports/runtime_permission_probes.json summary.failure_count == 0",
            "reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence",
            "reports/skill_os2_audit.json item native-permission-enforcement status becomes pass"
          ],
          "privacy_contract": [
            "Do not mark native_enforcement true for metadata-only fallbacks.",
            "Keep residual risks visible for targets that still rely on operator enforcement."
          ],
          "next_action": "Integrate a real target-client or external installer runtime guard before claiming native permission enforcement."
        },
        {
          "evidence_key": "native-client-telemetry",
          "label": "Native Client Telemetry",
          "category": "external",
          "owner": "Browser/Chrome/IDE/provider client integrator",
          "ledger_status": "pending",
          "submission_status": "missing",
          "intake_status": "missing",
          "source_accepted": false,
          "review_state": "awaiting-submission",
          "blocking_reason": "No evidence packet has been submitted for review.",
          "submission_path": "evidence/world_class/submissions/native-client-telemetry.json",
          "submitted_by": "",
          "submitted_at": "",
          "artifact_ref_count": 0,
          "intake_errors": [],
          "observed_state": {
            "external_source_events": 0,
            "adoption_sample_count": 1,
            "raw_content_allowed": false,
            "risk_band": "low",
            "accepted": false
          },
          "source_checklist": [
            {
              "evidence_key": "native-client-telemetry",
              "label": "External events",
              "field": "external_source_events",
              "expected": ">0",
              "actual": 0,
              "status": "blocked",
              "source_accepted": false,
              "next_action": "Import at least one metadata-only event from a real client."
            },
            {
              "evidence_key": "native-client-telemetry",
              "label": "Adoption sample",
              "field": "adoption_sample_count",
              "expected": ">0",
              "actual": 1,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Telemetry must include adoption outcome evidence."
            },
            {
              "evidence_key": "native-client-telemetry",
              "label": "Raw content blocked",
              "field": "raw_content_allowed",
              "expected": "false",
              "actual": false,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Telemetry must stay metadata-only."
            }
          ],
          "source_check_count": 3,
          "source_pass_count": 2,
          "source_blocked_count": 1,
          "success_checks": [
            "reports/adoption_drift_report.json summary.source_types.external > 0",
            "reports/adoption_drift_report.json summary.adoption_sample_count > 0",
            "reports/skill_os2_audit.json item native-client-telemetry status becomes pass"
          ],
          "privacy_contract": [
            "Telemetry must remain metadata-only and local-first.",
            "Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field."
          ],
          "next_action": "Install a real client against the native host and import production metadata-only events."
        }
      ],
      "unmatched_submissions": [],
      "source_reports": {
        "ledger": "reports/world_class_evidence_ledger.json",
        "intake": "reports/world_class_evidence_intake.json"
      },
      "artifacts": {
        "json": "reports/world_class_submission_review.json",
        "markdown": "reports/world_class_submission_review.md"
      }
    },
    "world_class_operator_runbook": {
      "schema_version": "1.0",
      "ok": true,
      "generated_at": "2026-06-13",
      "skill_dir": ".",
      "summary": {
        "evidence_item_count": 4,
        "pending_count": 4,
        "accepted_count": 0,
        "awaiting_submission_count": 4,
        "ready_for_ledger_review_count": 0,
        "valid_packet_source_incomplete_count": 0,
        "invalid_submission_count": 0,
        "source_check_count": 13,
        "source_pass_count": 7,
        "source_blocked_count": 6,
        "ready_to_claim_world_class": false,
        "runbook_counts_as_completion": false,
        "decision": "collect-evidence"
      },
      "submissions": {
        "directory": "evidence/world_class/submissions",
        "runbook_counts_submission_as_completion": false
      },
      "items": [
        {
          "evidence_key": "provider-holdout",
          "label": "Provider Holdout",
          "category": "external",
          "owner": "operator with provider credentials",
          "ledger_status": "pending",
          "intake_readiness": "awaiting-submission",
          "review_state": "awaiting-submission",
          "source_accepted": false,
          "objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
          "current": "model-executed 0; token-observed 0",
          "execution_runbook": [
            "YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
            "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
            "Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
            "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
          ],
          "blocking_reason": "No evidence packet has been submitted for review.",
          "submission_path": "evidence/world_class/submissions/provider-holdout.json",
          "template_path": "evidence/world_class/templates/provider-holdout.intake.json",
          "commands": {
            "prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions",
            "validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
            "review_queue": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",
            "refresh_ledger": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions",
            "guard_claim": "python3 scripts/yao.py world-class-claim-guard ."
          },
          "must_collect": {
            "provenance_requirements": [
              "provider-backed model run",
              "observed timing",
              "observed token metadata"
            ],
            "success_checks": [
              "reports/output_execution_runs.json summary.model_executed_count > 0",
              "reports/output_execution_runs.json summary.timing_observed_count > 0",
              "reports/output_execution_runs.json summary.token_observed_count > 0",
              "reports/skill_os2_audit.json item provider-holdout status becomes pass"
            ],
            "privacy_contract": [
              "Do not commit provider credentials or environment dumps.",
              "The output execution report records output hashes and aggregate run metadata, not raw provider prompts."
            ]
          },
          "evidence_artifacts": [
            "reports/output_execution_runs.json",
            "reports/output_execution_runs.md",
            "reports/skill_os2_audit.json",
            "evidence/world_class/intake.schema.json",
            "evidence/world_class/templates/provider-holdout.intake.json",
            "reports/world_class_evidence_intake.json",
            "reports/world_class_evidence_intake.md"
          ],
          "observed_state": {
            "model_executed_count": 0,
            "timing_observed_count": 10,
            "token_observed_count": 0,
            "accepted": false
          },
          "source_checklist": [
            {
              "evidence_key": "provider-holdout",
              "label": "Provider model run",
              "field": "model_executed_count",
              "expected": ">0",
              "actual": 0,
              "status": "blocked",
              "source_accepted": false,
              "next_action": "Run provider-backed output-exec with real credentials."
            },
            {
              "evidence_key": "provider-holdout",
              "label": "Timing observed",
              "field": "timing_observed_count",
              "expected": ">0",
              "actual": 10,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Provider execution should record timing metadata."
            },
            {
              "evidence_key": "provider-holdout",
              "label": "Token usage observed",
              "field": "token_observed_count",
              "expected": ">0",
              "actual": 0,
              "status": "blocked",
              "source_accepted": false,
              "next_action": "Provider execution should return non-estimated token usage."
            }
          ],
          "blocked_source_check_count": 2,
          "next_source_actions": [
            "Run provider-backed output-exec with real credentials.",
            "Provider execution should return non-estimated token usage."
          ],
          "submission_state": {
            "status": "missing",
            "path": "evidence/world_class/submissions/provider-holdout.json",
            "artifact_ref_count": 0,
            "attested_real_evidence": false,
            "privacy_contract_satisfied": false,
            "ledger_counts_as_completion": false
          },
          "anti_overclaim": {
            "planned_work_counts_as_evidence": false,
            "metadata_fallback_counts_as_native_enforcement": false,
            "pending_review_counts_as_human_decision": false,
            "local_command_runner_counts_as_provider_model": false
          }
        },
        {
          "evidence_key": "human-adjudication",
          "label": "Human Adjudication",
          "category": "human",
          "owner": "human reviewer",
          "ledger_status": "pending",
          "intake_readiness": "awaiting-submission",
          "review_state": "awaiting-submission",
          "source_accepted": false,
          "objective": "Record real blind A/B reviewer decisions before claiming human output review completion.",
          "current": "0/5 decisions; pending 5",
          "execution_runbook": [
            "python3 scripts/yao.py output-review-kit --write-template",
            "Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.",
            "python3 scripts/adjudicate_output_review.py --write-template",
            "Edit reports/output_review_decisions.json with winner_variant values and reviewer metadata.",
            "python3 scripts/yao.py output-review",
            "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
            "Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.",
            "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
          ],
          "blocking_reason": "No evidence packet has been submitted for review.",
          "submission_path": "evidence/world_class/submissions/human-adjudication.json",
          "template_path": "evidence/world_class/templates/human-adjudication.intake.json",
          "commands": {
            "prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions",
            "validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
            "review_queue": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",
            "refresh_ledger": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions",
            "guard_claim": "python3 scripts/yao.py world-class-claim-guard ."
