diff --git a/registry/index.json b/registry/index.json index 8e9faf7..ebe332e 100644 --- a/registry/index.json +++ b/registry/index.json @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833" + "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index 3235d6d..01c8ffd 100644 --- a/registry/packages/yao-meta-skill.json +++ b/registry/packages/yao-meta-skill.json @@ -16,8 +16,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833", - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19" + "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" }, "compatibility": { "openai": "pass", @@ -48,7 +48,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index 97b8377..b218722 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,23 +3,36 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "07380f06b33b94d0803b18eef34683c2153da554", + "commit": "5b858a903da563ac5e5ccf4d2ac1dd200ece0d1f", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 32, + "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", + " M reports/benchmark_reproducibility.json", + " M reports/benchmark_reproducibility.md", + " M reports/context_budget.json", + " M reports/context_budget.md", + " M reports/context_budget_summary.json", + " M reports/evidence_consistency.json", + " M reports/output_execution_runs.json", + " M reports/output_execution_runs.md", + " M reports/package_verification.json", + " M reports/package_verification.md" + ], "scope": "generation-time status before this report is written" }, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7", - "source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833", - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "evidence_bundle_sha256": "f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d", + "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -37,14 +50,15 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 32 }, "public_claim": { "ready": false, "scope": "public benchmark or world-class readiness claim", "blockers": [ + "release lock is not clean or commit is unavailable", "provider-backed model holdout evidence is incomplete", "human blind-review adjudication is incomplete", "world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)", @@ -53,10 +67,10 @@ "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks." }, "release_lock": { - "ready": true, - "commit": "07380f06b33b94d0803b18eef34683c2153da554", + "ready": false, + "commit": "5b858a903da563ac5e5ccf4d2ac1dd200ece0d1f", "status_scope": "generation-time status before this report is written", - "reason": "clean generation-time HEAD" + "reason": "working tree was dirty at generation time" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", @@ -64,7 +78,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7" + "sha256": "f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -138,7 +152,7 @@ "path": "reports/output_execution_runs.json", "exists": true, "bytes": 7967, - "sha256": "326c1b064f877eb7d06afe6f811fea55a12b1b595cfc6b4eeb026074af03bbb0" + "sha256": "c6d6e307a51e70c9c3146a57b506c4b92752417f704fe2fcff13134feb6f334f" }, { "label": "blind_review", @@ -173,7 +187,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 120363, - "sha256": "dfe7a658aae962ed16d95d375420f061f632f385387dd2bdcffdb7d979ed85f2" + "sha256": "7222c5a1b18f76e0b0a1d0a49a19255669bde759ced8eed5ddceddc424b4f796" }, { "label": "python_compatibility", @@ -187,14 +201,14 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "c808e62f5c2b18c0518212a9a55fd55b1f6f1ae1e06e232016b78ddac0c20156" + "sha256": "e8cd7941efbceb36d4cad4bd06600aad48ab0d2b56061256bb39ab3d7ebdd471" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "dae6d1bb3e92409f8194c06cad5ff212c388508696aeec7bf8b1c8f5eae2a9c9" + "sha256": "3189b49d1bef034fb9c9798a28a5bf3c6ac8bd0e73822b452cbacaa278a09043" }, { "label": "install_simulation", @@ -208,7 +222,7 @@ "path": "reports/skill_os2_audit.json", "exists": true, "bytes": 14310, - "sha256": "095495b62e56340e23f08a96152a9c725ea3e1e055bd2d79443ab42cc7129e17" + "sha256": "c0e499f9f051fc170c7350d2dbb370765e4f611b0ae2504fe492c909fd46a45d" }, { "label": "world_class_evidence_plan", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index 6dd5804..f4005c0 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,19 +1,19 @@ # Benchmark Reproducibility Generated at: `2026-06-16` -Commit: `07380f06b33b94d0803b18eef34683c2153da554` -Working tree dirty at generation: `false` -Evidence bundle SHA256: `f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7` +Commit: `5b858a903da563ac5e5ccf4d2ac1dd200ece0d1f` +Working tree dirty at generation: `true` +Evidence bundle SHA256: `f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d` ## Summary - reproducibility ready: `true` -- release lock ready: `true` +- release lock ready: `false` - methodology complete: `true` - required artifacts: `25` - missing artifacts: `0` -- source contract sha256: `a8b415ac609b` -- archive sha256: `431fec57d9ad` +- source contract sha256: `795cfae7d2e0` +- archive sha256: `c061bfca61f6` - output cases: `5` - disclosed failure cases: `3` - reproduction commands: `23` @@ -22,8 +22,8 @@ Evidence bundle SHA256: `f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff1764 - world-class ready: `false` - world-class source checks: `6` pass / `13` total; `7` blocked - public claim ready: `false` -- public claim blockers: `4` -- changed files at generation: `0` +- public claim blockers: `5` +- changed files at generation: `32` This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below. @@ -35,6 +35,7 @@ This report proves local benchmark reproducibility only. It keeps external provi | Blocker | | --- | +| release lock is not clean or commit is unavailable | | provider-backed model holdout evidence is incomplete | | human blind-review adjudication is incomplete | | world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) | @@ -42,15 +43,15 @@ This report proves local benchmark reproducibility only. It keeps external provi ## Release Lock -- ready: `true` -- reason: clean generation-time HEAD +- ready: `false` +- reason: working tree was dirty at generation time - status scope: generation-time status before this report is written ## Evidence Bundle - algorithm: `sha256(path,label,exists,artifact_sha256)` - artifacts: `25` / `25` -- sha256: `f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7` +- sha256: `f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d` ## Methodology Sections @@ -72,17 +73,17 @@ 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 | `326c1b064f87` | +| output_execution | `reports/output_execution_runs.json` | present | `c6d6e307a51e` | | blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` | | review_adjudication | `reports/output_review_adjudication.json` | present | `bb8c72a9291e` | | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` | | runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` | -| trust_report | `reports/security_trust_report.json` | present | `dfe7a658aae9` | +| trust_report | `reports/security_trust_report.json` | present | `7222c5a1b18f` | | python_compatibility | `reports/python_compatibility.json` | present | `6843f5283fd7` | -| registry_audit | `reports/registry_audit.json` | present | `c808e62f5c2b` | -| package_verification | `reports/package_verification.json` | present | `dae6d1bb3e92` | +| registry_audit | `reports/registry_audit.json` | present | `e8cd7941efbc` | +| package_verification | `reports/package_verification.json` | present | `3189b49d1bef` | | install_simulation | `reports/install_simulation.json` | present | `1c3fdea61d50` | -| skill_os2_audit | `reports/skill_os2_audit.json` | present | `095495b62e56` | +| skill_os2_audit | `reports/skill_os2_audit.json` | present | `c0e499f9f051` | | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `130161495dc4` | | world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `b8976c340da4` | | world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `7f502f722ff1` | diff --git a/reports/context_budget.json b/reports/context_budget.json index 731cc45..5f9f67a 100644 --- a/reports/context_budget.json +++ b/reports/context_budget.json @@ -6,15 +6,15 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1047970, + "other_text_tokens": 1048692, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1048767, - "deferred_resource_tokens": 485505, + "estimated_total_text_tokens": 1049489, + "deferred_resource_tokens": 485971, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 425527, + "estimated_tokens": 425993, "file_count": 125 }, { @@ -36,7 +36,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 425527, + "estimated_tokens": 425993, "file_count": 125 } ], @@ -59,7 +59,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 425527, + "estimated_tokens": 425993, "file_count": 125, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } diff --git a/reports/context_budget.md b/reports/context_budget.md index 1cde76c..9971096 100644 --- a/reports/context_budget.md +++ b/reports/context_budget.md @@ -2,7 +2,7 @@ | Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status | | --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- | -| root | `.