{
  "schema_version": "1.0",
  "ok": true,
  "generated_at": "2026-06-21",
  "skill_dir": ".",
  "commit": "139d0fd15ce995757d6d75fb45fb417d0b1b4e7d",
  "git_status": {
    "available": true,
    "dirty": true,
    "changed_file_count": 3,
    "generated_dirty": true,
    "generated_changed_file_count": 3,
    "source_dirty": false,
    "source_changed_file_count": 0,
    "sample": [
      " M reports/context_budget.json",
      " M reports/context_budget.md",
      " M reports/context_budget_summary.json"
    ],
    "source_sample": [],
    "generated_sample": [
      " M reports/context_budget.json",
      " M reports/context_budget.md",
      " M reports/context_budget_summary.json"
    ],
    "generated_dirty_prefixes": [
      "dist/",
      "registry/index.json",
      "registry/packages/",
      "reports/",
      "skill_atlas/",
      "skill-ir/examples/"
    ],
    "scope": "generation-time status before this report is written"
  },
  "summary": {
    "reproducibility_ready": true,
    "release_lock_ready": true,
    "methodology_complete": true,
    "required_artifact_count": 25,
    "missing_artifact_count": 0,
    "evidence_bundle_sha256": "e819a616c7276f6433bbcf38f30696cc0f19b6c035adf5c8cf09e64cbe8db9ad",
    "source_contract_sha256": "eddeea80a657e9c97cee2e1242d97577b886b33e2ffa6e319629ef5fcb029383",
    "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7",
    "output_case_count": 5,
    "failure_disclosure_count": 3,
    "command_count": 23,
    "command_executed_count": 10,
    "timing_observed_count": 10,
    "model_executed_count": 10,
    "token_observed_count": 10,
    "human_review_complete": false,
    "provider_evidence_complete": true,
    "world_class_ready": false,
    "world_class_open_gap_count": 3,
    "world_class_task_count": 4,
    "world_class_ledger_pending_count": 4,
    "world_class_source_check_count": 19,
    "world_class_source_pass_count": 12,
    "world_class_source_blocked_count": 7,
    "beta_test_ready": true,
    "beta_test_blocker_count": 0,
    "beta_test_deferred_evidence_count": 4,
    "public_claim_ready": false,
    "public_claim_blocker_count": 3,
    "working_tree_dirty": true,
    "changed_file_count": 3,
    "source_tree_dirty": false,
    "source_changed_file_count": 0,
    "generated_tree_dirty": true,
    "generated_changed_file_count": 3
  },
  "beta_test_release": {
    "ready": true,
    "scope": "beta/public test release without superiority, fully-reviewed, or world-class claims",
    "blockers": [],
    "allowed_deferred_evidence": [
      {
        "key": "provider-holdout",
        "label": "Provider Holdout",
        "reason": "Provider-backed source evidence exists, but formal ledger submission and reviewer acceptance are still pending before public claims."
      },
      {
        "key": "human-adjudication",
        "label": "Human Adjudication",
        "reason": "Human adjudication evidence is still pending; deferred for beta/public testing and still required before superiority, fully-reviewed, or world-class claims."
      },
      {
        "key": "native-permission-enforcement",
        "label": "Native Permission Enforcement",
        "reason": "Native enforcement proof is still pending; deferred for beta/public testing and still required before world-class claims."
      },
      {
        "key": "native-client-telemetry",
        "label": "Native Client Telemetry",
        "reason": "Real client telemetry is still pending; deferred for beta/public testing and still required before world-class claims."
      }
    ],
    "policy": "Human blind-review, native permission enforcement, real client telemetry, and ledger acceptance may be deferred for beta/public testing, but public claims must remain blocked until those evidence entries are accepted.",
    "required_wording": "Use beta, public test, or technical preview wording; do not claim world-class readiness, fully reviewed quality, or proven superiority over baseline."