          },
          "must_collect": {
            "provenance_requirements": [
              "real reviewer identity",
              "blind A/B decisions",
              "answer key unopened until decisions exist"
            ],
            "success_checks": [
              "reports/output_review_adjudication.json summary.pending_count == 0",
              "reports/output_review_adjudication.json summary.judgment_count == summary.pair_count",
              "reports/output_review_adjudication.json summary.invalid_decision_count == 0",
              "reports/skill_os2_audit.json item human-adjudication status becomes pass"
            ],
            "privacy_contract": [
              "Reviewer decisions should not include raw user data or private customer detail.",
              "Keep the answer key separate until after decisions are recorded."
            ]
          },
          "evidence_artifacts": [
            "reports/output_blind_review_pack.md",
            "reports/output_review_kit.md",
            "reports/output_review_decisions.json",
            "reports/output_review_adjudication.json",
            "reports/output_review_adjudication.md",
            "evidence/world_class/intake.schema.json",
            "evidence/world_class/templates/human-adjudication.intake.json",
            "reports/world_class_evidence_intake.json",
            "reports/world_class_evidence_intake.md"
          ],
          "observed_state": {
            "pair_count": 5,
            "judgment_count": 0,
            "pending_count": 5,
            "invalid_decision_count": 0,
            "answer_revealed_count": 0,
            "accepted": false
          },
          "source_checklist": [
            {
              "evidence_key": "human-adjudication",
              "label": "Review pairs exist",
              "field": "pair_count",
              "expected": ">0",
              "actual": 5,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Generate the blind A/B review pack."
            },
            {
              "evidence_key": "human-adjudication",
              "label": "No pending decisions",
              "field": "pending_count",
              "expected": "==0",
              "actual": 5,
              "status": "blocked",
              "source_accepted": false,
              "next_action": "Record a reviewer choice for every pair."
            },
            {
              "evidence_key": "human-adjudication",
              "label": "Judgments complete",
              "field": "judgment_count",
              "expected": "==pair_count",
              "actual": 0,
              "status": "blocked",
              "source_accepted": false,
              "next_action": "Every pair needs one valid human judgment."
            },
            {
              "evidence_key": "human-adjudication",
              "label": "No invalid decisions",
              "field": "invalid_decision_count",
              "expected": "==0",
              "actual": 0,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Fix malformed winner/confidence entries."
            }
          ],
          "blocked_source_check_count": 2,
          "next_source_actions": [
            "Record a reviewer choice for every pair.",
            "Every pair needs one valid human judgment."
          ],
          "submission_state": {
            "status": "missing",
            "path": "evidence/world_class/submissions/human-adjudication.json",
            "artifact_ref_count": 0,
            "attested_real_evidence": false,
            "privacy_contract_satisfied": false,
            "ledger_counts_as_completion": false
          },
          "anti_overclaim": {
            "planned_work_counts_as_evidence": false,
            "metadata_fallback_counts_as_native_enforcement": false,
            "pending_review_counts_as_human_decision": false,
            "local_command_runner_counts_as_provider_model": false
          }
        },
        {
          "evidence_key": "native-permission-enforcement",
          "label": "Native Permission Enforcement",
          "category": "external",
          "owner": "target client or installer integrator",
          "ledger_status": "pending",
          "intake_readiness": "awaiting-submission",
          "review_state": "awaiting-submission",
          "source_accepted": false,
          "objective": "Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.",
          "current": "native-enforced targets 0; installer-enforced targets 4",
          "execution_runbook": [
            "Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.",
            "Update the generated target adapter only when the guard is actually enforced by that target.",
            "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip",
            "python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation",
            "python3 scripts/yao.py runtime-permissions . --package-dir dist",
            "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
            "Copy evidence/world_class/templates/native-permission-enforcement.intake.json to evidence/world_class/submissions/native-permission-enforcement.json and fill only real evidence fields.",
            "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
          ],
          "blocking_reason": "No evidence packet has been submitted for review.",
          "submission_path": "evidence/world_class/submissions/native-permission-enforcement.json",
          "template_path": "evidence/world_class/templates/native-permission-enforcement.intake.json",
          "commands": {
            "prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions",
            "validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
            "review_queue": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",
            "refresh_ledger": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions",
            "guard_claim": "python3 scripts/yao.py world-class-claim-guard ."
          },
          "must_collect": {
            "provenance_requirements": [
              "real target client or external installer runtime guard",
              "native enforcement flag or externally accepted guard proof",
              "residual risk retained for fallback targets"
            ],
            "success_checks": [
              "reports/runtime_permission_probes.json summary.native_enforcement_count > 0",
              "reports/runtime_permission_probes.json summary.failure_count == 0",
              "reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence",
              "reports/skill_os2_audit.json item native-permission-enforcement status becomes pass"
            ],
            "privacy_contract": [
              "Do not mark native_enforcement true for metadata-only fallbacks.",
              "Keep residual risks visible for targets that still rely on operator enforcement."
            ]
          },
          "evidence_artifacts": [
            "dist/targets/*/adapter.json",
            "reports/runtime_permission_probes.json",
            "reports/runtime_permission_probes.md",
            "reports/install_simulation.json",
            "reports/install_simulation.md",
            "security/permission_policy.json",
            "evidence/world_class/intake.schema.json",
            "evidence/world_class/templates/native-permission-enforcement.intake.json",
            "reports/world_class_evidence_intake.json",
            "reports/world_class_evidence_intake.md"
          ],
          "observed_state": {
            "native_enforcement_count": 0,
            "metadata_fallback_count": 4,
            "installer_enforcement_pass_count": 4,
            "installer_permission_failure_count": 0,
            "installer_enforcement_ready": true,
            "residual_risk_count": 4,
            "failure_count": 0,
            "accepted": false
          },
          "source_checklist": [
            {
              "evidence_key": "native-permission-enforcement",
              "label": "Native enforcement",
              "field": "native_enforcement_count",
              "expected": ">0",
              "actual": 0,
              "status": "blocked",
              "source_accepted": false,
              "next_action": "Collect real target-client or external runtime guard proof."
            },
            {
              "evidence_key": "native-permission-enforcement",
              "label": "Probe failures",
              "field": "failure_count",
              "expected": "==0",
              "actual": 0,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Runtime permission probes must stay clean."
            },
            {
              "evidence_key": "native-permission-enforcement",
              "label": "Installer support",
              "field": "installer_enforcement_ready",
              "expected": "true",
              "actual": true,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Installer enforcement is supporting evidence, not native proof."
            }
          ],
          "blocked_source_check_count": 1,
          "next_source_actions": [
            "Collect real target-client or external runtime guard proof."