` | `production` | 1000 | 990 | 797 | 485505 | `governed` | scripts:425527 | 131.3 | - | ok | +| root | `.` | `production` | 1000 | 990 | 797 | 485971 | `governed` | scripts:425993 | 131.3 | - | ok | | complex-release-orchestrator | `examples/complex-release-orchestrator/generated-skill` | `production` | 1000 | 790 | 718 | 1657 | `not-required` | - | 164.6 | - | ok | | governed-incident-command | `examples/governed-incident-command/generated-skill` | `production` | 1000 | 760 | 658 | 1030 | `not-required` | - | 171.1 | - | ok | diff --git a/reports/context_budget_summary.json b/reports/context_budget_summary.json index 998cf72..d3075a3 100644 --- a/reports/context_budget_summary.json +++ b/reports/context_budget_summary.json @@ -8,11 +8,11 @@ "budget_limit": 1000, "initial_tokens": 990, "skill_body_tokens": 797, - "deferred_resource_tokens": 485505, + "deferred_resource_tokens": 485971, "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 425527, + "estimated_tokens": 425993, "file_count": 125 } ], @@ -35,7 +35,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 425527, + "estimated_tokens": 425993, "file_count": 125, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index aa22355..86c4b1f 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -189,12 +189,12 @@ "status": "pass", "expected": { "status": "pass", - "detail": "initial load 990/1000; deferred 485505/120000; top deferred scripts 425527; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 485971/120000; top deferred scripts 425993; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json" }, "actual": { "status": "pass", - "detail": "initial load 990/1000; deferred 485505/120000; top deferred scripts 425527; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 485971/120000; top deferred scripts 425993; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json" }, "paths": [ @@ -207,8 +207,8 @@ "key": "benchmark-release-lock-self-consistency", "label": "Benchmark release lock matches git dirty state", "status": "pass", - "expected": true, - "actual": true, + "expected": false, + "actual": false, "paths": [ "reports/benchmark_reproducibility.json" ], @@ -248,8 +248,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "07380f06b33b94d0803b18eef34683c2153da554", - "actual": "07380f06b33b94d0803b18eef34683c2153da554", + "expected": "5b858a903da563ac5e5ccf4d2ac1dd200ece0d1f", + "actual": "5b858a903da563ac5e5ccf4d2ac1dd200ece0d1f", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -261,30 +261,30 @@ "label": "overview embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833", - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "actual": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833", - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -394,8 +394,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "07380f06b33b94d0803b18eef34683c2153da554", - "actual": "07380f06b33b94d0803b18eef34683c2153da554", + "expected": "5b858a903da563ac5e5ccf4d2ac1dd200ece0d1f", + "actual": "5b858a903da563ac5e5ccf4d2ac1dd200ece0d1f", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -407,30 +407,30 @@ "label": "interpretation embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833", - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "actual": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833", - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "paths": [ "reports/benchmark_reproducibility.json", diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index 2d0eb93..8c4e7ca 100644 --- a/reports/output_execution_runs.json +++ b/reports/output_execution_runs.json @@ -34,7 +34,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 33.16, + "duration_ms": 32.03, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.89, + "duration_ms": 31.67, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.22, + "duration_ms": 32.12, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.79, + "duration_ms": 31.21, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.24, + "duration_ms": 30.86, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.76, + "duration_ms": 31.36, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.56, + "duration_ms": 31.46, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.56, + "duration_ms": 30.85, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.15, + "duration_ms": 31.35, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.43, + "duration_ms": 31.62, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index 9a317d9..281ffa6 100644 --- a/reports/output_execution_runs.md +++ b/reports/output_execution_runs.md @@ -23,16 +23,16 @@ Command runner evidence is present. This proves the eval harness executed an ext | Case | Variant | Mode | Model | Duration ms | Tokens | Score | Status | | --- | --- | --- | --- | ---: | ---: | ---: | --- | -| skill-package-contract | baseline | command | local-output-eval-runner | 33.16 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 30.89 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 32.22 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 31.79 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 30.24 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 30.76 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 30.56 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 30.56 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 30.15 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 31.43 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 32.03 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 31.67 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 32.12 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 31.21 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 30.86 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 31.36 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 31.46 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 30.85 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 31.35 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 31.62 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/package_verification.json b/reports/package_verification.json index 86b00e0..523a9c2 100644 --- a/reports/package_verification.json +++ b/reports/package_verification.json @@ -8,7 +8,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 diff --git a/reports/package_verification.md b/reports/package_verification.md index 2178aca..216c228 100644 --- a/reports/package_verification.md +++ b/reports/package_verification.md @@ -4,7 +4,7 @@ - Package directory: `dist` - Targets: `4 / 4` adapters present - Archive present: `True` -- Archive SHA256: `431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19` +- Archive SHA256: `c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c` - Failures: `0` - Warnings: `0` diff --git a/reports/registry_audit.json b/reports/registry_audit.json index 723824d..22eb5f8 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,8 +21,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833", - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19" + "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" }, "compatibility": { "openai": "pass", @@ -53,7 +53,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833" + "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index 19fcb76..f2b8214 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,8 +6,8 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833` -- Archive SHA256: `431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19` +- Package SHA256: `795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31` +- Archive SHA256: `c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c` - Install simulated: `True` ## Compatibility diff --git a/reports/review-studio.html b/reports/review-studio.html index 532451c..c26a5e1 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -740,12 +740,12 @@

