diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index 97d41dd..1d60e58 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,7 +3,7 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "0cc661195f0bff2d1365ddea52f69cb3a6d72b3b", + "commit": "6713b56d6b21158fac99e619fe45c580be72a703", "git_status": { "available": true, "dirty": false, @@ -17,9 +17,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "4f7164b6f04d9079f0497d3e84cefe9e2495ab9ee6fecaa3a74194f288fb8fca", - "source_contract_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544", - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", + "evidence_bundle_sha256": "25b549ca48ec334006fbf70ff184e76d56fca3192e72cb7ca2a37dafcdafdaa8", + "source_contract_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -54,7 +54,7 @@ }, "release_lock": { "ready": true, - "commit": "0cc661195f0bff2d1365ddea52f69cb3a6d72b3b", + "commit": "6713b56d6b21158fac99e619fe45c580be72a703", "status_scope": "generation-time status before this report is written", "reason": "clean generation-time HEAD" }, @@ -64,7 +64,7 @@ "existing_count": 24, "missing_count": 0, "missing_paths": [], - "sha256": "4f7164b6f04d9079f0497d3e84cefe9e2495ab9ee6fecaa3a74194f288fb8fca" + "sha256": "25b549ca48ec334006fbf70ff184e76d56fca3192e72cb7ca2a37dafcdafdaa8" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -138,7 +138,7 @@ "path": "reports/output_execution_runs.json", "exists": true, "bytes": 7967, - "sha256": "ce00448089a6b95f957d9c48fce6bd16efa9816d73c908ecc533b94dddf73af8" + "sha256": "00dbc38f651d9e4df728e1b4be1a7cba8a3913c997aab92f401841af4b72efb8" }, { "label": "blind_review", @@ -172,36 +172,36 @@ "label": "trust_report", "path": "reports/security_trust_report.json", "exists": true, - "bytes": 110333, - "sha256": "010b3f3967c4badaaa5c4d7b36475acc9ef149a8cb935216831ae2ae7f2b7fe8" + "bytes": 111439, + "sha256": "950daf3e77ad7102abac6bdaadfc9df1b1e56f321d17092423fb9a94e7466fc1" }, { "label": "python_compatibility", "path": "reports/python_compatibility.json", "exists": true, - "bytes": 23022, - "sha256": "c3a04d0b6b58425bc6446cd882413136b4c22916a0e345861443308d3724a5cc" + "bytes": 23413, + "sha256": "44e2c3c425798317d5b52b94915df2f56c541b5a62337f30b186494519bdf3a2" }, { "label": "registry_audit", "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "9d666ba878bcd9b53ba9a768218d89f2883e8cb339bdbdfbb27ddc056612a5f8" + "sha256": "ca9ec2947a9fcbab4e253b2e1b86a33df95f9d56b90be78bcf92f38d752e2213" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "7b58a0c7c756ce001190623ffca47c25c0abb0816f4c1ce32509309b31e2cd75" + "sha256": "f064d30b1de22d0e702cc3de0df04df84a11514f5790192a2e242e73b4569f5d" }, { "label": "install_simulation", "path": "reports/install_simulation.json", "exists": true, "bytes": 8604, - "sha256": "42e985aecb03c60483fcf54bcda1db1270f8515dbe40e6ea7ec27d4f485b3117" + "sha256": "f0cad15cbdff0dca69b544a506a7ae4d3d9a24598c81ecda216be7f33aebe4dd" }, { "label": "skill_os2_audit", @@ -263,8 +263,8 @@ "label": "world_class_claim_guard", "path": "reports/world_class_claim_guard.json", "exists": true, - "bytes": 17727, - "sha256": "0b31183a3f666895b343ee2b99c4dfd5f09d626213e29e8dc8051fab3219d2a5" + "bytes": 17927, + "sha256": "d8c41234cdabf679b6d56580a10647b7367844b81e38c7548f55ddefb3aaaa3c" } ], "missing_artifacts": [], diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index 7568cb3..83a5a70 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,9 +1,9 @@ # Benchmark Reproducibility Generated at: `2026-06-16` -Commit: `0cc661195f0bff2d1365ddea52f69cb3a6d72b3b` +Commit: `6713b56d6b21158fac99e619fe45c580be72a703` Working tree dirty at generation: `false` -Evidence bundle SHA256: `4f7164b6f04d9079f0497d3e84cefe9e2495ab9ee6fecaa3a74194f288fb8fca` +Evidence bundle SHA256: `25b549ca48ec334006fbf70ff184e76d56fca3192e72cb7ca2a37dafcdafdaa8` ## Summary @@ -12,8 +12,8 @@ Evidence bundle SHA256: `4f7164b6f04d9079f0497d3e84cefe9e2495ab9ee6fecaa3a74194f - methodology complete: `true` - required artifacts: `24` - missing artifacts: `0` -- source contract sha256: `ce3d8c67706a` -- archive sha256: `77d9bd77e4a9` +- source contract sha256: `909d0f5bad8e` +- archive sha256: `5c411a7ea189` - output cases: `5` - disclosed failure cases: `3` - reproduction commands: `22` @@ -50,7 +50,7 @@ This report proves local benchmark reproducibility only. It keeps external provi - algorithm: `sha256(path,label,exists,artifact_sha256)` - artifacts: `24` / `24` -- sha256: `4f7164b6f04d9079f0497d3e84cefe9e2495ab9ee6fecaa3a74194f288fb8fca` +- sha256: `25b549ca48ec334006fbf70ff184e76d56fca3192e72cb7ca2a37dafcdafdaa8` ## Methodology Sections @@ -72,16 +72,16 @@ This report proves local benchmark reproducibility only. It keeps external provi | output_cases | `evals/output/cases.jsonl` | present | `a6ae96857116` | | output_schema | `evals/output/schema.json` | present | `8ee340c95064` | | output_scorecard | `reports/output_quality_scorecard.json` | present | `0806258a8e08` | -| output_execution | `reports/output_execution_runs.json` | present | `ce00448089a6` | +| output_execution | `reports/output_execution_runs.json` | present | `00dbc38f651d` | | blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` | | review_adjudication | `reports/output_review_adjudication.json` | present | `240485a721af` | | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` | | runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` | -| trust_report | `reports/security_trust_report.json` | present | `010b3f3967c4` | -| python_compatibility | `reports/python_compatibility.json` | present | `c3a04d0b6b58` | -| registry_audit | `reports/registry_audit.json` | present | `9d666ba878bc` | -| package_verification | `reports/package_verification.json` | present | `7b58a0c7c756` | -| install_simulation | `reports/install_simulation.json` | present | `42e985aecb03` | +| trust_report | `reports/security_trust_report.json` | present | `950daf3e77ad` | +| python_compatibility | `reports/python_compatibility.json` | present | `44e2c3c42579` | +| registry_audit | `reports/registry_audit.json` | present | `ca9ec2947a9f` | +| package_verification | `reports/package_verification.json` | present | `f064d30b1de2` | +| install_simulation | `reports/install_simulation.json` | present | `f0cad15cbdff` | | skill_os2_audit | `reports/skill_os2_audit.json` | present | `57536bc67370` | | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `76a3f8e2b12b` | | world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `1cb74eaa978b` | @@ -90,7 +90,7 @@ This report proves local benchmark reproducibility only. It keeps external provi | world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `f5ca32d5ea8b` | | world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `260d5e03c52e` | | world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `04cc091b113f` | -| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `0b31183a3f66` | +| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `d8c41234cdab` | ## Reproduction Commands diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index 4fcdb0d..a896f64 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -4,14 +4,14 @@ "generated_at": "2026-06-16", "skill_dir": ".", "summary": { - "check_count": 30, - "pass_count": 30, + "check_count": 31, + "pass_count": 31, "warn_count": 0, "fail_count": 0, "decision": "consistent" }, "status_counts": { - "pass": 30, + "pass": 31, "warn": 0, "fail": 0 }, @@ -30,6 +30,7 @@ "reports/world_class_evidence_ledger.json", "reports/world_class_evidence_plan.json", "reports/world_class_evidence_intake.json", + "reports/world_class_evidence_preflight.json", "reports/world_class_submission_review.json", "reports/world_class_operator_runbook.json", "reports/skill_os2_coverage.json", @@ -55,6 +56,7 @@ "python3 scripts/render_skill_overview.py .": true, "python3 scripts/render_skill_interpretation.py .": true, "python3 scripts/render_review_viewer.py .": true, + "python3 scripts/render_world_class_preflight.py . --generated-at \"$GENERATED_AT\"": true, "python3 scripts/render_review_studio.py . --output-html reports/review-studio.html --output-json reports/review-studio.json": true, "python3 scripts/render_evidence_consistency.py . --generated-at \"$GENERATED_AT\"": true }, @@ -62,6 +64,7 @@ "python3 scripts/render_skill_overview.py .": true, "python3 scripts/render_skill_interpretation.py .": true, "python3 scripts/render_review_viewer.py .": true, + "python3 scripts/render_world_class_preflight.py . --generated-at \"$GENERATED_AT\"": true, "python3 scripts/render_review_studio.py . --output-html reports/review-studio.html --output-json reports/review-studio.json": true, "python3 scripts/render_evidence_consistency.py . --generated-at \"$GENERATED_AT\"": true } @@ -74,6 +77,7 @@ "python3 scripts/render_skill_overview.py .": true, "python3 scripts/render_skill_interpretation.py .": true, "python3 scripts/render_review_viewer.py .": true, + "python3 scripts/render_world_class_preflight.py . --generated-at \"$GENERATED_AT\"": true, "python3 scripts/render_review_studio.py . --output-html reports/review-studio.html --output-json reports/review-studio.json": true, "python3 scripts/render_evidence_consistency.py . --generated-at \"$GENERATED_AT\"": true }, @@ -81,6 +85,7 @@ "python3 scripts/render_skill_overview.py .": true, "python3 scripts/render_skill_interpretation.py .": true, "python3 scripts/render_review_viewer.py .": true, + "python3 scripts/render_world_class_preflight.py . --generated-at \"$GENERATED_AT\"": true, "python3 scripts/render_review_studio.py . --output-html reports/review-studio.html --output-json reports/review-studio.json": true, "python3 scripts/render_evidence_consistency.py . --generated-at \"$GENERATED_AT\"": true } @@ -91,6 +96,7 @@ "reports/skill-overview.json", "reports/skill-interpretation.json", "reports/review-viewer.json", + "reports/world_class_evidence_preflight.json", "reports/review-studio.json", "reports/evidence_consistency.json" ], @@ -111,8 +117,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "0cc661195f0bff2d1365ddea52f69cb3a6d72b3b", - "actual": "0cc661195f0bff2d1365ddea52f69cb3a6d72b3b", + "expected": "6713b56d6b21158fac99e619fe45c580be72a703", + "actual": "6713b56d6b21158fac99e619fe45c580be72a703", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -127,8 +133,8 @@ "release_lock_ready": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "source_contract_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544", - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", + "source_contract_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, @@ -140,8 +146,8 @@ "release_lock_ready": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "source_contract_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544", - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", + "source_contract_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, @@ -257,8 +263,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "0cc661195f0bff2d1365ddea52f69cb3a6d72b3b", - "actual": "0cc661195f0bff2d1365ddea52f69cb3a6d72b3b", + "expected": "6713b56d6b21158fac99e619fe45c580be72a703", + "actual": "6713b56d6b21158fac99e619fe45c580be72a703", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -273,8 +279,8 @@ "release_lock_ready": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "source_contract_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544", - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", + "source_contract_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, @@ -286,8 +292,8 @@ "release_lock_ready": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "source_contract_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544", - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", + "source_contract_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, @@ -1375,7 +1381,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 112 + "file_count": 113 }, { "path": "evals", @@ -1387,10 +1393,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 222 + "file_count": 224 } ], - "file_count": 401, + "file_count": 404, "folder_count": 4, "distribution": [ { @@ -1415,7 +1421,7 @@ }, { "label": "scripts", - "value": 112 + "value": 113 }, { "label": "evals", @@ -1423,7 +1429,7 @@ }, { "label": "reports", - "value": 222 + "value": 224 } ] }, @@ -1463,7 +1469,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 112 + "file_count": 113 }, { "path": "evals", @@ -1475,10 +1481,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 222 + "file_count": 224 } ], - "file_count": 401, + "file_count": 404, "folder_count": 4, "distribution": [ { @@ -1503,7 +1509,7 @@ }, { "label": "scripts", - "value": 112 + "value": 113 }, { "label": "evals", @@ -1511,7 +1517,7 @@ }, { "label": "reports", - "value": 222 + "value": 224 } ] }, @@ -1691,6 +1697,34 @@ ], "detail": "Benchmark reproducibility must not overstate public claim readiness." }, + { + "key": "preflight-world-class-boundary", + "label": "Preflight mirrors ledger without accepting evidence", + "status": "pass", + "expected": { + "pending_count": 4, + "source_check_count": 13, + "source_pass_count": 6, + "source_blocked_count": 7, + "ready_to_claim_world_class": false, + "preflight_counts_as_evidence": false, + "credential_value_exposed": false + }, + "actual": { + "pending_count": 4, + "source_check_count": 13, + "source_pass_count": 6, + "source_blocked_count": 7, + "ready_to_claim_world_class": false, + "preflight_counts_as_evidence": false, + "credential_value_exposed": false + }, + "paths": [ + "reports/world_class_evidence_ledger.json", + "reports/world_class_evidence_preflight.json" + ], + "detail": "Collection preflight may help operators gather evidence, but it must not print secrets or change world-class readiness." + }, { "key": "review-studio-no-overclaim", "label": "Review Studio does not overclaim pending world-class evidence", @@ -2078,19 +2112,19 @@ "label": "Skill OS 2.0 review summary mirrors current evidence", "status": "pass", "expected": [ - "score `91`", + "score `89`", "`16` gates", - "`3` warnings", + "`4` warnings", "`30` declared internal modules", - "`82 / 82` CLI help smoke checks passing across `112` scripts", - "`619` zip entries", - "archive with `619` entries", + "`83 / 83` CLI help smoke checks passing across `113` scripts", + "`623` zip entries", + "archive with `623` entries", "`12` installer permission checks enforced", "`0` permission failures", "`24` required artifacts", "`22` reproduction commands", "initial load `960/1000`", - "target count is `76`" + "target count is `77`" ], "actual": "all present", "paths": [ diff --git a/reports/evidence_consistency.md b/reports/evidence_consistency.md index 96a43f4..1bd98ea 100644 --- a/reports/evidence_consistency.md +++ b/reports/evidence_consistency.md @@ -5,8 +5,8 @@ Generated at: `2026-06-16` ## Summary - decision: `consistent` -- checks: `30` -- pass: `30` +- checks: `31` +- pass: `31` - warn: `0` - fail: `0` @@ -16,8 +16,8 @@ This gate compares generated evidence reports against each other. It does not cr | Check | Status | Detail | Paths | | --- | --- | --- | --- | -| Required report artifacts are readable | `pass` | The consistency gate can only be trusted when every source JSON report parses and every source Markdown report is readable. | `reports/benchmark_reproducibility.json`, `reports/skill-overview.json`, `reports/skill-interpretation.json`, `reports/adoption_drift_report.json`, `reports/world_class_evidence_ledger.json`, `reports/world_class_evidence_plan.json`, `reports/world_class_evidence_intake.json`, `reports/world_class_submission_review.json`, `reports/world_class_operator_runbook.json`, `reports/skill_os2_coverage.json`, `reports/review-studio.json`, `reports/package_verification.json`, `reports/install_simulation.json`, `reports/security_trust_report.json`, `reports/context_budget.json`, `reports/world_class_claim_guard.json`, `reports/skill-os-2-review.md` | -| Release evidence flow covers first-class reports | `pass` | Release refresh and clean-lock instructions must regenerate every first-class report before evidence consistency can be trusted. | `AGENTS.md`, `reports/benchmark_reproducibility.json`, `reports/skill-overview.json`, `reports/skill-interpretation.json`, `reports/review-viewer.json`, `reports/review-studio.json`, `reports/evidence_consistency.json` | +| Required report artifacts are readable | `pass` | The consistency gate can only be trusted when every source JSON report parses and every source Markdown report is readable. | `reports/benchmark_reproducibility.json`, `reports/skill-overview.json`, `reports/skill-interpretation.json`, `reports/adoption_drift_report.json`, `reports/world_class_evidence_ledger.json`, `reports/world_class_evidence_plan.json`, `reports/world_class_evidence_intake.json`, `reports/world_class_evidence_preflight.json`, `reports/world_class_submission_review.json`, `reports/world_class_operator_runbook.json`, `reports/skill_os2_coverage.json`, `reports/review-studio.json`, `reports/package_verification.json`, `reports/install_simulation.json`, `reports/security_trust_report.json`, `reports/context_budget.json`, `reports/world_class_claim_guard.json`, `reports/skill-os-2-review.md` | +| Release evidence flow covers first-class reports | `pass` | Release refresh and clean-lock instructions must regenerate every first-class report before evidence consistency can be trusted. | `AGENTS.md`, `reports/benchmark_reproducibility.json`, `reports/skill-overview.json`, `reports/skill-interpretation.json`, `reports/review-viewer.json`, `reports/world_class_evidence_preflight.json`, `reports/review-studio.json`, `reports/evidence_consistency.json` | | Benchmark release lock matches git dirty state | `pass` | The benchmark release lock must reflect the generation-time git dirty flag. | `reports/benchmark_reproducibility.json` | | overview embeds the benchmark commit | `pass` | Human-facing reports must point to the same benchmark release-lock commit. | `reports/benchmark_reproducibility.json`, `reports/skill-overview.json` | | overview embeds benchmark summary fields | `pass` | Selected summary fields must match exactly across generated reports. | `reports/benchmark_reproducibility.json`, `reports/skill-overview.json` | @@ -42,6 +42,7 @@ This gate compares generated evidence reports against each other. It does not cr | interpretation has a stable HTML contract | `pass` | Report output paths and language defaults are part of the user-facing contract. | `reports/skill-interpretation.json`, `reports/skill-interpretation.html` | | Coverage report mirrors world-class evidence boundary | `pass` | Blueprint coverage can be locally complete while public world-class evidence remains pending. | `reports/world_class_evidence_ledger.json`, `reports/skill_os2_coverage.json` | | Benchmark report mirrors world-class evidence boundary | `pass` | Benchmark reproducibility must not overstate public claim readiness. | `reports/world_class_evidence_ledger.json`, `reports/benchmark_reproducibility.json` | +| Preflight mirrors ledger without accepting evidence | `pass` | Collection preflight may help operators gather evidence, but it must not print secrets or change world-class readiness. | `reports/world_class_evidence_ledger.json`, `reports/world_class_evidence_preflight.json` | | Review Studio does not overclaim pending world-class evidence | `pass` | When world-class evidence is pending, Review Studio must stay in a review or warning posture. | `reports/world_class_evidence_ledger.json`, `reports/review-studio.json` | | Claim guard covers package and runtime claim surfaces | `pass` | The overclaim guard must scan package manifests, adapter metadata, security policy, and ledger surfaces before public readiness can be trusted. | `reports/world_class_claim_guard.json`, `manifest.json`, `agents/interface.yaml`, `dist/manifest.json`, `dist/targets/openai/adapter.json`, `evidence/world_class/README.md`, `security/permission_policy.json`, `reports/world_class_evidence_ledger.json` | | World-class evidence workflows cover every pending ledger entry | `pass` | Every pending world-class evidence key must have matching plan, intake, submission review, operator runbook, and Review Studio actions without counting planned work as completion. | `reports/world_class_evidence_ledger.json`, `reports/world_class_evidence_plan.json`, `reports/world_class_evidence_intake.json`, `reports/world_class_submission_review.json`, `reports/world_class_operator_runbook.json`, `reports/review-studio.json` | diff --git a/reports/review-studio.html b/reports/review-studio.html index a9a6477..23f7299 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -670,28 +670,28 @@
审查结论 review - Score 91/100 + Score 89/100