          ],
          "submission_state": {
            "status": "missing",
            "path": "evidence/world_class/submissions/native-permission-enforcement.json",
            "artifact_ref_count": 0,
            "attested_real_evidence": false,
            "privacy_contract_satisfied": false,
            "ledger_counts_as_completion": false
          },
          "anti_overclaim": {
            "planned_work_counts_as_evidence": false,
            "metadata_fallback_counts_as_native_enforcement": false,
            "pending_review_counts_as_human_decision": false,
            "local_command_runner_counts_as_provider_model": false
          }
        },
        {
          "evidence_key": "native-client-telemetry",
          "label": "Native Client Telemetry",
          "category": "external",
          "owner": "Browser/Chrome/IDE/provider client integrator",
          "ledger_status": "pending",
          "intake_readiness": "awaiting-submission",
          "review_state": "awaiting-submission",
          "source_accepted": false,
          "objective": "Import production metadata-only events from a real external client into the local drift loop.",
          "current": "external source events 0; adoption samples 1",
          "execution_runbook": [
            "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
            "Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.",
            "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl",
            "python3 scripts/yao.py skill-atlas --workspace-root .",
            "python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
            "Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.",
            "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
          ],
          "blocking_reason": "No evidence packet has been submitted for review.",
          "submission_path": "evidence/world_class/submissions/native-client-telemetry.json",
          "template_path": "evidence/world_class/templates/native-client-telemetry.intake.json",
          "commands": {
            "prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions",
            "validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
            "review_queue": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",
            "refresh_ledger": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions",
            "guard_claim": "python3 scripts/yao.py world-class-claim-guard ."
          },
          "must_collect": {
            "provenance_requirements": [
              "real external client source",
              "metadata-only event",
              "local-first import path"
            ],
            "success_checks": [
              "reports/adoption_drift_report.json summary.source_types.external > 0",
              "reports/adoption_drift_report.json summary.adoption_sample_count > 0",
              "reports/skill_os2_audit.json item native-client-telemetry status becomes pass"
            ],
            "privacy_contract": [
              "Telemetry must remain metadata-only and local-first.",
              "Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field."
            ]
          },
          "evidence_artifacts": [
            "reports/adoption_drift_report.json",
            "reports/adoption_drift_report.md",
            "reports/telemetry_hook_recipes.json",
            "scripts/telemetry_native_host.py",
            "evidence/world_class/intake.schema.json",
            "evidence/world_class/templates/native-client-telemetry.intake.json",
            "reports/world_class_evidence_intake.json",
            "reports/world_class_evidence_intake.md"
          ],
          "observed_state": {
            "external_source_events": 0,
            "adoption_sample_count": 1,
            "raw_content_allowed": false,
            "risk_band": "low",
            "accepted": false
          },
          "source_checklist": [
            {
              "evidence_key": "native-client-telemetry",
              "label": "External events",
              "field": "external_source_events",
              "expected": ">0",
              "actual": 0,
              "status": "blocked",
              "source_accepted": false,
              "next_action": "Import at least one metadata-only event from a real client."
            },
            {
              "evidence_key": "native-client-telemetry",
              "label": "Adoption sample",
              "field": "adoption_sample_count",
              "expected": ">0",
              "actual": 1,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Telemetry must include adoption outcome evidence."
            },
            {
              "evidence_key": "native-client-telemetry",
              "label": "Raw content blocked",
              "field": "raw_content_allowed",
              "expected": "false",
              "actual": false,
              "status": "pass",
              "source_accepted": false,
              "next_action": "Telemetry must stay metadata-only."
            }
          ],
          "blocked_source_check_count": 1,
          "next_source_actions": [
            "Import at least one metadata-only event from a real client."
          ],
          "submission_state": {
            "status": "missing",
            "path": "evidence/world_class/submissions/native-client-telemetry.json",
            "artifact_ref_count": 0,
            "attested_real_evidence": false,
            "privacy_contract_satisfied": false,
            "ledger_counts_as_completion": false
          },
          "anti_overclaim": {
            "planned_work_counts_as_evidence": false,
            "metadata_fallback_counts_as_native_enforcement": false,
            "pending_review_counts_as_human_decision": false,
            "local_command_runner_counts_as_provider_model": false
          }
        }
      ],
      "source_reports": {
        "ledger": "reports/world_class_evidence_ledger.json",
        "intake": "reports/world_class_evidence_intake.json",
        "submission_review": "reports/world_class_submission_review.json",
        "claim_guard": "reports/world_class_claim_guard.json"
      },
      "artifacts": {
        "json": "reports/world_class_operator_runbook.json",
        "markdown": "reports/world_class_operator_runbook.md",
        "html": "reports/world_class_operator_runbook.html"
      }
    },
    "world_class_claim_guard": {
      "schema_version": "1.0",
      "ok": true,
      "generated_at": "2026-06-13",
      "skill_dir": ".",
      "summary": {
        "ledger_ready_to_claim_world_class": false,
        "ledger_pending_count": 4,
        "claim_surface_count": 76,
        "violation_count": 0,
        "overclaim_guard_active": true,
        "decision": "claim-guard-pass-evidence-pending"
      },
      "rules": [
        {
          "key": "ready-to-claim-true",
          "reason": "ready_to_claim_world_class cannot be true while ledger evidence is pending.",
          "pattern": "ready[\\s_-]*to[\\s_-]*claim[\\s_-]*world[\\s_-]*class\\s*[:=]\\s*`?true`?"
        },
        {
          "key": "world-class-ready-true",
          "reason": "world-class readiness cannot be claimed before accepted external and human evidence exists.",
          "pattern": "(public\\s+)?world[\\s_-]*class[\\s_-]*ready\\s*[:=]\\s*`?true`?"
        },
        {
          "key": "json-world-class-ready-true",
          "reason": "machine-readable claim fields must remain false until the ledger is ready.",
          "pattern": "\"(?:ready_to_claim_world_class|world_class_ready|public_world_class_ready)\"\\s*:\\s*true"
        },
        {
          "key": "completion-phrase",
          "reason": "completion language is blocked until the world-class ledger is accepted.",
          "pattern": "(public\\s+)?world[\\s_-]*class\\s+(?:complete|completed|achieved|certified)"
        },
        {
          "key": "zh-completion-phrase",
          "reason": "中文完成态表述必须等到 ledger ready 后才能出现。",
          "pattern": "世界级(?:已完成|完成|已达成|达成|准备就绪|可声明|认证通过)"
        }
      ],
      "scanned_surfaces": [
        {
          "path": "README.md",
          "violation_count": 0
        },
        {
          "path": "SKILL.md",
          "violation_count": 0
        },
        {
          "path": "docs/README.fr-FR.md",
          "violation_count": 0
        },
        {
          "path": "docs/README.ja-JP.md",
          "violation_count": 0
        },
        {
          "path": "docs/README.ru-RU.md",
          "violation_count": 0
        },
        {
          "path": "docs/README.zh-CN.md",
          "violation_count": 0
        },
        {
          "path": "docs/migration-v2.md",
          "violation_count": 0
        },
        {
          "path": "reports/adaptation_proposals.md",
          "violation_count": 0
        },
        {
          "path": "reports/adoption_drift_report.md",
          "violation_count": 0
        },
        {
          "path": "reports/architecture_maintainability.md",
          "violation_count": 0
        },
        {
          "path": "reports/artifact-design-profile.md",
          "violation_count": 0
        },
        {
          "path": "reports/baseline-compare.md",
          "violation_count": 0
        },
        {
          "path": "reports/benchmark_methodology.md",
          "violation_count": 0
        },
        {