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

125 scripts scanned; secrets found

Py Compat0

199 files scanned for Python 3.11

Arch Debt0

836 largest lines; 8 watchlist; 68 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock true

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

180 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

652 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

5 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

125 scripts scanned; secrets found

Py Compat0

199 files scanned for Python 3.11

Arch Debt0

836 largest lines; 8 watchlist; 68 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock false

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

180 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

652 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 990/1000; deferred 485505/120000; top deferred scripts 425527; resource governance governed; quality density 131.3

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; 125 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 199 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

196 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 836 lines; 68 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; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true

reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly 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
通过

上下文

initial load 990/1000; deferred 485971/120000; top deferred scripts 425993; resource governance governed; quality density 131.3

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; 125 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 199 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

196 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 836 lines; 68 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; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false

reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly 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

@@ -807,12 +807,12 @@
-

上下文

initial load 990/1000; deferred 485505/120000; top deferred scripts 425527; resource governance governed; quality density 131.3

+

上下文

initial load 990/1000; deferred 485971/120000; top deferred scripts 425993; resource governance governed; quality density 131.3

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
125
网络脚本
3
Help 失败
0
包体哈希
a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833
+

信任报告

Secret
0
脚本数
125
网络脚本
3
Help 失败
0
包体哈希
795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31

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。

@@ -837,14 +837,14 @@
-

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true

+

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false

漂移信号

事件数
1
采用率
0
漏触发
0
Bad Output Count
0
风险带
low
-

日常运维

决策
proposal-review
提案数
5
Approval Count
0
Pending Review Count
0
发布锁
是
世界级
否
Writes Source Files
否
Auto Patch Enabled
否
-