核心指标

-
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

4 blockers; local reproducible true

Blueprint21/21

2.0 coverage; extensions partial 0, planned 0; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

112 scripts scanned; secrets found

Py Compat0

177 files scanned for Python 3.11

Arch Debt0

899 largest lines; 8 watchlist; 64 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

173 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

619 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

+
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

4 blockers; local reproducible true

Blueprint21/21

2.0 coverage; extensions partial 0, planned 0; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

113 scripts scanned; secrets found

Py Compat0

180 files scanned for Python 3.11

Arch Debt0

899 largest lines; 8 watchlist; 65 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

175 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

623 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

审查闸门

-
通过

意图画布

intent confidence 100/100; Intent is clear enough to package the first routeable version.

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

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

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 960/1000; deferred 436837/120000; top deferred scripts 387626; resource governance governed; quality density 135.4

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 112 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 177 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

174 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 899 lines; 64 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

3/3 permissions approved; gaps 0; required file_write, network, subprocess

reports/security_trust_report.json + security/permission_policy.json 证据
通过

权限探针

4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4

reports/runtime_permission_probes.json 证据
通过

组合治理

12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low

reports/adoption_drift_report.json 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

reports/registry_audit.json + reports/install_simulation.json 证据
通过

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md 证据
+
通过

意图画布

intent confidence 100/100; Intent is clear enough to package the first routeable version.

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

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

reports/output_quality_scorecard.json 证据
关注

上下文

initial load 960/1000; deferred 442670/120000; top deferred scripts 393459; resource governance needs-review; quality density 135.4

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 113 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 180 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

177 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 899 lines; 65 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

3/3 permissions approved; gaps 0; required file_write, network, subprocess

reports/security_trust_report.json + security/permission_policy.json 证据
通过

权限探针

4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4

reports/runtime_permission_probes.json 证据
通过

组合治理

12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low

reports/adoption_drift_report.json 证据
关注

人工批准

0 active waivers; 2 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

reports/registry_audit.json + reports/install_simulation.json 证据
通过

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

阻断事项

无。

-

关注事项

+

关注事项

修复动作

-
关注

输出实验

补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。

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。
修复位置
evals/output/cases.jsonl + reports/output_quality_scorecard.md + reports/output_review_kit.html + reports/output_review_adjudication.md
验证命令
python3 scripts/adjudicate_output_review.py --write-template && python3 scripts/yao.py output-review
关注

人工批准

对保留的 warning 写入 reviewer、理由、范围和到期时间,或修掉 warning。

warning 可以被接受,但必须可审计、会过期,并且不能掩盖 blocker。
修复位置
reports/review_waivers.md
验证命令
python3 scripts/render_review_waivers.py .
关注

世界证据

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。

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。
修复位置
reports/world_class_operator_runbook.html + reports/world_class_evidence_ledger.md + reports/world_class_evidence_intake.md + reports/world_class_submission_review.md
验证命令
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 .