          "path": "reports/benchmark_reproducibility.md",
          "violation_count": 0
        },
        {
          "path": "reports/candidate_registry.md",
          "violation_count": 0
        },
        {
          "path": "reports/compiled_targets.md",
          "violation_count": 0
        },
        {
          "path": "reports/conformance_matrix.md",
          "violation_count": 0
        },
        {
          "path": "reports/context_budget.md",
          "violation_count": 0
        },
        {
          "path": "reports/description_drift_history.md",
          "violation_count": 0
        },
        {
          "path": "reports/description_optimization.md",
          "violation_count": 0
        },
        {
          "path": "reports/description_optimization_suite.md",
          "violation_count": 0
        },
        {
          "path": "reports/family_summary.md",
          "violation_count": 0
        },
        {
          "path": "reports/feishu-ranking-pattern-analysis-2026-04-01.md",
          "violation_count": 0
        },
        {
          "path": "reports/github-benchmark-scan.md",
          "violation_count": 0
        },
        {
          "path": "reports/install_simulation.md",
          "violation_count": 0
        },
        {
          "path": "reports/intent-confidence.md",
          "violation_count": 0
        },
        {
          "path": "reports/intent-dialogue.md",
          "violation_count": 0
        },
        {
          "path": "reports/iteration-directions.md",
          "violation_count": 0
        },
        {
          "path": "reports/iteration_bundles/governed-incident-command/bundle.md",
          "violation_count": 0
        },
        {
          "path": "reports/iteration_bundles/governed-incident-command/review.md",
          "violation_count": 0
        },
        {
          "path": "reports/iteration_bundles/team-frontend-review/bundle.md",
          "violation_count": 0
        },
        {
          "path": "reports/iteration_bundles/team-frontend-review/review.md",
          "violation_count": 0
        },
        {
          "path": "reports/iteration_bundles/yao-meta-skill/bundle.md",
          "violation_count": 0
        },
        {
          "path": "reports/iteration_bundles/yao-meta-skill/review.md",
          "violation_count": 0
        },
        {
          "path": "reports/iteration_ledger.md",
          "violation_count": 0
        },
        {
          "path": "reports/output-risk-profile.md",
          "violation_count": 0
        },
        {
          "path": "reports/output_blind_review_pack.md",
          "violation_count": 0
        },
        {
          "path": "reports/output_execution_runs.md",
          "violation_count": 0
        },
        {
          "path": "reports/output_quality_scorecard.md",
          "violation_count": 0
        },
        {
          "path": "reports/output_review_adjudication.md",
          "violation_count": 0
        },
        {
          "path": "reports/output_review_kit.html",
          "violation_count": 0
        },
        {
          "path": "reports/output_review_kit.md",
          "violation_count": 0
        },
        {
          "path": "reports/package_verification.md",
          "violation_count": 0
        },
        {
          "path": "reports/portability_score.md",
          "violation_count": 0
        },
        {
          "path": "reports/promotion_decisions.md",
          "violation_count": 0
        },
        {
          "path": "reports/prompt-quality-profile.md",
          "violation_count": 0
        },
        {
          "path": "reports/python_compatibility.md",
          "violation_count": 0
        },
        {
          "path": "reports/reference-scan.md",
          "violation_count": 0
        },
        {
          "path": "reports/reference-synthesis.md",
          "violation_count": 0
        },
        {
          "path": "reports/registry_audit.md",
          "violation_count": 0
        },
        {
          "path": "reports/regression_history.md",
          "violation_count": 0
        },
        {
          "path": "reports/review-studio.html",
          "violation_count": 0
        },
        {
          "path": "reports/review-viewer.html",
          "violation_count": 0
        },
        {
          "path": "reports/review_annotations.md",
          "violation_count": 0
        },
        {
          "path": "reports/review_waivers.md",
          "violation_count": 0
        },
        {
          "path": "reports/route_scorecard.md",
          "violation_count": 0
        },
        {
          "path": "reports/runtime_permission_probes.md",
          "violation_count": 0
        },
        {
          "path": "reports/security_trust_report.md",
          "violation_count": 0
        },
        {
          "path": "reports/skill-interpretation.html",
          "violation_count": 0
        },
        {
          "path": "reports/skill-os-2-review.md",
          "violation_count": 0
        },
        {
          "path": "reports/skill-overview-v2-plan.md",
          "violation_count": 0
        },
        {
          "path": "reports/skill-overview.html",
          "violation_count": 0
        },
        {
          "path": "reports/skill_atlas.html",
          "violation_count": 0
        },
        {
          "path": "reports/skill_os2_audit.md",
          "violation_count": 0
        },
        {
          "path": "reports/skill_os2_coverage.md",
          "violation_count": 0
        },
        {
          "path": "reports/system-model.md",
          "violation_count": 0
        },
        {
          "path": "reports/telemetry_hook_recipes.md",
          "violation_count": 0
        },
        {
          "path": "reports/upgrade_check.md",
          "violation_count": 0
        },
        {
          "path": "reports/user_patterns.md",
          "violation_count": 0
        },
        {
          "path": "reports/world_class_evidence_intake.md",
          "violation_count": 0
        },
        {
          "path": "reports/world_class_evidence_ledger.md",
          "violation_count": 0
        },
        {
          "path": "reports/world_class_evidence_plan.md",
          "violation_count": 0
        },
        {
          "path": "reports/world_class_operator_runbook.html",
          "violation_count": 0
        },
        {
          "path": "reports/world_class_operator_runbook.md",
          "violation_count": 0
        },
        {
          "path": "reports/world_class_submission_review.md",
          "violation_count": 0
        },
        {
          "path": "reports/yao-deploy-bridge-skill-research-plan.md",
          "violation_count": 0
        }
      ],
      "violations": [],
      "source_ledger": {
        "json": "reports/world_class_evidence_ledger.json",
        "markdown": "reports/world_class_evidence_ledger.md"
      },
      "artifacts": {
        "json": "reports/world_class_claim_guard.json",
        "markdown": "reports/world_class_claim_guard.md"
      }
    },
    "registry": {
      "ok": true,
      "schema_version": "2.0",
      "skill_dir": ".",
      "registry_dir": "registry",
      "package": {
        "schema_version": "2.0",
        "name": "yao-meta-skill",
        "version": "1.1.0",
        "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
        "targets": [
          "openai",
          "claude",
          "generic",
          "agent-skills-compatible",
          "vscode"
        ],
        "maturity": "governed",
        "owner": "Yao Team",
        "review_cadence": "quarterly",
        "trust_level": "local",
        "license": "MIT",
        "checksums": {
          "package_sha256": "ecb6c742c79077b26d1f9e61ede1b1c4c078b485fc57467b969d9c1744bc91b6",
          "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc"
        },
        "compatibility": {
          "openai": "pass",
          "claude": "pass",
          "agent-skills": "pass",
          "vscode": "pass",
          "generic": "pass",
          "agent-skills-compatible": "pass"
        },
        "source": {
          "skill_dir": ".",
          "skill_ir": "skill-ir/examples/yao-meta-skill.json",
          "ir_schema_version": "2.0.0",
          "canonical_metadata": "agents/interface.yaml"
        },
        "artifacts": {
          "overview_html": "reports/skill-overview.html",
          "review_studio_html": "reports/review-studio.html",
          "trust_report": "reports/security_trust_report.md",
          "conformance_matrix": "reports/conformance_matrix.md",
          "compiled_targets": "reports/compiled_targets.md",
          "package_verification": "reports/package_verification.md",
          "install_simulation": "reports/install_simulation.md",
          "adoption_drift": "reports/adoption_drift_report.md",
          "review_waivers": "reports/review_waivers.md",
          "review_annotations": "reports/review_annotations.md",
          "package_metadata": "registry/packages/yao-meta-skill.json"
        },
        "distribution": {
          "archive_verified": true,
          "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
          "package_verification": "reports/package_verification.json",
          "install_simulated": true,
          "install_simulation": "reports/install_simulation.json"
        },
        "generated_at": "2026-06-13"