周度队列

决策
curator-review
Week Id
2026-W25
日报数
1
唯一机会
5
待批准复核
1
提案复核
4
Top Score
88
发布锁
是
Writes Source Files
否
Auto Patch Enabled
否
+

日常运维

决策
proposal-review
提案数
5
Approval Count
0
Pending Review Count
0
发布锁
否
世界级
否
Writes Source Files
否
Auto Patch Enabled
否
+

周度队列

决策
curator-review
Week Id
2026-W25
日报数
1
唯一机会
5
待批准复核
1
提案复核
4
Top Score
88
发布锁
否
Writes Source Files
否
Auto Patch Enabled
否
@@ -877,8 +877,8 @@
-

公开声明

本地复现
是
发布锁
是
可公开声明
否
声明阻断
4
Provider 证据
否
人审完成
否
世界级就绪
否
-

声明阻断

  • 阻断provider-backed model holdout evidence is incomplete
  • 阻断human blind-review adjudication is incomplete
  • 阻断world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)
  • 阻断world-class source checks are not all accepted (6/13 pass, 7 blocked)
+

公开声明

本地复现
是
发布锁
否
可公开声明
否
声明阻断
5
Provider 证据
否
人审完成
否
世界级就绪
否
+

声明阻断

  • 阻断release lock is not clean or commit is unavailable
  • 阻断provider-backed model holdout evidence is incomplete
  • 阻断human blind-review adjudication is incomplete
  • 阻断world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)
  • 阻断world-class source checks are not all accepted (6/13 pass, 7 blocked)
@@ -898,12 +898,12 @@

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
431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19
+

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
c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c

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
是
Zip 条目
652
失败数
0
警告数
0
归档哈希
431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19
+