  },
  "public_claim": {
    "ready": false,
    "scope": "public benchmark or world-class readiness claim",
    "blockers": [
      "human blind-review adjudication is incomplete",
      "world-class evidence is not accepted yet (3 open gaps, 4 ledger pending)",
      "world-class source checks are not all accepted (12/19 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": true,
    "commit": "139d0fd15ce995757d6d75fb45fb417d0b1b4e7d",
    "status_scope": "generation-time status before this report is written",
    "source_changed_file_count": 0,
    "generated_changed_file_count": 3,
    "reason": "only generated evidence artifacts were dirty at generation time"
  },
  "evidence_bundle": {
    "algorithm": "sha256(path,label,exists,artifact_sha256)",
    "artifact_count": 25,
    "existing_count": 25,
    "missing_count": 0,
    "missing_paths": [],
    "sha256": "e819a616c7276f6433bbcf38f30696cc0f19b6c035adf5c8cf09e64cbe8db9ad"
  },
  "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": 8449,
      "sha256": "4df66b63d2e717a559a6881b966fb1b92def7329cc89aa48ee0d8596f87402e5"
    },
    {
      "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": 14084,
      "sha256": "91fd88dd9b0f8876f68027a87893d1852dac59772613345bbbfabba658c9227e"
    },
    {
      "label": "trigger_scorecard",
      "path": "reports/route_scorecard.json",
      "exists": true,
      "bytes": 16950,
      "sha256": "a649547a7d3d5fe02262ca1b188ed4022d8f557770be425f7b7cf762aa76533a"
    },
    {
      "label": "runtime_conformance",
      "path": "reports/conformance_matrix.json",
      "exists": true,
      "bytes": 10342,
      "sha256": "97f9ba949c23a60b00e9ba2ff279ca03ba517845cc7c62aa8a42645d58006c7e"
    },
    {
      "label": "trust_report",
      "path": "reports/security_trust_report.json",
      "exists": true,
      "bytes": 139090,
      "sha256": "2ef43f009be68b1dd1a994b841d69b89723cf0b6d7725dc6ad86670d14235135"
    },
    {
      "label": "python_compatibility",
      "path": "reports/python_compatibility.json",
      "exists": true,
      "bytes": 30351,
      "sha256": "7f3fc8e785bf7007755c0b7f277967fd478ea17a5800ab14b9c23de395576cda"
    },
    {
      "label": "registry_audit",
      "path": "reports/registry_audit.json",
      "exists": true,
      "bytes": 3137,
      "sha256": "03cb951dc8ba71843602bffa1148d7a40095a7e109a024193422aaa8a94ba4c7"
    },
    {
      "label": "package_verification",
      "path": "reports/package_verification.json",
      "exists": true,
      "bytes": 19525,
      "sha256": "e2ad726ce0486be0f57d88e518ef4d265479a04756419c6f8df50cf7d05b1f14"
    },
    {
      "label": "install_simulation",
      "path": "reports/install_simulation.json",
      "exists": true,
      "bytes": 8793,
      "sha256": "6cf79201727352e5f92f4e1fa1697a069ab325d526065f5316ee939e84475ef5"
    },
    {
      "label": "skill_os2_audit",
      "path": "reports/skill_os2_audit.json",
      "exists": true,
      "bytes": 13824,
      "sha256": "1079221b5ac72e19e3e7a0f4970f133d828336f34bac82abf3fb867d18834cfa"
    },
    {
      "label": "world_class_evidence_plan",
      "path": "reports/world_class_evidence_plan.json",
      "exists": true,
      "bytes": 23314,
      "sha256": "374ee899a0ba5b84a95337de993439d78e5708be4fdf40dee4292766d0d2bf99"
    },
    {
      "label": "world_class_evidence_ledger",
      "path": "reports/world_class_evidence_ledger.json",
      "exists": true,
      "bytes": 26274,
      "sha256": "565ae80a82286e912df134c88a269566ecf635f39e55618df4ed4eac69d7c7ea"
    },
    {
      "label": "world_class_evidence_intake",
      "path": "reports/world_class_evidence_intake.json",
      "exists": true,
      "bytes": 20922,
      "sha256": "e36a7e753f4176e7ddd7a74fcc5b064769191baf73b5faa58752f80457ec58ff"
    },
    {
      "label": "world_class_evidence_preflight",
      "path": "reports/world_class_evidence_preflight.json",
      "exists": true,
      "bytes": 90852,
      "sha256": "9e4f0bc489ca958b5a9e2854f17b847de8ee1f081de40e8c8b86cec138afe633"
    },
    {
      "label": "world_class_submission_review",
      "path": "reports/world_class_submission_review.json",
      "exists": true,
      "bytes": 17292,
      "sha256": "3c944b4bd27f61483e8e02aa3f3b6c8cdb4aba8dc986241e8cbe60ba64489123"
    },
    {
      "label": "world_class_operator_runbook",
      "path": "reports/world_class_operator_runbook.json",
      "exists": true,
      "bytes": 83712,
      "sha256": "d8678010fcfd5fb8f28d95925478496749f5498ce13a171c80f79372b874351d"
    },
    {
      "label": "world_class_operator_runbook_markdown",
      "path": "reports/world_class_operator_runbook.md",
      "exists": true,
      "bytes": 25504,
      "sha256": "fe3a73bf2eb9a018ec03881c95d23d30abcbf8bc36cbb264f68daa08238d8e5f"
    },
    {
      "label": "world_class_operator_runbook_html",
      "path": "reports/world_class_operator_runbook.html",
      "exists": true,
      "bytes": 34651,
      "sha256": "022594013b2469a0e5776e3f5f6a99fa069917c5ba5cb90256b7841b1f5fd1e3"
    },
    {
      "label": "world_class_claim_guard",
      "path": "reports/world_class_claim_guard.json",
      "exists": true,
      "bytes": 18759,
      "sha256": "556700f05a65bda9b55d829c109d1aec54ae5b4da80ffbefe1196319df86f117"
    }
  ],
  "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 evidence preflight",
      "command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
      "evidence": "reports/world_class_evidence_preflight.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": "evidence consistency",
      "command": "python3 scripts/yao.py evidence-consistency .",
      "evidence": "reports/evidence_consistency.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 flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
    "Provider-backed model holdout source evidence is complete, but ledger acceptance still requires a valid independently reviewed submission packet.",
    "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.",
    "Beta/public testing may proceed without human blind-review only when wording avoids superiority, fully-reviewed, or world-class claims."
  ],
  "artifacts": {
    "json": "reports/benchmark_reproducibility.json",
    "markdown": "reports/benchmark_reproducibility.md"
  }
}