      },
      "index": {
        "schema_version": "2.0",
        "generated_at": "2026-06-13",
        "package_count": 1,
        "packages": [
          {
            "name": "yao-meta-skill",
            "version": "1.1.0",
            "maturity": "governed",
            "owner": "Yao Team",
            "targets": [
              "openai",
              "claude",
              "generic",
              "agent-skills-compatible",
              "vscode"
            ],
            "package_metadata": "registry/packages/yao-meta-skill.json",
            "package_sha256": "ecb6c742c79077b26d1f9e61ede1b1c4c078b485fc57467b969d9c1744bc91b6"
          }
        ]
      },
      "failures": [],
      "warnings": [],
      "artifacts": {
        "index": "registry/index.json",
        "package": "registry/packages/yao-meta-skill.json",
        "json": "reports/registry_audit.json",
        "markdown": "reports/registry_audit.md"
      }
    },
    "package_verification": {
      "ok": true,
      "schema_version": "2.0",
      "generated_at": "2026-06-15",
      "skill_dir": ".",
      "package_dir": "dist",
      "summary": {
        "target_count": 4,
        "adapter_count": 4,
        "archive_present": true,
        "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
        "archive_entry_count": 586,
        "failure_count": 0,
        "warning_count": 0
      },
      "checks": [
        {
          "id": "package-manifest",
          "status": "pass",
          "detail": "Package manifest exists: dist/manifest.json"
        },
        {
          "id": "openai-adapter",
          "status": "pass",
          "detail": "Adapter exists for target: openai"
        },
        {
          "id": "openai-field-name",
          "status": "pass",
          "detail": "openai adapter includes field: name"
        },
        {
          "id": "openai-field-description",
          "status": "pass",
          "detail": "openai adapter includes field: description"
        },
        {
          "id": "openai-field-version",
          "status": "pass",
          "detail": "openai adapter includes field: version"
        },
        {
          "id": "openai-field-display_name",
          "status": "pass",
          "detail": "openai adapter includes field: display_name"
        },
        {
          "id": "openai-field-short_description",
          "status": "pass",
          "detail": "openai adapter includes field: short_description"
        },
        {
          "id": "openai-field-default_prompt",
          "status": "pass",
          "detail": "openai adapter includes field: default_prompt"
        },
        {
          "id": "openai-field-job_to_be_done",
          "status": "pass",
          "detail": "openai adapter includes field: job_to_be_done"
        },
        {
          "id": "openai-field-ir_source",
          "status": "pass",
          "detail": "openai adapter includes field: ir_source"
        },
        {
          "id": "openai-field-ir_schema_version",
          "status": "pass",
          "detail": "openai adapter includes field: ir_schema_version"
        },
        {
          "id": "openai-field-semantic_contract",
          "status": "pass",
          "detail": "openai adapter includes field: semantic_contract"
        },
        {
          "id": "openai-field-semantic_parity",
          "status": "pass",
          "detail": "openai adapter includes field: semantic_parity"
        },
        {
          "id": "openai-field-compiler",
          "status": "pass",
          "detail": "openai adapter includes field: compiler"
        },
        {
          "id": "openai-field-compiled_contract",
          "status": "pass",
          "detail": "openai adapter includes field: compiled_contract"
        },
        {
          "id": "openai-field-permission_contract",
          "status": "pass",
          "detail": "openai adapter includes field: permission_contract"
        },
        {
          "id": "openai-field-target_permission_contract",
          "status": "pass",
          "detail": "openai adapter includes field: target_permission_contract"
        },
        {
          "id": "openai-field-target_native_contract",
          "status": "pass",
          "detail": "openai adapter includes field: target_native_contract"
        },
        {
          "id": "openai-field-target_transform",
          "status": "pass",
          "detail": "openai adapter includes field: target_transform"
        },
        {
          "id": "openai-field-canonical_metadata",
          "status": "pass",
          "detail": "openai adapter includes field: canonical_metadata"
        },
        {
          "id": "openai-field-canonical_format",
          "status": "pass",
          "detail": "openai adapter includes field: canonical_format"
        },
        {
          "id": "openai-field-activation_mode",
          "status": "pass",
          "detail": "openai adapter includes field: activation_mode"
        },
        {
          "id": "openai-field-execution_context",
          "status": "pass",
          "detail": "openai adapter includes field: execution_context"
        },
        {
          "id": "openai-field-shell",
          "status": "pass",
          "detail": "openai adapter includes field: shell"
        },
        {
          "id": "openai-field-trust_level",
          "status": "pass",
          "detail": "openai adapter includes field: trust_level"
        },
        {
          "id": "openai-field-remote_inline_execution",
          "status": "pass",
          "detail": "openai adapter includes field: remote_inline_execution"
        },
        {
          "id": "openai-field-degradation_strategy",
          "status": "pass",
          "detail": "openai adapter includes field: degradation_strategy"
        },
        {
          "id": "openai-field-portability_profile",
          "status": "pass",
          "detail": "openai adapter includes field: portability_profile"
        },
        {
          "id": "claude-adapter",
          "status": "pass",
          "detail": "Adapter exists for target: claude"
        },
        {
          "id": "claude-field-name",
          "status": "pass",
          "detail": "claude adapter includes field: name"
        },
        {
          "id": "claude-field-description",
          "status": "pass",
          "detail": "claude adapter includes field: description"
        },
        {
          "id": "claude-field-version",
          "status": "pass",
          "detail": "claude adapter includes field: version"
        },
        {
          "id": "claude-field-display_name",
          "status": "pass",
          "detail": "claude adapter includes field: display_name"
        },
        {
          "id": "claude-field-short_description",
          "status": "pass",
          "detail": "claude adapter includes field: short_description"
        },
        {
          "id": "claude-field-default_prompt",
          "status": "pass",
          "detail": "claude adapter includes field: default_prompt"
        },
        {
          "id": "claude-field-job_to_be_done",
          "status": "pass",
          "detail": "claude adapter includes field: job_to_be_done"
        },
        {
          "id": "claude-field-ir_source",
          "status": "pass",
          "detail": "claude adapter includes field: ir_source"
        },
        {
          "id": "claude-field-ir_schema_version",
          "status": "pass",
          "detail": "claude adapter includes field: ir_schema_version"
        },
        {
          "id": "claude-field-semantic_contract",
          "status": "pass",
          "detail": "claude adapter includes field: semantic_contract"
        },
        {
          "id": "claude-field-semantic_parity",
          "status": "pass",
          "detail": "claude adapter includes field: semantic_parity"
        },
        {
          "id": "claude-field-compiler",
          "status": "pass",
          "detail": "claude adapter includes field: compiler"
        },
        {
          "id": "claude-field-compiled_contract",
          "status": "pass",
          "detail": "claude adapter includes field: compiled_contract"
        },
        {
          "id": "claude-field-permission_contract",
          "status": "pass",
          "detail": "claude adapter includes field: permission_contract"
        },
        {
          "id": "claude-field-target_permission_contract",
          "status": "pass",
          "detail": "claude adapter includes field: target_permission_contract"
        },
        {
          "id": "claude-field-target_native_contract",
          "status": "pass",
          "detail": "claude adapter includes field: target_native_contract"
        },
        {
          "id": "claude-field-target_transform",
          "status": "pass",
          "detail": "claude adapter includes field: target_transform"
        },
        {
          "id": "claude-field-canonical_metadata",
          "status": "pass",
          "detail": "claude adapter includes field: canonical_metadata"
        },
        {
          "id": "claude-field-canonical_format",
          "status": "pass",
          "detail": "claude adapter includes field: canonical_format"
        },
        {
          "id": "claude-field-activation_mode",
          "status": "pass",
