{
  "schema_version": "1.0",
  "ok": true,
  "generated_at": "2026-06-17",
  "skill_dir": ".",
  "commit": "67058cecebd13cd6e6fa54c009300cc145e8e999",
  "git_status": {
    "available": true,
    "dirty": true,
    "changed_file_count": 56,
    "sample": [
      " M registry/index.json",
      " M registry/packages/yao-meta-skill.json",
      " M reports/adoption_drift_report.json",
      " M reports/adoption_drift_report.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_summary.json",
      " M reports/evidence_consistency.json",
      " M reports/evidence_consistency.md",
      " M reports/install_simulation.json"
    ],
    "scope": "generation-time status before this report is written"
  },
  "summary": {
    "reproducibility_ready": true,
    "release_lock_ready": false,
    "methodology_complete": true,
    "required_artifact_count": 25,
    "missing_artifact_count": 0,
    "evidence_bundle_sha256": "733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379",
    "source_contract_sha256": "9cb9a19e774540e721b143a240baf41b41c32b9f10df532eb4a7d1cf7a2fe67b",
    "archive_sha256": "4195938709645eeb7c7a26afbd28b0a29a9162c61a15a1e003a42159a6c13fe7",
    "output_case_count": 5,
    "failure_disclosure_count": 3,
    "command_count": 23,
    "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": 56
  },
  "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": "67058cecebd13cd6e6fa54c009300cc145e8e999",
    "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": 25,
    "existing_count": 25,
    "missing_count": 0,
    "missing_paths": [],
    "sha256": "733cfff69f5bb93eb87cce2bd17695d88a40e88f9feca7db8a3d125128df5379"
  },
  "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": 7967,
      "sha256": "6450488d6ac4f80b0160161d5385bbf2f6aec2856076621a81027ae5c89fa38a"
    },
    {
      "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": 10135,
      "sha256": "bb8c72a9291e329c83890884af9b73535a6cb86fa435afe2d6ba2ff07d88a02c"
    },
    {
      "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": 10342,
      "sha256": "97f9ba949c23a60b00e9ba2ff279ca03ba517845cc7c62aa8a42645d58006c7e"
    },
    {
      "label": "trust_report",
      "path": "reports/security_trust_report.json",
      "exists": true,
      "bytes": 129571,
      "sha256": "5b05d1110b96a6a72300cc5913140a9d4c0bdf099b1232df8c3bce6e2d023514"
    },
    {
      "label": "python_compatibility",
      "path": "reports/python_compatibility.json",
      "exists": true,
      "bytes": 28298,
      "sha256": "8b48340618cc702a8d8f5aaf6ce6d05a1a5463a8008d06a28809671632b212da"
    },
    {
      "label": "registry_audit",
      "path": "reports/registry_audit.json",
      "exists": true,
      "bytes": 3183,
      "sha256": "8683ab3f627c2fe16c77dabe34798d2fb6942bb05c636cc35e4f6edd617c79d5"
    },
    {
      "label": "package_verification",
      "path": "reports/package_verification.json",
      "exists": true,
      "bytes": 19338,
      "sha256": "1372317d59e9ff19cfa4f69bfcfb5ddb9a9770f5628d9454a8f165e363c5b95b"
    },
    {
      "label": "install_simulation",
      "path": "reports/install_simulation.json",
      "exists": true,
      "bytes": 8604,
      "sha256": "3a707c08d4b0df167b835215f0f7696568a5a1e4099854d8a02647cdcd5b8b37"
    },
    {
      "label": "skill_os2_audit",
      "path": "reports/skill_os2_audit.json",
      "exists": true,
      "bytes": 14310,
      "sha256": "453a86240e7fe1a703615ba3ce9a97d940e9c552ee9e39d5cccbf7c3481dd507"
    },
    {
      "label": "world_class_evidence_plan",
      "path": "reports/world_class_evidence_plan.json",
      "exists": true,
      "bytes": 20828,
      "sha256": "0a836a86ad6c648d8c442a16cae7cdb17d3640a0ba6ec69c1290825ede6d152a"
    },
    {
      "label": "world_class_evidence_ledger",
      "path": "reports/world_class_evidence_ledger.json",
      "exists": true,
      "bytes": 22288,
      "sha256": "fe81833eab69292525975b347177bc7fcda6410f493fc60bd840a20e86ca0039"
    },
    {
      "label": "world_class_evidence_intake",
      "path": "reports/world_class_evidence_intake.json",
      "exists": true,
      "bytes": 19319,
      "sha256": "4506c836338c65a3a01b15b1f26a1fdd0a8ef520a1e5f1574ee89ce9d3bbeb29"
    },
    {
      "label": "world_class_evidence_preflight",
      "path": "reports/world_class_evidence_preflight.json",
      "exists": true,
      "bytes": 41208,
      "sha256": "725d10a6f951ab1e64f4e6a1cfa907404b51f598a753b5a0351e1381fef7cd9e"
    },
    {
      "label": "world_class_submission_review",
      "path": "reports/world_class_submission_review.json",
      "exists": true,
      "bytes": 13658,
      "sha256": "7693638c2e8369a8a179b3420c11090668f8f104f452dc370082dc9ebafe882d"
    },
    {
      "label": "world_class_operator_runbook",
      "path": "reports/world_class_operator_runbook.json",
      "exists": true,
      "bytes": 24899,
      "sha256": "f90d59c3e5866da33138869c1c5299350a43389d81e84ba466df794befb494fa"
    },
    {
      "label": "world_class_operator_runbook_markdown",
      "path": "reports/world_class_operator_runbook.md",
      "exists": true,
      "bytes": 15479,
      "sha256": "be79ee0f70a3ceed473c481562c5fddaee6cfb36c960ba15ae10c846d5809650"
    },
    {
      "label": "world_class_operator_runbook_html",
      "path": "reports/world_class_operator_runbook.html",
      "exists": true,
      "bytes": 21409,
      "sha256": "9a7be02a6990245c9dd1f72ced5928d80a3aaebea4647737c2aaf0b0a2f798df"
    },
    {
      "label": "world_class_claim_guard",
      "path": "reports/world_class_claim_guard.json",
      "exists": true,
      "bytes": 18596,
      "sha256": "abe7f7d60c0025e140373fadaefbed4063f285c140c74b9c7cfb464e354bb526"
    }
  ],
  "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 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"
  }
}