证据采集

以下条目仍需真实外部或人工证据;提交文件、校验命令和阻断检查必须同时闭环。

pending · external

Provider Holdout

model-executed 0; token-observed 0

提交
evidence/world_class/submissions/provider-holdout.json
模板
evidence/world_class/templates/provider-holdout.intake.json
阻断
2 blocked / 1 pass
下一步
Run provider-backed holdout cases with real credentials and commit only aggregate evidence.
阻断检查
  • Provider model runmodel_executed_count: 0 / >0Run provider-backed output-exec with real credentials.
  • Token usage observedtoken_observed_count: 0 / >0Provider execution should return non-estimated token usage.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60
  2. python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  3. Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.
pending · human

Human Adjudication

0/5 decisions; pending 5

提交
evidence/world_class/submissions/human-adjudication.json
模板
evidence/world_class/templates/human-adjudication.intake.json
阻断
2 blocked / 2 pass
下一步
Record real A/B choices in the decision template, then regenerate adjudication.
阻断检查
  • No pending decisionspending_count: 5 / ==0Record a reviewer choice for every pair.
  • Judgments completejudgment_count: 0 / ==pair_countEvery pair needs one valid human judgment.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. python3 scripts/yao.py output-review-kit --write-template
  2. Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.
  3. python3 scripts/adjudicate_output_review.py --write-template
pending · external

Native Permission Enforcement

native-enforced targets 0; installer-enforced targets 4

提交
evidence/world_class/submissions/native-permission-enforcement.json
模板
evidence/world_class/templates/native-permission-enforcement.intake.json
阻断
1 blocked / 2 pass
下一步
Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.
阻断检查
  • Native enforcementnative_enforcement_count: 0 / >0Collect real target-client or external runtime guard proof.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.
  2. Update the generated target adapter only when the guard is actually enforced by that target.
  3. python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip
pending · external

Native Client Telemetry

external source events 0; adoption samples 0

提交
evidence/world_class/submissions/native-client-telemetry.json
模板
evidence/world_class/templates/native-client-telemetry.intake.json
阻断
2 blocked / 1 pass
下一步
Install a real client against the native host and import production metadata-only events.
阻断检查
  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
  • Adoption sampleadoption_sample_count: 0 / >0Telemetry must include adoption outcome evidence.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. 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>/
  2. Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.
  3. python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl
+
关注

输出实验

补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。

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。
修复位置
evals/output/cases.jsonl + reports/output_quality_scorecard.md + reports/output_review_kit.html + reports/output_review_adjudication.md
验证命令
python3 scripts/adjudicate_output_review.py --write-template && python3 scripts/yao.py output-review
关注

上下文

压缩或拆分高成本 deferred resources,保留最小可路由上下文。

初始加载可以安全,但后续 references、scripts、evals 体量过大时,reviewer 仍需要看到维护和读取成本。
修复位置
SKILL.md + references/ + scripts/ + evals/
验证命令
python3 scripts/render_context_reports.py
关注

人工批准

对保留的 warning 写入 reviewer、理由、范围和到期时间,或修掉 warning。

warning 可以被接受,但必须可审计、会过期,并且不能掩盖 blocker。
修复位置
reports/review_waivers.md
验证命令
python3 scripts/render_review_waivers.py .
关注

世界证据

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。

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。
修复位置
reports/world_class_operator_runbook.html + reports/world_class_evidence_ledger.md + reports/world_class_evidence_intake.md + reports/world_class_submission_review.md
验证命令
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 .

证据采集

以下条目仍需真实外部或人工证据;提交文件、校验命令和阻断检查必须同时闭环。

pending · external

Provider Holdout

model-executed 0; token-observed 0

提交
evidence/world_class/submissions/provider-holdout.json
模板
evidence/world_class/templates/provider-holdout.intake.json
阻断
2 blocked / 1 pass
下一步
Run provider-backed holdout cases with real credentials and commit only aggregate evidence.
阻断检查
  • Provider model runmodel_executed_count: 0 / >0Run provider-backed output-exec with real credentials.
  • Token usage observedtoken_observed_count: 0 / >0Provider execution should return non-estimated token usage.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60
  2. python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  3. Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.
pending · human

Human Adjudication

0/5 decisions; pending 5

提交
evidence/world_class/submissions/human-adjudication.json
模板
evidence/world_class/templates/human-adjudication.intake.json
阻断
2 blocked / 2 pass
下一步
Record real A/B choices in the decision template, then regenerate adjudication.
阻断检查
  • No pending decisionspending_count: 5 / ==0Record a reviewer choice for every pair.
  • Judgments completejudgment_count: 0 / ==pair_countEvery pair needs one valid human judgment.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. python3 scripts/yao.py output-review-kit --write-template
  2. Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.
  3. python3 scripts/adjudicate_output_review.py --write-template
pending · external

Native Permission Enforcement

native-enforced targets 0; installer-enforced targets 4

提交
evidence/world_class/submissions/native-permission-enforcement.json
模板
evidence/world_class/templates/native-permission-enforcement.intake.json
阻断
1 blocked / 2 pass
下一步
Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.
阻断检查
  • Native enforcementnative_enforcement_count: 0 / >0Collect real target-client or external runtime guard proof.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.
  2. Update the generated target adapter only when the guard is actually enforced by that target.
  3. python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip
pending · external

Native Client Telemetry

external source events 0; adoption samples 0

提交
evidence/world_class/submissions/native-client-telemetry.json
模板
evidence/world_class/templates/native-client-telemetry.intake.json
阻断
2 blocked / 1 pass
下一步
Install a real client against the native host and import production metadata-only events.
阻断检查
  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
  • Adoption sampleadoption_sample_count: 0 / >0Telemetry must include adoption outcome evidence.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. 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>/
  2. Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.
  3. python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl
@@ -743,17 +743,17 @@
-

上下文

initial load 960/1000; deferred 436837/120000; top deferred scripts 387626; resource governance governed; quality density 135.4

+

上下文

initial load 960/1000; deferred 442670/120000; top deferred scripts 393459; resource governance needs-review; quality density 135.4

编译证据

Review reports/compiled_targets.md before packaging to inspect target adapter modes, generated files, preserved semantics, warnings, and unsupported features.

-

信任报告

Secret
0
脚本数
112
网络脚本
3
Help 失败
0
包体哈希
ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544
+

信任报告

Secret
0
脚本数
113
网络脚本
3
Help 失败
0
包体哈希
909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1

安全边界

高风险 secret、远程 inline execution、缺失依赖策略或无法解释的脚本接口应阻断 governed release。

-

Python 兼容

目标 Python
3.11
文件数
177
问题数
0
语法错误
0
F-string 3.11
0
+

Python 兼容

目标 Python
3.11
文件数
180
问题数
0
语法错误
0
F-string 3.11
0

解释器边界

CI 和发布审查以 Python 3.11 兼容为底线;本地更高版本允许的新语法不能绕过兼容门禁。

@@ -781,7 +781,7 @@

人工批准

warning 可以被有边界地接受,但必须写入 reviewer、理由、范围和到期时间;blocker 与 world-class 完成证据不能通过 waiver 变成通过。

-

批准概况

0 active waivers; 1 warning gates still need reviewer decision

+

批准概况

0 active waivers; 2 warning gates still need reviewer decision

批准台账

Waiver Count
0
Active Count
0
Expired Count
0
Invalid Count
0
覆盖 Gate
0

批准候选

@@ -821,18 +821,18 @@
-

声明守卫

台账可声明
台账待补
4
声明面
173
违规数
0
Overclaim Guard Active
+

声明守卫

台账可声明
台账待补
4
声明面
175
违规数
0
Overclaim Guard Active

声明边界

claim guard 扫描 README、docs 和 reports 中的完成态表述;ledger 未 ready 时,任何英文完成断言、true 状态声明或中文完成态都会阻断发布审查。

