Split Skill OS review consistency check

This commit is contained in:
yaojingang
2026-06-16 09:58:18 +08:00
parent 129ab2a1c7
commit ca6afbde87
43 changed files with 569 additions and 445 deletions
+1 -1
View File
@@ -16,7 +16,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f"
"package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833"
}
]
}
+3 -3
View File
@@ -16,8 +16,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f",
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf"
"package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19"
},
"compatibility": {
"openai": "pass",
@@ -48,7 +48,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
+17 -17
View File
@@ -4,10 +4,10 @@
"generated_at": "2026-06-16",
"skill_dir": ".",
"summary": {
"python_file_count": 195,
"script_file_count": 124,
"python_file_count": 196,
"script_file_count": 125,
"test_file_count": 71,
"internal_module_count": 41,
"internal_module_count": 42,
"cli_script_count": 85,
"command_handler_count": 68,
"entrypoint_command_handler_count": 18,
@@ -29,13 +29,6 @@
"severity": "pass",
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/render_evidence_consistency.py",
"lines": 808,
"kind": "cli-script",
"severity": "pass",
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "scripts/skill_report_model.py",
"lines": 800,
@@ -50,6 +43,13 @@
"severity": "pass",
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/render_evidence_consistency.py",
"lines": 766,
"kind": "cli-script",
"severity": "pass",
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "scripts/yao_cli_parser.py",
"lines": 759,
@@ -115,13 +115,6 @@
"severity": "pass",
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/render_evidence_consistency.py",
"lines": 808,
"kind": "cli-script",
"severity": "pass",
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "scripts/skill_report_model.py",
"lines": 800,
@@ -136,6 +129,13 @@
"severity": "pass",
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/render_evidence_consistency.py",
"lines": 766,
"kind": "cli-script",
"severity": "pass",
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "scripts/yao_cli_parser.py",
"lines": 759,
+5 -5
View File
@@ -5,10 +5,10 @@ Generated at: `2026-06-16`
## Summary
- decision: `pass`
- python files: `195`
- scripts: `124`
- python files: `196`
- scripts: `125`
- tests: `71`
- internal modules: `41`
- internal modules: `42`
- CLI scripts: `85`
- Yao CLI command handlers: `68`
- entrypoint command handlers: `18`
@@ -30,9 +30,9 @@ No file-size hotspots found.
| File | Lines | Kind | Recommended next split |
| --- | ---: | --- | --- |
| `tests/verify_review_studio.py` | `836` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
| `scripts/render_evidence_consistency.py` | `808` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
| `scripts/skill_report_model.py` | `800` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
| `tests/verify_yao_cli.py` | `785` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
| `scripts/render_evidence_consistency.py` | `766` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
| `scripts/yao_cli_parser.py` | `759` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
| `scripts/build_skill_atlas.py` | `730` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
| `scripts/compile_skill.py` | `723` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
@@ -43,9 +43,9 @@ No file-size hotspots found.
| File | Lines | Kind | Severity |
| --- | ---: | --- | --- |
| `tests/verify_review_studio.py` | `836` | `test` | `pass` |
| `scripts/render_evidence_consistency.py` | `808` | `cli-script` | `pass` |
| `scripts/skill_report_model.py` | `800` | `internal-module` | `pass` |
| `tests/verify_yao_cli.py` | `785` | `test` | `pass` |
| `scripts/render_evidence_consistency.py` | `766` | `cli-script` | `pass` |
| `scripts/yao_cli_parser.py` | `759` | `internal-module` | `pass` |
| `scripts/build_skill_atlas.py` | `730` | `cli-script` | `pass` |
| `scripts/compile_skill.py` | `723` | `cli-script` | `pass` |
+38 -24
View File
@@ -3,23 +3,36 @@
"ok": true,
"generated_at": "2026-06-16",
"skill_dir": ".",
"commit": "d3076c3561b01a8eda07bbed87bc0ae2114c9b66",
"commit": "129ab2a1c7b128a6a5393d7dc27eb00c0a171f52",
"git_status": {
"available": true,
"dirty": false,
"changed_file_count": 0,
"sample": [],
"dirty": true,
"changed_file_count": 43,
"sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/architecture_maintainability.json",
" M reports/architecture_maintainability.md",
" 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/install_simulation.json",
" M reports/output_execution_runs.json"