          "detail": "claude adapter includes field: activation_mode"
        },
        {
          "id": "claude-field-execution_context",
          "status": "pass",
          "detail": "claude adapter includes field: execution_context"
        },
        {
          "id": "claude-field-shell",
          "status": "pass",
          "detail": "claude adapter includes field: shell"
        },
        {
          "id": "claude-field-trust_level",
          "status": "pass",
          "detail": "claude adapter includes field: trust_level"
        },
        {
          "id": "claude-field-remote_inline_execution",
          "status": "pass",
          "detail": "claude adapter includes field: remote_inline_execution"
        },
        {
          "id": "claude-field-degradation_strategy",
          "status": "pass",
          "detail": "claude adapter includes field: degradation_strategy"
        },
        {
          "id": "claude-field-portability_profile",
          "status": "pass",
          "detail": "claude adapter includes field: portability_profile"
        },
        {
          "id": "generic-adapter",
          "status": "pass",
          "detail": "Adapter exists for target: generic"
        },
        {
          "id": "generic-field-name",
          "status": "pass",
          "detail": "generic adapter includes field: name"
        },
        {
          "id": "generic-field-description",
          "status": "pass",
          "detail": "generic adapter includes field: description"
        },
        {
          "id": "generic-field-version",
          "status": "pass",
          "detail": "generic adapter includes field: version"
        },
        {
          "id": "generic-field-display_name",
          "status": "pass",
          "detail": "generic adapter includes field: display_name"
        },
        {
          "id": "generic-field-short_description",
          "status": "pass",
          "detail": "generic adapter includes field: short_description"
        },
        {
          "id": "generic-field-default_prompt",
          "status": "pass",
          "detail": "generic adapter includes field: default_prompt"
        },
        {
          "id": "generic-field-job_to_be_done",
          "status": "pass",
          "detail": "generic adapter includes field: job_to_be_done"
        },
        {
          "id": "generic-field-ir_source",
          "status": "pass",
          "detail": "generic adapter includes field: ir_source"
        },
        {
          "id": "generic-field-ir_schema_version",
          "status": "pass",
          "detail": "generic adapter includes field: ir_schema_version"
        },
        {
          "id": "generic-field-semantic_contract",
          "status": "pass",
          "detail": "generic adapter includes field: semantic_contract"
        },
        {
          "id": "generic-field-semantic_parity",
          "status": "pass",
          "detail": "generic adapter includes field: semantic_parity"
        },
        {
          "id": "generic-field-compiler",
          "status": "pass",
          "detail": "generic adapter includes field: compiler"
        },
        {
          "id": "generic-field-compiled_contract",
          "status": "pass",
          "detail": "generic adapter includes field: compiled_contract"
        },
        {
          "id": "generic-field-permission_contract",
          "status": "pass",
          "detail": "generic adapter includes field: permission_contract"
        },
        {
          "id": "generic-field-target_permission_contract",
          "status": "pass",
          "detail": "generic adapter includes field: target_permission_contract"
        },
        {
          "id": "generic-field-target_native_contract",
          "status": "pass",
          "detail": "generic adapter includes field: target_native_contract"
        },
        {
          "id": "generic-field-target_transform",
          "status": "pass",
          "detail": "generic adapter includes field: target_transform"
        },
        {
          "id": "generic-field-canonical_metadata",
          "status": "pass",
          "detail": "generic adapter includes field: canonical_metadata"
        },
        {
          "id": "generic-field-canonical_format",
          "status": "pass",
          "detail": "generic adapter includes field: canonical_format"
        },
        {
          "id": "generic-field-activation_mode",
          "status": "pass",
          "detail": "generic adapter includes field: activation_mode"
        },
        {
          "id": "generic-field-execution_context",
          "status": "pass",
          "detail": "generic adapter includes field: execution_context"
        },
        {
          "id": "generic-field-shell",
          "status": "pass",
          "detail": "generic adapter includes field: shell"
        },
        {
          "id": "generic-field-trust_level",
          "status": "pass",
          "detail": "generic adapter includes field: trust_level"
        },
        {
          "id": "generic-field-remote_inline_execution",
          "status": "pass",
          "detail": "generic adapter includes field: remote_inline_execution"
        },
        {
          "id": "generic-field-degradation_strategy",
          "status": "pass",
          "detail": "generic adapter includes field: degradation_strategy"
        },
        {
          "id": "generic-field-portability_profile",
          "status": "pass",
          "detail": "generic adapter includes field: portability_profile"
        },
        {
          "id": "vscode-adapter",
          "status": "pass",
          "detail": "Adapter exists for target: vscode"
        },
        {
          "id": "vscode-field-name",
          "status": "pass",
          "detail": "vscode adapter includes field: name"
        },
        {
          "id": "vscode-field-description",
          "status": "pass",
          "detail": "vscode adapter includes field: description"
        },
        {
          "id": "vscode-field-version",
          "status": "pass",
          "detail": "vscode adapter includes field: version"
        },
        {
          "id": "vscode-field-display_name",
          "status": "pass",
          "detail": "vscode adapter includes field: display_name"
        },
        {
          "id": "vscode-field-short_description",
          "status": "pass",
          "detail": "vscode adapter includes field: short_description"
        },
        {
          "id": "vscode-field-default_prompt",
          "status": "pass",
          "detail": "vscode adapter includes field: default_prompt"
        },
        {
          "id": "vscode-field-job_to_be_done",
          "status": "pass",
          "detail": "vscode adapter includes field: job_to_be_done"
        },
        {
          "id": "vscode-field-ir_source",
          "status": "pass",
          "detail": "vscode adapter includes field: ir_source"
        },
        {
          "id": "vscode-field-ir_schema_version",
          "status": "pass",
          "detail": "vscode adapter includes field: ir_schema_version"
        },
        {
          "id": "vscode-field-semantic_contract",
          "status": "pass",
          "detail": "vscode adapter includes field: semantic_contract"
        },
        {
          "id": "vscode-field-semantic_parity",
          "status": "pass",
          "detail": "vscode adapter includes field: semantic_parity"
        },
        {
          "id": "vscode-field-compiler",
          "status": "pass",
          "detail": "vscode adapter includes field: compiler"
        },
        {
          "id": "vscode-field-compiled_contract",
          "status": "pass",
          "detail": "vscode adapter includes field: compiled_contract"
        },
        {
          "id": "vscode-field-permission_contract",
          "status": "pass",
          "detail": "vscode adapter includes field: permission_contract"
        },
        {
          "id": "vscode-field-target_permission_contract",
          "status": "pass",
          "detail": "vscode adapter includes field: target_permission_contract"
        },
        {
          "id": "vscode-field-target_native_contract",
          "status": "pass",
          "detail": "vscode adapter includes field: target_native_contract"
        },
        {
          "id": "vscode-field-target_transform",
          "status": "pass",
          "detail": "vscode adapter includes field: target_transform"
        },
        {
          "id": "vscode-field-canonical_metadata",
          "status": "pass",
          "detail": "vscode adapter includes field: canonical_metadata"
        },
        {
          "id": "vscode-field-canonical_format",
          "status": "pass",
          "detail": "vscode adapter includes field: canonical_format"
        },
        {
          "id": "vscode-field-activation_mode",
          "status": "pass",
          "detail": "vscode adapter includes field: activation_mode"
        },
        {
          "id": "vscode-field-execution_context",
          "status": "pass",
          "detail": "vscode adapter includes field: execution_context"
        },
        {
          "id": "vscode-field-shell",
          "status": "pass",
          "detail": "vscode adapter includes field: shell"
        },
        {
          "id": "vscode-field-trust_level",
          "status": "pass",