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

-

包体元数据

名称
yao-meta-skill
版本
1.1.0
Maturity
governed
Owner
Yao Team
License
MIT
信任级别
local
目标平台
openai, claude, generic, agent-skills-compatible, vscode
兼容通过
6/6
归档哈希
77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf
+

包体元数据

名称
yao-meta-skill
版本
1.1.0
Maturity
governed
Owner
Yao Team
License
MIT
信任级别
local
目标平台
openai, claude, generic, agent-skills-compatible, vscode
兼容通过
6/6
归档哈希
5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

-

包体验证

目标数
4
Adapter
4
归档存在
Zip 条目
619
失败数
0
警告数
0
归档哈希
77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf
+

包体验证

目标数
4
Adapter
4
归档存在
Zip 条目
623
失败数
0
警告数
0
归档哈希
5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e
diff --git a/reports/review-studio.json b/reports/review-studio.json index 466d7c7..b6a9ff7 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -4,11 +4,11 @@ "skill_dir": ".", "summary": { "decision": "review", - "world_class_score": 91, + "world_class_score": 89, "gate_count": 16, "blocker_count": 0, - "warning_count": 3, - "action_count": 3, + "warning_count": 4, + "action_count": 4, "annotation_count": 0, "open_annotation_count": 0, "open_annotation_blocker_count": 0, @@ -42,8 +42,8 @@ { "key": "context-budget", "label": "上下文", - "status": "pass", - "detail": "initial load 960/1000; deferred 436837/120000; top deferred scripts 387626; resource governance governed; quality density 135.4", + "status": "warn", + "detail": "initial load 960/1000; deferred 442670/120000; top deferred scripts 393459; resource governance needs-review; quality density 135.4", "evidence": "reports/context_budget.json", "link": "context_budget.md" }, @@ -59,7 +59,7 @@ "key": "trust-report", "label": "信任报告", "status": "pass", - "detail": "0 secrets; 112 scripts; 3 network-capable scripts; 0 help smoke failures", + "detail": "0 secrets; 113 scripts; 3 network-capable scripts; 0 help smoke failures", "evidence": "reports/security_trust_report.json", "link": "security_trust_report.md" }, @@ -67,7 +67,7 @@ "key": "python-compat", "label": "Python 兼容", "status": "pass", - "detail": "Python 3.11; 177 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards", + "detail": "Python 3.11; 180 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards", "evidence": "reports/python_compatibility.json", "link": "python_compatibility.md" }, @@ -75,7 +75,7 @@ "key": "architecture-maintainability", "label": "架构维护", "status": "pass", - "detail": "174 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 899 lines; 64 CLI handlers; 18 in entrypoint", + "detail": "177 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 899 lines; 65 CLI handlers; 18 in entrypoint", "evidence": "reports/architecture_maintainability.json", "link": "architecture_maintainability.md" }, @@ -115,7 +115,7 @@ "key": "review-waivers", "label": "人工批准", "status": "warn", - "detail": "0 active waivers; 1 warning gates still need reviewer decision", + "detail": "0 active waivers; 2 warning gates still need reviewer decision", "evidence": "reports/review_waivers.json", "link": "review_waivers.md" }, @@ -154,11 +154,19 @@ "evidence": "reports/output_quality_scorecard.json", "link": "output_quality_scorecard.md" }, + { + "key": "context-budget", + "label": "上下文", + "status": "warn", + "detail": "initial load 960/1000; deferred 442670/120000; top deferred scripts 393459; resource governance needs-review; quality density 135.4", + "evidence": "reports/context_budget.json", + "link": "context_budget.md" + }, { "key": "review-waivers", "label": "人工批准", "status": "warn", - "detail": "0 active waivers; 1 warning gates still need reviewer decision", + "detail": "0 active waivers; 2 warning gates still need reviewer decision", "evidence": "reports/review_waivers.json", "link": "review_waivers.md" }, @@ -235,6 +243,53 @@ "verification_command": "python3 scripts/adjudicate_output_review.py --write-template && python3 scripts/yao.py output-review", "evidence_steps": [] }, + { + "gate_key": "context-budget", + "label": "上下文", + "status": "warn", + "priority": "warning", + "summary": "压缩或拆分高成本 deferred resources,保留最小可路由上下文。", + "why": "初始加载可以安全,但后续 references、scripts、evals 体量过大时,reviewer 仍需要看到维护和读取成本。", + "source_fix": "SKILL.md + references/ + scripts/ + evals/", + "source_refs": [ + { + "path": "SKILL.md", + "label": "entrypoint", + "kind": "source", + "line": 9, + "exists": true, + "link": "../SKILL.md" + }, + { + "path": "reports/context_budget.md", + "label": "context budget", + "kind": "report", + "line": 1, + "exists": true, + "link": "context_budget.md" + }, + { + "path": "scripts/resource_boundary_check.py", + "label": "resource boundary checker", + "kind": "source", + "line": 44, + "exists": true, + "link": "../scripts/resource_boundary_check.py" + }, + { + "path": "references/skill-engineering-method.md", + "label": "skill engineering method", + "kind": "method", + "line": 208, + "exists": true, + "link": "../references/skill-engineering-method.md" + } + ], + "evidence": "reports/context_budget.json", + "evidence_link": "context_budget.md", + "verification_command": "python3 scripts/render_context_reports.py", + "evidence_steps": [] + }, { "gate_key": "review-waivers", "label": "人工批准", @@ -1193,7 +1248,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 112 + "file_count": 113 }, { "path": "evals", @@ -1205,10 +1260,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 222 + "file_count": 224 } ], - "file_count": 401, + "file_count": 404, "folder_count": 4, "distribution": [ { @@ -1233,7 +1288,7 @@ }, { "label": "scripts", - "value": 112 + "value": 113 }, { "label": "evals", @@ -1241,7 +1296,7 @@ }, { "label": "reports", - "value": 222 + "value": 224 } ] }, @@ -1363,7 +1418,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 112 + "file_count": 113 }, { "path": "evals", @@ -1375,7 +1430,7 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 222 + "file_count": 224 } ], "strengths": [ @@ -1680,9 +1735,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "4f7164b6f04d9079f0497d3e84cefe9e2495ab9ee6fecaa3a74194f288fb8fca", - "source_contract_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544", - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", + "evidence_bundle_sha256": "25b549ca48ec334006fbf70ff184e76d56fca3192e72cb7ca2a37dafcdafdaa8", + "source_contract_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -1704,7 +1759,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "0cc661195f0bff2d1365ddea52f69cb3a6d72b3b", + "commit": "6713b56d6b21158fac99e619fe45c580be72a703", "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.", @@ -1788,8 +1843,8 @@ "failures": [] }, "trust_security": { - "scanned_files": 199, - "script_count": 112, + "scanned_files": 200, + "script_count": 113, "internal_module_count": 30, "secret_findings": 0, "dependency_files": [ @@ -1798,18 +1853,18 @@ "network_script_count": 3, "network_policy_covered_count": 3, "network_policy_missing_count": 0, - "file_write_script_count": 69, + "file_write_script_count": 70, "permission_required_count": 3, "permission_approved_count": 3, "permission_missing_count": 0, "permission_invalid_count": 0, "permission_expired_count": 0, - "help_smoke_checked_count": 82, + "help_smoke_checked_count": 83, "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 199, - "package_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544" + "package_hash_file_count": 200, + "package_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1" }, "skill_atlas": { "skill_count": 12, @@ -1847,8 +1902,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544", - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf" + "package_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e" }, "compatibility": { "openai": "pass", @@ -1879,7 +1934,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1895,8 +1950,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", - "archive_entry_count": 619, + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", + "archive_entry_count": 623, "failure_count": 0, "warning_count": 0 }, @@ -1907,7 +1962,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 619, + "archive_entry_count": 623, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1974,12 +2029,12 @@ { "field": "archive_sha256", "from": "", - "to": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf" + "to": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544" + "to": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1" } ] }, @@ -4374,7 +4429,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.26, + "duration_ms": 26.42, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4397,7 +4452,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.84, + "duration_ms": 26.21, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4425,7 +4480,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.71, + "duration_ms": 29.52, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4476,7 +4531,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.07, + "duration_ms": 27.97, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4499,7 +4554,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.39, + "duration_ms": 26.12, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4526,7 +4581,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.35, + "duration_ms": 26.11, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4549,7 +4604,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.48, + "duration_ms": 26.05, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4578,7 +4633,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.29, + "duration_ms": 25.87, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5299,7 +5354,7 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "0cc661195f0bff2d1365ddea52f69cb3a6d72b3b", + "commit": "6713b56d6b21158fac99e619fe45c580be72a703", "git_status": { "available": true, "dirty": false, @@ -5313,9 +5368,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "4f7164b6f04d9079f0497d3e84cefe9e2495ab9ee6fecaa3a74194f288fb8fca", - "source_contract_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544", - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", + "evidence_bundle_sha256": "25b549ca48ec334006fbf70ff184e76d56fca3192e72cb7ca2a37dafcdafdaa8", + "source_contract_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -5350,7 +5405,7 @@ }, "release_lock": { "ready": true, - "commit": "0cc661195f0bff2d1365ddea52f69cb3a6d72b3b", + "commit": "6713b56d6b21158fac99e619fe45c580be72a703", "status_scope": "generation-time status before this report is written", "reason": "clean generation-time HEAD" }, @@ -5360,7 +5415,7 @@ "existing_count": 24, "missing_count": 0, "missing_paths": [], - "sha256": "4f7164b6f04d9079f0497d3e84cefe9e2495ab9ee6fecaa3a74194f288fb8fca" + "sha256": "25b549ca48ec334006fbf70ff184e76d56fca3192e72cb7ca2a37dafcdafdaa8" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -5434,7 +5489,7 @@ "path": "reports/output_execution_runs.json", "exists": true, "bytes": 7967, - "sha256": "ce00448089a6b95f957d9c48fce6bd16efa9816d73c908ecc533b94dddf73af8" + "sha256": "00dbc38f651d9e4df728e1b4be1a7cba8a3913c997aab92f401841af4b72efb8" }, { "label": "blind_review", @@ -5468,36 +5523,36 @@ "label": "trust_report", "path": "reports/security_trust_report.json", "exists": true, - "bytes": 110333, - "sha256": "010b3f3967c4badaaa5c4d7b36475acc9ef149a8cb935216831ae2ae7f2b7fe8" + "bytes": 111439, + "sha256": "950daf3e77ad7102abac6bdaadfc9df1b1e56f321d17092423fb9a94e7466fc1" }, { "label": "python_compatibility", "path": "reports/python_compatibility.json", "exists": true, - "bytes": 23022, - "sha256": "c3a04d0b6b58425bc6446cd882413136b4c22916a0e345861443308d3724a5cc" + "bytes": 23413, + "sha256": "44e2c3c425798317d5b52b94915df2f56c541b5a62337f30b186494519bdf3a2" }, { "label": "registry_audit", "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "9d666ba878bcd9b53ba9a768218d89f2883e8cb339bdbdfbb27ddc056612a5f8" + "sha256": "ca9ec2947a9fcbab4e253b2e1b86a33df95f9d56b90be78bcf92f38d752e2213" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "7b58a0c7c756ce001190623ffca47c25c0abb0816f4c1ce32509309b31e2cd75" + "sha256": "f064d30b1de22d0e702cc3de0df04df84a11514f5790192a2e242e73b4569f5d" }, { "label": "install_simulation", "path": "reports/install_simulation.json", "exists": true, "bytes": 8604, - "sha256": "42e985aecb03c60483fcf54bcda1db1270f8515dbe40e6ea7ec27d4f485b3117" + "sha256": "f0cad15cbdff0dca69b544a506a7ae4d3d9a24598c81ecda216be7f33aebe4dd" }, { "label": "skill_os2_audit", @@ -5559,8 +5614,8 @@ "label": "world_class_claim_guard", "path": "reports/world_class_claim_guard.json", "exists": true, - "bytes": 17727, - "sha256": "0b31183a3f666895b343ee2b99c4dfd5f09d626213e29e8dc8051fab3219d2a5" + "bytes": 17927, + "sha256": "d8c41234cdabf679b6d56580a10647b7367844b81e38c7548f55ddefb3aaaa3c" } ], "missing_artifacts": [], @@ -5824,7 +5879,7 @@ "label": "Trust Security", "status": "pass", "objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.", - "current": "112 scripts; secrets 0; help failures 0", + "current": "113 scripts; secrets 0; help failures 0", "command": "python3 scripts/yao.py trust .", "test": "python3 tests/verify_trust_check.py", "evidence": [ @@ -5898,7 +5953,7 @@ "label": "Registry Distribution", "status": "pass", "objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.", - "current": "archive entries 619; install failures 0", + "current": "archive entries 623; 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": [ @@ -6307,7 +6362,7 @@ "label": "Evidence Consistency", "status": "pass", "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.", - "current": "29 consistency checks", + "current": "31 consistency checks", "command": "make ci-test", "test": "tests/verify_evidence_consistency.py", "evidence": [ @@ -11391,8 +11446,8 @@ "ok": true, "skill_dir": ".", "summary": { - "scanned_files": 199, - "script_count": 112, + "scanned_files": 200, + "script_count": 113, "internal_module_count": 30, "secret_findings": 0, "dependency_files": [ @@ -11401,18 +11456,18 @@ "network_script_count": 3, "network_policy_covered_count": 3, "network_policy_missing_count": 0, - "file_write_script_count": 69, + "file_write_script_count": 70, "permission_required_count": 3, "permission_approved_count": 3, "permission_missing_count": 0, "permission_invalid_count": 0, "permission_expired_count": 0, - "help_smoke_checked_count": 82, + "help_smoke_checked_count": 83, "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 199, - "package_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544" + "package_hash_file_count": 200, + "package_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1" }, "failures": [], "warnings": [], @@ -12387,6 +12442,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/render_world_class_preflight.py", + "interface": "cli", + "interface_declared": true, + "interface_reason": "Renders a preflight checklist 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", @@ -13034,9 +13103,9 @@ "help_smoke": { "enabled": true, "timeout_seconds": 5.0, - "candidate_count": 82, - "checked_count": 82, - "passed_count": 82, + "candidate_count": 83, + "checked_count": 83, + "passed_count": 83, "failed_count": 0, "skipped_count": 30, "failed_scripts": [], @@ -13691,6 +13760,16 @@ "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_preflight.py", + "command": "python3 scripts/render_world_class_preflight.py --help", + "returncode": 0, + "timed_out": false, + "passed": true, + "has_help_text": true, + "stdout_excerpt": "usage: render_world_class_preflight.py [-h]\n [--submissions-dir SUBMISSIONS_DIR]\n [--output-json OUTPUT_JSON]\n [--output-md OU", + "stderr_excerpt": "" + }, { "path": "scripts/render_world_class_submission_review.py", "command": "python3 scripts/render_world_class_submission_review.py --help", @@ -14094,6 +14173,7 @@ "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_preflight.py", "scripts/render_world_class_submission_review.py", "scripts/run_conformance_suite.py", "scripts/run_description_optimization_suite.py", @@ -14170,11 +14250,11 @@ "python_compatibility": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "root": ".", "summary": { "target_python": "3.11", - "file_count": 177, + "file_count": 180, "issue_count": 0, "syntax_error_count": 0, "fstring_311_violation_count": 0, @@ -14287,6 +14367,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "scripts/evidence_consistency_release.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "scripts/evidence_consistency_world_class.py", "ok": true, @@ -14611,6 +14697,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "scripts/render_world_class_preflight.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "scripts/render_world_class_submission_review.py", "ok": true, @@ -15241,6 +15333,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "tests/verify_world_class_preflight.