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
652
失败数
0
警告数
0
归档哈希
c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c
diff --git a/reports/review-studio.json b/reports/review-studio.json index 79e34e1..937f645 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -43,7 +43,7 @@ "key": "context-budget", "label": "上下文", "status": "pass", - "detail": "initial load 990/1000; deferred 485505/120000; top deferred scripts 425527; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 485971/120000; top deferred scripts 425993; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json", "link": "context_budget.md" }, @@ -107,7 +107,7 @@ "key": "operations-loop", "label": "运营回路", "status": "pass", - "detail": "1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true", + "detail": "1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false", "evidence": "reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly", "link": "adoption_drift_report.md" }, @@ -1922,13 +1922,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7", - "source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833", - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "evidence_bundle_sha256": "f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d", + "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1946,11 +1946,11 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 32 }, - "commit": "07380f06b33b94d0803b18eef34683c2153da554", + "commit": "5b858a903da563ac5e5ccf4d2ac1dd200ece0d1f", "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.", @@ -2055,7 +2055,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833" + "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" }, "skill_atlas": { "skill_count": 12, @@ -2093,8 +2093,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833", - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19" + "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" }, "compatibility": { "openai": "pass", @@ -2125,7 +2125,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -2141,7 +2141,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -2220,12 +2220,12 @@ { "field": "archive_sha256", "from": "", - "to": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19" + "to": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833" + "to": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" } ] }, @@ -4602,7 +4602,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 33.16, + "duration_ms": 32.03, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4630,7 +4630,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.89, + "duration_ms": 31.67, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4653,7 +4653,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.22, + "duration_ms": 32.12, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4681,7 +4681,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.79, + "duration_ms": 31.21, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4704,7 +4704,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.24, + "duration_ms": 30.86, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4732,7 +4732,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.76, + "duration_ms": 31.36, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4755,7 +4755,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.56, + "duration_ms": 31.46, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4782,7 +4782,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.56, + "duration_ms": 30.85, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4805,7 +4805,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.15, + "duration_ms": 31.35, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4834,7 +4834,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.43, + "duration_ms": 31.62, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5560,23 +5560,36 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "07380f06b33b94d0803b18eef34683c2153da554", + "commit": "5b858a903da563ac5e5ccf4d2ac1dd200ece0d1f", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 32, + "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", + " M reports/benchmark_reproducibility.json", + " M reports/benchmark_reproducibility.md", + " M reports/context_budget.json", + " M reports/context_budget.md", + " M reports/context_budget_summary.json", + " M reports/evidence_consistency.json", + " M reports/output_execution_runs.json", + " M reports/output_execution_runs.md", + " M reports/package_verification.json", + " M reports/package_verification.md" + ], "scope": "generation-time status before this report is written" }, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7", - "source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833", - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "evidence_bundle_sha256": "f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d", + "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -5594,14 +5607,15 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 32 }, "public_claim": { "ready": false, "scope": "public benchmark or world-class readiness claim", "blockers": [ + "release lock is not clean or commit is unavailable", "provider-backed model holdout evidence is incomplete", "human blind-review adjudication is incomplete", "world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)", @@ -5610,10 +5624,10 @@ "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks." }, "release_lock": { - "ready": true, - "commit": "07380f06b33b94d0803b18eef34683c2153da554", + "ready": false, + "commit": "5b858a903da563ac5e5ccf4d2ac1dd200ece0d1f", "status_scope": "generation-time status before this report is written", - "reason": "clean generation-time HEAD" + "reason": "working tree was dirty at generation time" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", @@ -5621,7 +5635,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7" + "sha256": "f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -5695,7 +5709,7 @@ "path": "reports/output_execution_runs.json", "exists": true, "bytes": 7967, - "sha256": "326c1b064f877eb7d06afe6f811fea55a12b1b595cfc6b4eeb026074af03bbb0" + "sha256": "c6d6e307a51e70c9c3146a57b506c4b92752417f704fe2fcff13134feb6f334f" }, { "label": "blind_review", @@ -5730,7 +5744,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 120363, - "sha256": "dfe7a658aae962ed16d95d375420f061f632f385387dd2bdcffdb7d979ed85f2" + "sha256": "7222c5a1b18f76e0b0a1d0a49a19255669bde759ced8eed5ddceddc424b4f796" }, { "label": "python_compatibility", @@ -5744,14 +5758,14 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "c808e62f5c2b18c0518212a9a55fd55b1f6f1ae1e06e232016b78ddac0c20156" + "sha256": "e8cd7941efbceb36d4cad4bd06600aad48ab0d2b56061256bb39ab3d7ebdd471" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "dae6d1bb3e92409f8194c06cad5ff212c388508696aeec7bf8b1c8f5eae2a9c9" + "sha256": "3189b49d1bef034fb9c9798a28a5bf3c6ac8bd0e73822b452cbacaa278a09043" }, { "label": "install_simulation", @@ -5765,7 +5779,7 @@ "path": "reports/skill_os2_audit.json", "exists": true, "bytes": 14310, - "sha256": "095495b62e56340e23f08a96152a9c725ea3e1e055bd2d79443ab42cc7129e17" + "sha256": "c0e499f9f051fc170c7350d2dbb370765e4f611b0ae2504fe492c909fd46a45d" }, { "label": "world_class_evidence_plan", @@ -12005,7 +12019,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833" + "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" }, "failures": [], "warnings": [], @@ -16429,15 +16443,15 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1047970, + "other_text_tokens": 1048692, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1048767, - "deferred_resource_tokens": 485505, + "estimated_total_text_tokens": 1049489, + "deferred_resource_tokens": 485971, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 425527, + "estimated_tokens": 425993, "file_count": 125 }, { @@ -16459,7 +16473,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 425527, + "estimated_tokens": 425993, "file_count": 125 } ], @@ -16482,7 +16496,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 425527, + "estimated_tokens": 425993, "file_count": 125, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } @@ -18476,7 +18490,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -18493,7 +18507,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -18942,7 +18956,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true }, "actions": [ @@ -18991,7 +19005,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -19011,7 +19025,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -19263,7 +19277,7 @@ "no_route_opportunity_count": 0 }, "release_state": { - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4 @@ -23333,8 +23347,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833", - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19" + "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" }, "compatibility": { "openai": "pass", @@ -23365,7 +23379,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -23390,7 +23404,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833" + "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" } ] }, @@ -23413,7 +23427,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -24421,12 +24435,12 @@ { "field": "archive_sha256", "from": "", - "to": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19" + "to": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833" + "to": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" } ] }, diff --git a/reports/review-viewer.json b/reports/review-viewer.json index 679629a..afea5bc 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -997,13 +997,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7", - "source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833", - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "evidence_bundle_sha256": "f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d", + "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1021,11 +1021,11 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 32 }, - "commit": "07380f06b33b94d0803b18eef34683c2153da554", + "commit": "5b858a903da563ac5e5ccf4d2ac1dd200ece0d1f", "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.", @@ -1130,7 +1130,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833" + "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" }, "skill_atlas": { "skill_count": 12, @@ -1168,8 +1168,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833", - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19" + "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" }, "compatibility": { "openai": "pass", @@ -1200,7 +1200,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1216,7 +1216,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -1295,12 +1295,12 @@ { "field": "archive_sha256", "from": "", - "to": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19" + "to": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833" + "to": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" } ] }, diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json index 92bdffa..4e8ffc7 100644 --- a/reports/security_trust_report.json +++ b/reports/security_trust_report.json @@ -23,7 +23,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833" + "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" }, "failures": [], "warnings": [], diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index f11291a..3e592fd 100644 --- a/reports/security_trust_report.md +++ b/reports/security_trust_report.md @@ -16,7 +16,7 @@ - Interactive scripts: `0` - Package hash scope: `source-contract-without-generated-reports` - Package hash files: `216` -- Package SHA256: `a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833` +- Package SHA256: `795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31` ## Failures diff --git a/reports/skill-interpretation.html b/reports/skill-interpretation.html index b96c819..1647a08 100644 --- a/reports/skill-interpretation.html +++ b/reports/skill-interpretation.html @@ -803,7 +803,7 @@
  1. 稳定Stable完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 360 个词/字，references 约 16828 个词/字。Entrypoint is about 360 words/characters; references are about 16828.
-
完整度Completeness100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在，便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
  • compiled_targets.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
可维护性Maintainability100
  • SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  • 入口文件保持克制，可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 360 个词/字，references 约 16828 个词/字。Entrypoint is about 360 words/characters; references are about 16828.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高，建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
+
完整度Completeness100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在，便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。skill-ir.json exists.
  • compiled_targets.json 已存在。compiled_targets.json exists.
可维护性Maintainability100
  • SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  • 入口文件保持克制，可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 360 个词/字，references 约 16828 个词/字。Entrypoint is about 360 words/characters; references are about 16828.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高，建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index 220370c..f494085 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -1001,13 +1001,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7", - "source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833", - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "evidence_bundle_sha256": "f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d", + "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1025,11 +1025,11 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 32 }, - "commit": "07380f06b33b94d0803b18eef34683c2153da554", + "commit": "5b858a903da563ac5e5ccf4d2ac1dd200ece0d1f", "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.", @@ -1134,7 +1134,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833" + "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" }, "skill_atlas": { "skill_count": 12, @@ -1172,8 +1172,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833", - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19" + "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" }, "compatibility": { "openai": "pass", @@ -1204,7 +1204,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1220,7 +1220,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -1299,12 +1299,12 @@ { "field": "archive_sha256", "from": "", - "to": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19" + "to": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833" + "to": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" } ] }, diff --git a/reports/skill-overview.html b/reports/skill-overview.html index 98c3ac9..9c1a235 100644 --- a/reports/skill-overview.html +++ b/reports/skill-overview.html @@ -803,7 +803,7 @@