          "detail": "vscode adapter includes field: trust_level"
        },
        {
          "id": "vscode-field-remote_inline_execution",
          "status": "pass",
          "detail": "vscode adapter includes field: remote_inline_execution"
        },
        {
          "id": "vscode-field-degradation_strategy",
          "status": "pass",
          "detail": "vscode adapter includes field: degradation_strategy"
        },
        {
          "id": "vscode-field-portability_profile",
          "status": "pass",
          "detail": "vscode adapter includes field: portability_profile"
        },
        {
          "id": "openai-file-targets/openai/adapter.json",
          "status": "pass",
          "detail": "Package contains targets/openai/adapter.json"
        },
        {
          "id": "openai-file-targets/openai/agents/openai.yaml",
          "status": "pass",
          "detail": "Package contains targets/openai/agents/openai.yaml"
        },
        {
          "id": "claude-file-targets/claude/adapter.json",
          "status": "pass",
          "detail": "Package contains targets/claude/adapter.json"
        },
        {
          "id": "claude-file-targets/claude/README.md",
          "status": "pass",
          "detail": "Package contains targets/claude/README.md"
        },
        {
          "id": "generic-file-targets/generic/adapter.json",
          "status": "pass",
          "detail": "Package contains targets/generic/adapter.json"
        },
        {
          "id": "vscode-file-targets/vscode/adapter.json",
          "status": "pass",
          "detail": "Package contains targets/vscode/adapter.json"
        },
        {
          "id": "vscode-file-targets/vscode/README.md",
          "status": "pass",
          "detail": "Package contains targets/vscode/README.md"
        },
        {
          "id": "archive-safe-paths",
          "status": "pass",
          "detail": "Archive has no absolute or parent-traversal entries"
        },
        {
          "id": "archive-entry-yao-meta-skill/SKILL.md",
          "status": "pass",
          "detail": "Archive contains yao-meta-skill/SKILL.md"
        },
        {
          "id": "archive-entry-yao-meta-skill/manifest.json",
          "status": "pass",
          "detail": "Archive contains yao-meta-skill/manifest.json"
        },
        {
          "id": "archive-entry-yao-meta-skill/agents/interface.yaml",
          "status": "pass",
          "detail": "Archive contains yao-meta-skill/agents/interface.yaml"
        },
        {
          "id": "archive-excludes-generated",
          "status": "pass",
          "detail": "Archive excludes generated dist/, .previews/, and tests/tmp* contents"
        },
        {
          "id": "registry-ok",
          "status": "pass",
          "detail": "Registry audit is OK"
        },
        {
          "id": "registry-name-match",
          "status": "pass",
          "detail": "Registry package name matches package manifest"
        },
        {
          "id": "registry-version-match",
          "status": "pass",
          "detail": "Registry package version matches package manifest"
        },
        {
          "id": "registry-compat-openai",
          "status": "pass",
          "detail": "Registry compatibility is reviewable for target: openai"
        },
        {
          "id": "registry-compat-claude",
          "status": "pass",
          "detail": "Registry compatibility is reviewable for target: claude"
        },
        {
          "id": "registry-compat-generic",
          "status": "pass",
          "detail": "Registry compatibility is reviewable for target: generic"
        },
        {
          "id": "registry-compat-vscode",
          "status": "pass",
          "detail": "Registry compatibility is reviewable for target: vscode"
        }
      ],
      "failures": [],
      "warnings": [],
      "artifacts": {
        "manifest": "dist/manifest.json",
        "archive": "dist/yao-meta-skill.zip",
        "json": "reports/package_verification.json",
        "markdown": "reports/package_verification.md"
      }
    },
    "install_simulation": {
      "ok": true,
      "schema_version": "2.0",
      "generated_at": "2026-06-13",
      "skill_dir": ".",
      "package_dir": "tests/tmp_review_studio/dist",
      "install_root": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill",
      "installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill",
      "summary": {
        "archive_present": true,
        "archive_entry_count": 603,
        "archive_extracted": true,
        "entrypoint_loaded": true,
        "manifest_loaded": true,
        "interface_loaded": true,
        "adapter_count": 4,
        "installer_permission_enforced_count": 12,
        "installer_permission_failure_count": 0,
        "permission_target_count": 4,
        "permission_capability_count": 3,
        "install_root_is_temp": false,
        "failure_count": 0,
        "warning_count": 0
      },
      "checks": [
        {
          "id": "archive-present",
          "status": "pass",
          "detail": "Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip"
        },
        {
          "id": "archive-safe-paths",
          "status": "pass",
          "detail": "Archive has no absolute or parent-traversal entries"
        },
        {
          "id": "single-top-level",
          "status": "pass",
          "detail": "Archive top-level directory is yao-meta-skill"
        },
        {
          "id": "entrypoint-load",
          "status": "pass",
          "detail": "Installed SKILL.md frontmatter is readable"
        },
        {
          "id": "entrypoint-name",
          "status": "pass",
          "detail": "Installed SKILL.md name matches package directory"
        },
        {
          "id": "entrypoint-description",
          "status": "pass",
          "detail": "Installed SKILL.md description is present"
        },
        {
          "id": "manifest-load",
          "status": "pass",
          "detail": "Installed manifest.json is readable"
        },
        {
          "id": "manifest-name",
          "status": "pass",
          "detail": "Installed manifest name matches package manifest"
        },
        {
          "id": "manifest-version",
          "status": "pass",
          "detail": "Installed manifest version matches package manifest"
        },
        {
          "id": "interface-load",
          "status": "pass",
          "detail": "Installed agents/interface.yaml is readable"
        },
        {
          "id": "overview-report",
          "status": "pass",
          "detail": "Installed overview report is present"
        },
        {
          "id": "review-studio-report",
          "status": "pass",
          "detail": "Installed Review Studio report is present"
        },
        {
          "id": "adapter-claude",
          "status": "pass",
          "detail": "claude adapter is readable after package install simulation"
        },
        {
          "id": "adapter-claude-name",
          "status": "pass",
          "detail": "claude adapter name matches package manifest"
        },
        {
          "id": "adapter-generic",
          "status": "pass",
          "detail": "generic adapter is readable after package install simulation"
        },
        {
          "id": "adapter-generic-name",
          "status": "pass",
          "detail": "generic adapter name matches package manifest"
        },
        {
          "id": "adapter-openai",
          "status": "pass",
          "detail": "openai adapter is readable after package install simulation"
        },
        {
          "id": "adapter-openai-name",
          "status": "pass",
          "detail": "openai adapter name matches package manifest"
        },
        {
          "id": "adapter-vscode",
          "status": "pass",
          "detail": "vscode adapter is readable after package install simulation"
        },
        {
          "id": "adapter-vscode-name",
          "status": "pass",
          "detail": "vscode adapter name matches package manifest"
        },
        {
          "id": "permission-policy-load",
          "status": "pass",
          "detail": "Installed permission policy is readable"
        },
        {
          "id": "permission-claude-contract",
          "status": "pass",
          "detail": "claude adapter exposes target permission contract for installer enforcement"
        },
        {
          "id": "permission-claude-file_write-approved",
          "status": "pass",
          "detail": "claude capability file_write has active reviewer approval"
        },
        {
          "id": "permission-claude-file_write-target-enforcement",
          "status": "pass",
          "detail": "claude capability file_write has target enforcement note"
        },
        {
          "id": "permission-claude-network-approved",
          "status": "pass",
          "detail": "claude capability network has active reviewer approval"
        },
        {
          "id": "permission-claude-network-target-enforcement",
          "status": "pass",
          "detail": "claude capability network has target enforcement note"
        },
        {
          "id": "permission-claude-subprocess-approved",
          "status": "pass",
          "detail": "claude capability subprocess has active reviewer approval"
        },