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "tests/verify_world_class_submission_review.py", "ok": true, @@ -15266,12 +15364,12 @@ "generated_at": "2026-06-16", "skill_dir": ".", "summary": { - "python_file_count": 174, - "script_file_count": 111, - "test_file_count": 63, - "internal_module_count": 32, - "cli_script_count": 81, - "command_handler_count": 64, + "python_file_count": 177, + "script_file_count": 113, + "test_file_count": 64, + "internal_module_count": 33, + "cli_script_count": 82, + "command_handler_count": 65, "entrypoint_command_handler_count": 18, "command_module_count": 6, "warn_line_threshold": 900, @@ -15293,7 +15391,7 @@ }, { "path": "scripts/yao_cli_parser.py", - "lines": 810, + "lines": 821, "kind": "internal-module", "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." @@ -15347,6 +15445,13 @@ "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." }, + { + "path": "scripts/render_evidence_consistency.py", + "lines": 707, + "kind": "cli-script", + "severity": "pass", + "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." + }, { "path": "scripts/apply_adaptation.py", "lines": 706, @@ -15360,13 +15465,6 @@ "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." } ], "watchlist": [ @@ -15379,7 +15477,7 @@ }, { "path": "scripts/yao_cli_parser.py", - "lines": 810, + "lines": 821, "kind": "internal-module", "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." @@ -15437,21 +15535,23 @@ "context_budget": { "ok": true, "failures": [], - "warnings": [], + "warnings": [ + "Deferred resource footprint is high: 442670 estimated tokens across references/scripts/evals. Keep Review Studio warnings visible until the largest resource dirs are split, archived, or justified." + ], "stats": { "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 767, - "other_text_tokens": 1377236, + "other_text_tokens": 1395152, "estimated_initial_load_tokens": 960, - "estimated_total_text_tokens": 1378003, - "deferred_resource_tokens": 436837, + "estimated_total_text_tokens": 1395919, + "deferred_resource_tokens": 442670, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 387626, - "file_count": 111 + "estimated_tokens": 393459, + "file_count": 113 }, { "path": "references", @@ -15467,37 +15567,38 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 387626, - "file_count": 111 + "estimated_tokens": 393459, + "file_count": 113 } ], "deferred_resource_governance": { - "status": "governed", + "status": "needs-review", "large_dir_count": 1, - "governed_large_dir_count": 1, + "governed_large_dir_count": 0, "directories": [ { - "status": "governed", + "status": "needs-review", "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": [], + "missing": [ + "trust report covers scripts" + ], "path": "scripts", - "estimated_tokens": 387626, - "file_count": 111, + "estimated_tokens": 393459, + "file_count": 113, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } ], - "summary": "Large deferred resources are indexed and backed by evidence." + "summary": "One or more large deferred resource directories still need explicit governance evidence." }, - "relevant_file_count": 565, + "relevant_file_count": 573, "unused_resource_dirs": [], "quality_signal_points": 130, "quality_density": 135.4 @@ -17365,7 +17466,7 @@ "adoption_drift": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-15T17:08:05Z", + "generated_at": "2026-06-15T17:38:29Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -19718,9 +19819,9 @@ "summary": { "ledger_ready_to_claim_world_class": false, "ledger_pending_count": 4, - "claim_surface_count": 173, - "json_claim_surface_count": 85, - "metadata_claim_surface_count": 86, + "claim_surface_count": 175, + "json_claim_surface_count": 86, + "metadata_claim_surface_count": 87, "package_claim_surface_count": 17, "violation_count": 0, "overclaim_guard_active": true, @@ -20382,6 +20483,14 @@ "path": "reports/world_class_evidence_plan.md", "violation_count": 0 }, + { + "path": "reports/world_class_evidence_preflight.json", + "violation_count": 0 + }, + { + "path": "reports/world_class_evidence_preflight.md", + "violation_count": 0 + }, { "path": "reports/world_class_operator_runbook.html", "violation_count": 0 @@ -20480,8 +20589,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544", - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf" + "package_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e" }, "compatibility": { "openai": "pass", @@ -20512,7 +20621,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -20537,7 +20646,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544" + "package_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1" } ] }, @@ -20560,8 +20669,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", - "archive_entry_count": 619, + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", + "archive_entry_count": 623, "failure_count": 0, "warning_count": 0 }, @@ -21226,7 +21335,7 @@ "installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill", "summary": { "archive_present": true, - "archive_entry_count": 619, + "archive_entry_count": 623, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -21568,12 +21677,12 @@ { "field": "archive_sha256", "from": "", - "to": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf" + "to": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544" + "to": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1" } ] }, diff --git a/reports/review-viewer.json b/reports/review-viewer.json index dfbc149..7f4b37c 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -513,7 +513,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 112 + "file_count": 113 }, { "path": "evals", @@ -525,10 +525,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 222 + "file_count": 224 } ], - "file_count": 401, + "file_count": 404, "folder_count": 4, "distribution": [ { @@ -553,7 +553,7 @@ }, { "label": "scripts", - "value": 112 + "value": 113 }, { "label": "evals", @@ -561,7 +561,7 @@ }, { "label": "reports", - "value": 222 + "value": 224 } ] }, @@ -683,7 +683,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 112 + "file_count": 113 }, { "path": "evals", @@ -695,7 +695,7 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 222 + "file_count": 224 } ], "strengths": [ @@ -1000,9 +1000,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "4f7164b6f04d9079f0497d3e84cefe9e2495ab9ee6fecaa3a74194f288fb8fca", - "source_contract_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544", - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", + "evidence_bundle_sha256": "25b549ca48ec334006fbf70ff184e76d56fca3192e72cb7ca2a37dafcdafdaa8", + "source_contract_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -1024,7 +1024,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "0cc661195f0bff2d1365ddea52f69cb3a6d72b3b", + "commit": "6713b56d6b21158fac99e619fe45c580be72a703", "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.", @@ -1108,8 +1108,8 @@ "failures": [] }, "trust_security": { - "scanned_files": 199, - "script_count": 112, + "scanned_files": 200, + "script_count": 113, "internal_module_count": 30, "secret_findings": 0, "dependency_files": [ @@ -1118,18 +1118,18 @@ "network_script_count": 3, "network_policy_covered_count": 3, "network_policy_missing_count": 0, - "file_write_script_count": 69, + "file_write_script_count": 70, "permission_required_count": 3, "permission_approved_count": 3, "permission_missing_count": 0, "permission_invalid_count": 0, "permission_expired_count": 0, - "help_smoke_checked_count": 82, + "help_smoke_checked_count": 83, "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 199, - "package_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544" + "package_hash_file_count": 200, + "package_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1" }, "skill_atlas": { "skill_count": 12, @@ -1167,8 +1167,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544", - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf" + "package_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e" }, "compatibility": { "openai": "pass", @@ -1199,7 +1199,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1215,8 +1215,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", - "archive_entry_count": 619, + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", + "archive_entry_count": 623, "failure_count": 0, "warning_count": 0 }, @@ -1227,7 +1227,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 619, + "archive_entry_count": 623, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1294,12 +1294,12 @@ { "field": "archive_sha256", "from": "", - "to": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf" + "to": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544" + "to": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1" } ] }, diff --git a/reports/skill-interpretation.html b/reports/skill-interpretation.html index 82493c1..e801600 100644 --- a/reports/skill-interpretation.html +++ b/reports/skill-interpretation.html @@ -930,7 +930,7 @@