  1. 稳定Stable完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 360 个词/字，references 约 16828 个词/字。Entrypoint is about 360 words/characters; references are about 16828.
-
完整度Completeness100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在，便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
  • compiled_targets.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
可维护性Maintainability100
  • SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  • 入口文件保持克制，可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 360 个词/字，references 约 16828 个词/字。Entrypoint is about 360 words/characters; references are about 16828.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高，建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
+
完整度Completeness100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在，便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。skill-ir.json exists.
  • compiled_targets.json 已存在。compiled_targets.json exists.
可维护性Maintainability100
  • SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  • 入口文件保持克制，可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 360 个词/字，references 约 16828 个词/字。Entrypoint is about 360 words/characters; references are about 16828.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高，建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
diff --git a/reports/skill-overview.json b/reports/skill-overview.json index d36cfc8..ae38d0c 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -996,13 +996,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7", - "source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833", - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "evidence_bundle_sha256": "f91abd056143c4d3a50857e8b7ae90d49139157b1cd7bb81eb103d4c9951e59d", + "source_contract_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1020,11 +1020,11 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 32 }, - "commit": "07380f06b33b94d0803b18eef34683c2153da554", + "commit": "5b858a903da563ac5e5ccf4d2ac1dd200ece0d1f", "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.", @@ -1129,7 +1129,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 216, - "package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833" + "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" }, "skill_atlas": { "skill_count": 12, @@ -1167,8 +1167,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833", - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19" + "package_sha256": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" }, "compatibility": { "openai": "pass", @@ -1199,7 +1199,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1215,7 +1215,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19", + "archive_sha256": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c", "archive_entry_count": 652, "failure_count": 0, "warning_count": 0 @@ -1294,12 +1294,12 @@ { "field": "archive_sha256", "from": "", - "to": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19" + "to": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833" + "to": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" } ] }, diff --git a/reports/skill_os2_audit.json b/reports/skill_os2_audit.json index 750007b..fe5def6 100644 --- a/reports/skill_os2_audit.json +++ b/reports/skill_os2_audit.json @@ -307,7 +307,7 @@ "key": "review-studio", "label": "Review Studio", "status": "pass", - "current": "decision review; warnings 4; score 89", + "current": "decision review; warnings 3; score 91", "target": "One page shows gates, evidence paths, blockers, warnings, actions, waivers, and annotations", "evidence": [ { diff --git a/reports/skill_os2_audit.md b/reports/skill_os2_audit.md index 99fb67b..ee9676e 100644 --- a/reports/skill_os2_audit.md +++ b/reports/skill_os2_audit.md @@ -28,7 +28,7 @@ Generated at: `2026-06-16` | Native Permission Enforcement | external-required | native-enforced targets 0; installer-enforced targets 4 | At least one target/client enforces approved permissions at runtime | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. | | Skill Atlas | pass | 12 skills; actionable collisions 0 | Workspace catalog, route overlap, stale/owner gaps, drift, and no-route opportunities | Feed real drift data into Atlas once client telemetry is installed. | | Registry Distribution | pass | zip entries 652; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. | -| Review Studio | pass | decision review; warnings 4; score 89 | One page shows gates, evidence paths, blockers, warnings, actions, waivers, and annotations | Resolve human/external warning gates before claiming full release readiness. | +| Review Studio | pass | decision review; warnings 3; score 91 | One page shows gates, evidence paths, blockers, warnings, actions, waivers, and annotations | Resolve human/external warning gates before claiming full release readiness. | | Telemetry Drift | pass | events 1; risk low; recipes 5 | Local-first metadata-only event contract, aggregate drift report, hook recipes, and import path | Keep raw JSONL out of distributed packages and use aggregate reports for Atlas. | | Native Client Telemetry | external-required | external source events 0; adoption samples 0 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. | diff --git a/reports/skillops/daily/2026-06-16.json b/reports/skillops/daily/2026-06-16.json index a35cbc8..386b061 100644 --- a/reports/skillops/daily/2026-06-16.json +++ b/reports/skillops/daily/2026-06-16.json @@ -14,7 +14,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -31,7 +31,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "writes_source_files": false, "auto_patch_enabled": false, @@ -480,7 +480,7 @@ "local_blueprint_ready": true, "public_world_class_ready": false, "world_class_pending_count": 4, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true }, "actions": [ diff --git a/reports/skillops/daily/2026-06-16.md b/reports/skillops/daily/2026-06-16.md index 105c41c..d0fbea0 100644 --- a/reports/skillops/daily/2026-06-16.md +++ b/reports/skillops/daily/2026-06-16.md @@ -14,7 +14,7 @@ Generated at: `2026-06-16` - local blueprint ready: `true` - public world-class ready: `false` - world-class pending: `4` -- release lock ready: `true` +- release lock ready: `false` - evidence consistency ok: `true` This report is an operations cockpit for explicit-source SkillOps. It does not scan private logs, write source files, apply patches, or count as world-class external or human evidence. diff --git a/reports/skillops/weekly/2026-W25.json b/reports/skillops/weekly/2026-W25.json index 998d23e..65c79eb 100644 --- a/reports/skillops/weekly/2026-W25.json +++ b/reports/skillops/weekly/2026-W25.json @@ -15,7 +15,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -35,7 +35,7 @@ "top_score": 88, "skill_count": 12, "actionable_portfolio_issue_count": 0, - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4, @@ -287,7 +287,7 @@ "no_route_opportunity_count": 0 }, "release_state": { - "release_lock_ready": true, + "release_lock_ready": false, "evidence_consistency_ok": true, "public_world_class_ready": false, "world_class_pending_count": 4 diff --git a/reports/skillops/weekly/2026-W25.md b/reports/skillops/weekly/2026-W25.md index 4d75fc3..1fd6a71 100644 --- a/reports/skillops/weekly/2026-W25.md +++ b/reports/skillops/weekly/2026-W25.md @@ -13,7 +13,7 @@ Week: `2026-W25` - top_score: `88` - skill_count: `12` - actionable_portfolio_issue_count: `0` -- release_lock_ready: `True` +- release_lock_ready: `False` - evidence_consistency_ok: `True` - public_world_class_ready: `False` - world_class_pending_count: `4` diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index 801f29d..9fa7e99 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -70,12 +70,12 @@ { "field": "archive_sha256", "from": "", - "to": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19" + "to": "c061bfca61f625a3cc88b55d91f35bdac9d9679509c4bb01b590d45532ec2c1c" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833" + "to": "795cfae7d2e06fc741fda329b649400b55031f3a959f2016ff0222a47a6dac31" } ] }, diff --git a/scripts/skill_report_i18n.py b/scripts/skill_report_i18n.py index 5700028..430e4f1 100644 --- a/scripts/skill_report_i18n.py +++ b/scripts/skill_report_i18n.py @@ -106,16 +106,26 @@ TEXT_EN = { "frontmatter description 已存在，具备基础路由面。": "The frontmatter description exists, giving the skill a basic routing surface.", "description 有足够长度说明任务边界。": "The description is long enough to explain the task boundary.", "description 已包含使用场景或排除边界信号。": "The description includes usage-scenario or exclusion-boundary signals.", + "description 证据不足，触发边界不稳定。": "Description evidence is insufficient, so the trigger boundary is unstable.", + "description 偏短，建议补充输入、输出或非目标。": "The description is short; add inputs, outputs, or non-goals.", + "description 缺少明确使用场景或排除边界。": "The description lacks clear usage scenarios or exclusion boundaries.", "evals/ 已存在，可承载触发样例或质量检查。": "evals/ exists and can hold trigger examples or quality checks.", + "evals/ 证据不足，误触发检查仍偏弱。": "evals/ evidence is insufficient, so accidental-trigger checks remain weak.", "intent-confidence 报告已生成，可辅助判断触发稳定性。": "The intent-confidence report exists and helps judge trigger stability.", + "intent-confidence 证据不足。": "intent-confidence evidence is insufficient.", "入口文件保持克制，可维护性较好。": "The entrypoint stays restrained, which supports maintainability.", + "入口文件偏长，建议继续拆到 references/。": "The entrypoint is long; continue splitting durable guidance into references/.", "references/ 已承载扩展指导。": "references/ carries extended guidance.", + "references/ 证据不足，长指导可能堆在入口。": "references/ evidence is insufficient; long guidance may still be crowded into the entrypoint.", "scripts/ 已承载确定性逻辑。": "scripts/ carries deterministic logic.", + "scripts/ 证据不足，重复执行逻辑可能仍靠人工。": "scripts/ evidence is insufficient; repeated execution may still rely on manual work.", "evals/ 已承载可迁移检查。": "evals/ carries portable checks.", "agents/interface.yaml 已存在。": "agents/interface.yaml exists.", "manifest.json 已存在。": "manifest.json exists.", "目标平台或 adapter target 已声明。": "Target platforms or adapter targets are declared.", + "目标平台证据不足。": "Target-platform evidence is insufficient.", "入口文件未发现明显私有绝对路径。": "No obvious private absolute paths were found in the entrypoint.", + "入口文件含私有绝对路径，迁移风险较高。": "The entrypoint contains private absolute paths, increasing portability risk.", "分数越高代表上下文成本越低。": "A higher score means lower context cost.", "上下文成本处于可控区间。": "Context cost is within a controlled range.", "上下文成本偏高，建议压缩入口或拆分 references。": "Context cost is high; compress the entrypoint or split references further.", @@ -123,7 +133,12 @@ TEXT_EN = { "跨平台": "Cross-platform", "本地复用": "Local reuse", "输入材料": "Input material", + "用户提供的工作流、提示词、文档、记录或散乱笔记": "User-provided workflows, prompts, documents, records, or rough notes.", + "期望沉淀的复用场景、排除项、约束和质量标准": "The reusable scenario, exclusions, constraints, and quality standards to capture.", "Skill 包体": "Skill package", + "可路由的 SKILL.md": "A routeable SKILL.md.", + "agents/interface.yaml 元数据": "agents/interface.yaml metadata.", + "必要的 references、scripts、evals、reports 证据": "Necessary references, scripts, evals, and reports evidence.", "可复用能力": "Reusable capability", "入口层": "Entrypoint layer", "参考层": "Reference layer", @@ -314,6 +329,15 @@ def en_for(text: str) -> str: match = re.match(r"^已生成\s+(\d+)\s+/\s+(\d+)\s+类报告证据。$", value) if match: return f"Generated {match.group(1)} / {match.group(2)} evidence report types." + match = re.match(r"^(.+?)\s+已存在。$", value) + if match: + return f"{match.group(1)} exists." + match = re.match(r"^(.+?)\s+未发现或为空，完整度扣分。$", value) + if match: + return f"{match.group(1)} was not found or is empty, reducing completeness." + match = re.match(r"^(.+?)\s+证据不足。$", value) + if match: + return f"{match.group(1)} evidence is insufficient." match = re.match(r"^SKILL\.md 约\s+(.+?)\s+个词/字。$", value) if match: return f"SKILL.md is about {match.group(1)} words/characters." diff --git a/tests/verify_skill_overview.py b/tests/verify_skill_overview.py index 2ab865c..d884f35 100644 --- a/tests/verify_skill_overview.py +++ b/tests/verify_skill_overview.py @@ -68,6 +68,23 @@ def main() -> None: ) assert en_for("交付结果：SKILL.md, agents/interface.yaml") == "Deliverables: SKILL.md, agents/interface.yaml" assert en_for("已生成 12 / 20 类报告证据。") == "Generated 12 / 20 evidence report types." + assert en_for("skill-ir.json 已存在。") == "skill-ir.json exists." + assert en_for("compiled_targets.json 已存在。") == "compiled_targets.json exists." + assert en_for("reports 未发现或为空，完整度扣分。") == ( + "reports was not found or is empty, reducing completeness." + ) + assert en_for("evals/ 证据不足。") == "evals/ evidence is insufficient." + assert en_for("用户提供的工作流、提示词、文档、记录或散乱笔记") == ( + "User-provided workflows, prompts, documents, records, or rough notes." + ) + assert en_for("期望沉淀的复用场景、排除项、约束和质量标准") == ( + "The reusable scenario, exclusions, constraints, and quality standards to capture." + ) + assert en_for("可路由的 SKILL.md") == "A routeable SKILL.md." + assert en_for("agents/interface.yaml 元数据") == "agents/interface.yaml metadata." + assert en_for("必要的 references、scripts、evals、reports 证据") == ( + "Necessary references, scripts, evals, and reports evidence." + ) assert en_for("入口约 864 个词/字，references 约 565 个词/字。") == ( "Entrypoint is about 864 words/characters; references are about 565." ) @@ -210,6 +227,7 @@ def main() -> None: assert directions_json["directions"][0]["title"] in initial_report_html, initial_report_html[:5000] assert "世界证据" in initial_report_html, initial_report_html assert "No world-class ledger has been generated" in initial_report_html, initial_report_html + assert "Skill-specific source text is authored in Chinese" not in initial_report_html, initial_report_html sample_ledger = { "schema_version": "1.0",