        {
          "id": "permission-claude-subprocess-target-enforcement",
          "status": "pass",
          "detail": "claude capability subprocess has target enforcement note"
        },
        {
          "id": "permission-generic-contract",
          "status": "pass",
          "detail": "generic adapter exposes target permission contract for installer enforcement"
        },
        {
          "id": "permission-generic-file_write-approved",
          "status": "pass",
          "detail": "generic capability file_write has active reviewer approval"
        },
        {
          "id": "permission-generic-file_write-target-enforcement",
          "status": "pass",
          "detail": "generic capability file_write has target enforcement note"
        },
        {
          "id": "permission-generic-network-approved",
          "status": "pass",
          "detail": "generic capability network has active reviewer approval"
        },
        {
          "id": "permission-generic-network-target-enforcement",
          "status": "pass",
          "detail": "generic capability network has target enforcement note"
        },
        {
          "id": "permission-generic-subprocess-approved",
          "status": "pass",
          "detail": "generic capability subprocess has active reviewer approval"
        },
        {
          "id": "permission-generic-subprocess-target-enforcement",
          "status": "pass",
          "detail": "generic capability subprocess has target enforcement note"
        },
        {
          "id": "permission-openai-contract",
          "status": "pass",
          "detail": "openai adapter exposes target permission contract for installer enforcement"
        },
        {
          "id": "permission-openai-file_write-approved",
          "status": "pass",
          "detail": "openai capability file_write has active reviewer approval"
        },
        {
          "id": "permission-openai-file_write-target-enforcement",
          "status": "pass",
          "detail": "openai capability file_write has target enforcement note"
        },
        {
          "id": "permission-openai-network-approved",
          "status": "pass",
          "detail": "openai capability network has active reviewer approval"
        },
        {
          "id": "permission-openai-network-target-enforcement",
          "status": "pass",
          "detail": "openai capability network has target enforcement note"
        },
        {
          "id": "permission-openai-subprocess-approved",
          "status": "pass",
          "detail": "openai capability subprocess has active reviewer approval"
        },
        {
          "id": "permission-openai-subprocess-target-enforcement",
          "status": "pass",
          "detail": "openai capability subprocess has target enforcement note"
        },
        {
          "id": "permission-vscode-contract",
          "status": "pass",
          "detail": "vscode adapter exposes target permission contract for installer enforcement"
        },
        {
          "id": "permission-vscode-file_write-approved",
          "status": "pass",
          "detail": "vscode capability file_write has active reviewer approval"
        },
        {
          "id": "permission-vscode-file_write-target-enforcement",
          "status": "pass",
          "detail": "vscode capability file_write has target enforcement note"
        },
        {
          "id": "permission-vscode-network-approved",
          "status": "pass",
          "detail": "vscode capability network has active reviewer approval"
        },
        {
          "id": "permission-vscode-network-target-enforcement",
          "status": "pass",
          "detail": "vscode capability network has target enforcement note"
        },
        {
          "id": "permission-vscode-subprocess-approved",
          "status": "pass",
          "detail": "vscode capability subprocess has active reviewer approval"
        },
        {
          "id": "permission-vscode-subprocess-target-enforcement",
          "status": "pass",
          "detail": "vscode capability subprocess has target enforcement note"
        }
      ],
      "failures": [],
      "warnings": [],
      "artifacts": {
        "archive": "tests/tmp_review_studio/dist/yao-meta-skill.zip",
        "package_manifest": "tests/tmp_review_studio/dist/manifest.json",
        "json": "tests/tmp_review_studio/install_simulation.json",
        "markdown": "tests/tmp_review_studio/install_simulation.md"
      }
    },
    "upgrade_check": {
      "ok": true,
      "schema_version": "2.0",
      "generated_at": "2026-06-13",
      "previous": {
        "name": "yao-meta-skill",
        "version": "1.0.0",
        "targets": [
          "openai",
          "claude",
          "generic"
        ]
      },
      "current": {
        "name": "yao-meta-skill",
        "version": "1.1.0",
        "targets": [
          "openai",
          "claude",
          "generic",
          "agent-skills-compatible",
          "vscode"
        ]
      },
      "summary": {
        "declared_bump": "minor",
        "recommended_bump": "minor",
        "breaking_change_count": 0,
        "added_target_count": 2,
        "metadata_change_count": 1,
        "checksum_change_count": 2,
        "failure_count": 0,
        "warning_count": 0
      },
      "upgrade_diff": {
        "name_changed": false,
        "added_targets": [
          "agent-skills-compatible",
          "vscode"
        ],
        "removed_targets": [],
        "compatibility_changes": [
          {
            "target": "agent-skills",
            "from": "missing",
            "to": "pass",
            "direction": "improved"
          },
          {
            "target": "agent-skills-compatible",
            "from": "missing",
            "to": "pass",
            "direction": "improved"
          },
          {
            "target": "vscode",
            "from": "missing",
            "to": "pass",
            "direction": "improved"
          }
        ],
        "metadata_changes": [
          {
            "field": "description",
            "from": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes.",
            "to": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse."
          }
        ],
        "checksum_changes": [
          {
            "field": "archive_sha256",
            "from": "",
            "to": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc"
          },
          {
            "field": "package_sha256",
            "from": "0000000000000000000000000000000000000000000000000000000000000000",
            "to": "ecb6c742c79077b26d1f9e61ede1b1c4c078b485fc57467b969d9c1744bc91b6"
          }
        ]
      },
      "release_notes": [
        "Recommended version bump: minor.",
        "Added targets: agent-skills-compatible, vscode.",
        "Package or archive checksum changed; reviewers should verify package artifacts before release.",
        "Package verification evidence: reports/package_verification.md."
      ],
      "failures": [],
      "warnings": [],
      "artifacts": {
        "previous_package": "registry/examples/yao-meta-skill-1.0.0.json",
        "current_package": "reports/registry_audit.json",
        "json": "tests/tmp_review_studio/upgrade_check.json",
        "markdown": "tests/tmp_review_studio/upgrade_check.md"
      }
    },
    "manifest": {
      "name": "yao-meta-skill",
      "version": "1.1.0",
      "owner": "Yao Team",
      "updated_at": "2026-03-31",
      "status": "active",
      "maturity_tier": "governed",
      "lifecycle_stage": "library",
      "context_budget_tier": "production",
      "review_cadence": "quarterly",
      "target_platforms": [
        "openai",
        "claude",
        "generic",
        "agent-skills-compatible",
        "vscode"
      ],
      "factory_components": [
        "templates",
        "references",
        "scripts",
        "reports"
      ]
    },
    "frontmatter": {
      "name": "yao-meta-skill",
      "description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
      "metadata": {
        "author": "Yao Team",
        "philosophy": "structured design, evaluation loop, template ergonomics, operational packaging"
      }
    },
    "interface": {
      "interface": {
        "display_name": "Yao Meta Skill",
        "short_description": "Create trigger-aware agent skills",
        "default_prompt": "Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals."
      },
      "compatibility": {
        "canonical_format": "agent-skills",
        "adapter_targets": [
          "openai",
          "claude",
          "generic",
          "vscode"
        ],
        "activation": {
          "mode": "manual",
          "paths": []
        },
        "execution": {
          "context": "inline",
          "shell": "bash"
        },
        "trust": {
          "source_tier": "local",
          "remote_inline_execution": "forbid",
          "remote_metadata_policy": "allow-metadata-only"
        },
        "degradation": {
          "openai": "metadata-adapter",
          "claude": "neutral-source-plus-adapter",
          "generic": "neutral-source",
          "vscode": "agent-skills-source-with-vscode-notes"
        }
      }
    }
  },
  "artifacts": {
    "html": "reports/review-studio.html",
    "json": "reports/review-studio.json"
  }
}