让 reviewer 快速确认关键文件、目录和资产分布。Lets reviewers confirm key files, directories, and asset distribution quickly.

-
资产分布Asset Distribution401项401 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
+
资产分布Asset Distribution404项404 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index 6caa6b7..562f4fd 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -513,7 +513,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 112 + "file_count": 113 }, { "path": "evals", @@ -525,10 +525,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 222 + "file_count": 224 } ], - "file_count": 401, + "file_count": 404, "folder_count": 4, "distribution": [ { @@ -553,7 +553,7 @@ }, { "label": "scripts", - "value": 112 + "value": 113 }, { "label": "evals", @@ -561,7 +561,7 @@ }, { "label": "reports", - "value": 222 + "value": 224 } ] }, @@ -687,7 +687,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 112 + "file_count": 113 }, { "path": "evals", @@ -699,7 +699,7 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 222 + "file_count": 224 } ], "strengths": [ @@ -1004,9 +1004,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "4f7164b6f04d9079f0497d3e84cefe9e2495ab9ee6fecaa3a74194f288fb8fca", - "source_contract_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544", - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", + "evidence_bundle_sha256": "25b549ca48ec334006fbf70ff184e76d56fca3192e72cb7ca2a37dafcdafdaa8", + "source_contract_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -1028,7 +1028,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "0cc661195f0bff2d1365ddea52f69cb3a6d72b3b", + "commit": "6713b56d6b21158fac99e619fe45c580be72a703", "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.", @@ -1112,8 +1112,8 @@ "failures": [] }, "trust_security": { - "scanned_files": 199, - "script_count": 112, + "scanned_files": 200, + "script_count": 113, "internal_module_count": 30, "secret_findings": 0, "dependency_files": [ @@ -1122,18 +1122,18 @@ "network_script_count": 3, "network_policy_covered_count": 3, "network_policy_missing_count": 0, - "file_write_script_count": 69, + "file_write_script_count": 70, "permission_required_count": 3, "permission_approved_count": 3, "permission_missing_count": 0, "permission_invalid_count": 0, "permission_expired_count": 0, - "help_smoke_checked_count": 82, + "help_smoke_checked_count": 83, "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 199, - "package_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544" + "package_hash_file_count": 200, + "package_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1" }, "skill_atlas": { "skill_count": 12, @@ -1171,8 +1171,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544", - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf" + "package_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e" }, "compatibility": { "openai": "pass", @@ -1203,7 +1203,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1219,8 +1219,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", - "archive_entry_count": 619, + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", + "archive_entry_count": 623, "failure_count": 0, "warning_count": 0 }, @@ -1231,7 +1231,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 619, + "archive_entry_count": 623, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1298,12 +1298,12 @@ { "field": "archive_sha256", "from": "", - "to": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf" + "to": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544" + "to": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1" } ] }, diff --git a/reports/skill-overview.html b/reports/skill-overview.html index e1d20c1..db74b18 100644 --- a/reports/skill-overview.html +++ b/reports/skill-overview.html @@ -930,7 +930,7 @@

让 reviewer 快速确认关键文件、目录和资产分布。Lets reviewers confirm key files, directories, and asset distribution quickly.

-
资产分布Asset Distribution401项401 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
+
资产分布Asset Distribution404项404 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
路径Path作用Role类型Type
SKILL.mdSkill 入口文件Skill entrypoint文件file
README.md人类可读使用说明Human-readable usage guide文件file
agents/interface.yaml跨平台接口元数据Neutral interface metadata文件file
manifest.json生命周期与打包元数据Lifecycle and portability metadata文件file
references扩展指导与复用资料Extended guidance and reusable notes目录folder
scripts确定性脚本或本地工具Deterministic helpers or local tooling目录folder
evals触发与质量检查Trigger and quality checks目录folder
reports生成的证据与总结报告Generated evidence and overview artifacts目录folder
diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 71763fc..e741c5f 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -512,7 +512,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 112 + "file_count": 113 }, { "path": "evals", @@ -524,10 +524,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 222 + "file_count": 224 } ], - "file_count": 401, + "file_count": 404, "folder_count": 4, "distribution": [ { @@ -552,7 +552,7 @@ }, { "label": "scripts", - "value": 112 + "value": 113 }, { "label": "evals", @@ -560,7 +560,7 @@ }, { "label": "reports", - "value": 222 + "value": 224 } ] }, @@ -682,7 +682,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 112 + "file_count": 113 }, { "path": "evals", @@ -694,7 +694,7 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 222 + "file_count": 224 } ], "strengths": [ @@ -999,9 +999,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "4f7164b6f04d9079f0497d3e84cefe9e2495ab9ee6fecaa3a74194f288fb8fca", - "source_contract_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544", - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", + "evidence_bundle_sha256": "25b549ca48ec334006fbf70ff184e76d56fca3192e72cb7ca2a37dafcdafdaa8", + "source_contract_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 22, @@ -1023,7 +1023,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "0cc661195f0bff2d1365ddea52f69cb3a6d72b3b", + "commit": "6713b56d6b21158fac99e619fe45c580be72a703", "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.", @@ -1107,8 +1107,8 @@ "failures": [] }, "trust_security": { - "scanned_files": 199, - "script_count": 112, + "scanned_files": 200, + "script_count": 113, "internal_module_count": 30, "secret_findings": 0, "dependency_files": [ @@ -1117,18 +1117,18 @@ "network_script_count": 3, "network_policy_covered_count": 3, "network_policy_missing_count": 0, - "file_write_script_count": 69, + "file_write_script_count": 70, "permission_required_count": 3, "permission_approved_count": 3, "permission_missing_count": 0, "permission_invalid_count": 0, "permission_expired_count": 0, - "help_smoke_checked_count": 82, + "help_smoke_checked_count": 83, "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 199, - "package_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544" + "package_hash_file_count": 200, + "package_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1" }, "skill_atlas": { "skill_count": 12, @@ -1166,8 +1166,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544", - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf" + "package_sha256": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e" }, "compatibility": { "openai": "pass", @@ -1198,7 +1198,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1214,8 +1214,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf", - "archive_entry_count": 619, + "archive_sha256": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e", + "archive_entry_count": 623, "failure_count": 0, "warning_count": 0 }, @@ -1226,7 +1226,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 619, + "archive_entry_count": 623, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1293,12 +1293,12 @@ { "field": "archive_sha256", "from": "", - "to": "77d9bd77e4a9e3992b727da369e195d94753fd4195b33981abadd10e81ee9fdf" + "to": "5c411a7ea1891bf797cd9f7f2d7b02f6bde20055e383d17040725f7116e8583e" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "ce3d8c67706a5059ae162d937f51d7469aee3d0095a53889c686524f2b43d544" + "to": "909d0f5bad8ede6cc24b6c733b614a36c178878447612aa97276ff05e5206ce1" } ] },
路径Path作用Role类型Type
SKILL.mdSkill 入口文件Skill entrypoint文件file
README.md人类可读使用说明Human-readable usage guide文件file
agents/interface.yaml跨平台接口元数据Neutral interface metadata文件file
manifest.json生命周期与打包元数据Lifecycle and portability metadata文件file
references扩展指导与复用资料Extended guidance and reusable notes目录folder
scripts确定性脚本或本地工具Deterministic helpers or local tooling目录folder
evals触发与质量检查Trigger and quality checks目录folder
reports生成的证据与总结报告Generated evidence and overview artifacts目录folder