],
"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": "31ae7b678afcfde9e095ddce258b99ab03f16c86602532c7d6f851e16602a4c0",
"source_contract_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f",
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"evidence_bundle_sha256": "f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7",
"source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"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": 43
},
"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": "d3076c3561b01a8eda07bbed87bc0ae2114c9b66",
"ready": false,
"commit": "129ab2a1c7b128a6a5393d7dc27eb00c0a171f52",
"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": "31ae7b678afcfde9e095ddce258b99ab03f16c86602532c7d6f851e16602a4c0"
"sha256": "f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -138,7 +152,7 @@
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7967,
"sha256": "9cb62bc09a8bf21b99337cbabac7a2aec3d38c19bd498afc25576e8be10d5a83"
"sha256": "326c1b064f877eb7d06afe6f811fea55a12b1b595cfc6b4eeb026074af03bbb0"
},
{
"label": "blind_review",
@@ -172,43 +186,43 @@
"label": "trust_report",
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 119700,
"sha256": "f11ef0006e640a8940d970e81a51b2ecee4ef7563b5a731d8960e734a63d3f2d"
"bytes": 120363,
"sha256": "dfe7a658aae962ed16d95d375420f061f632f385387dd2bdcffdb7d979ed85f2"
},
{
"label": "python_compatibility",
"path": "reports/python_compatibility.json",
"exists": true,
"bytes": 25717,
"sha256": "07f236fc1dcd9457f519500dc17697320d3927e7e53b32fb9e08945cd36d547b"
"bytes": 25857,
"sha256": "6843f5283fd7b24f7ee17fcdc16d6a4d737a56abec941b51886b2077f4827162"
},
{
"label": "registry_audit",
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "55b3799ce55a8ea780cf7a40add15b221a0acba12f6f7d36984b1954ee113ab9"
"sha256": "c808e62f5c2b18c0518212a9a55fd55b1f6f1ae1e06e232016b78ddac0c20156"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19338,
"sha256": "8bbb67f796e1bd11141dc16c7f6094f8888d2d3af5a7a1d0e2b4272248458c5f"
"sha256": "dae6d1bb3e92409f8194c06cad5ff212c388508696aeec7bf8b1c8f5eae2a9c9"
},
{
"label": "install_simulation",
"path": "reports/install_simulation.json",
"exists": true,
"bytes": 8604,
"sha256": "edf427265714b5c1700c67f499b1a5f18eef730a638ecf74c624cdce69573125"
"sha256": "1c3fdea61d50ae05224bc7ebeffcf4ec205de213ab0755f6c6593ef76ad59726"
},
{
"label": "skill_os2_audit",
"path": "reports/skill_os2_audit.json",
"exists": true,
"bytes": 14310,
"sha256": "72aee6e0804d5cae471af7669b592d24117ddd1b431cfb5d2dc84418241e54b4"
"sha256": "095495b62e56340e23f08a96152a9c725ea3e1e055bd2d79443ab42cc7129e17"
},
{
"label": "world_class_evidence_plan",
+19 -18
View File
@@ -1,19 +1,19 @@
# Benchmark Reproducibility
Generated at: `2026-06-16`
Commit: `d3076c3561b01a8eda07bbed87bc0ae2114c9b66`
Working tree dirty at generation: `false`
Evidence bundle SHA256: `31ae7b678afcfde9e095ddce258b99ab03f16c86602532c7d6f851e16602a4c0`
Commit: `129ab2a1c7b128a6a5393d7dc27eb00c0a171f52`
Working tree dirty at generation: `true`
Evidence bundle SHA256: `f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7`
## Summary
- reproducibility ready: `true`
- release lock ready: `true`
- release lock ready: `false`
- methodology complete: `true`
- required artifacts: `25`
- missing artifacts: `0`
- source contract sha256: `cd5b790b3cfa`
- archive sha256: `9f3a1f4da502`
- source contract sha256: `a8b415ac609b`
- archive sha256: `431fec57d9ad`
- output cases: `5`
- disclosed failure cases: `3`
- reproduction commands: `23`
@@ -22,8 +22,8 @@ Evidence bundle SHA256: `31ae7b678afcfde9e095ddce258b99ab03f16c86602532c7d6f851e
- 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: `43`
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: `31ae7b678afcfde9e095ddce258b99ab03f16c86602532c7d6f851e16602a4c0`
- sha256: `f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7`
## 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 | `9cb62bc09a8b` |
| output_execution | `reports/output_execution_runs.json` | present | `326c1b064f87` |
| 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 | `f11ef0006e64` |
| python_compatibility | `reports/python_compatibility.json` | present | `07f236fc1dcd` |
| registry_audit | `reports/registry_audit.json` | present | `55b3799ce55a` |
| package_verification | `reports/package_verification.json` | present | `8bbb67f796e1` |
| install_simulation | `reports/install_simulation.json` | present | `edf427265714` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `72aee6e0804d` |
| trust_report | `reports/security_trust_report.json` | present | `dfe7a658aae9` |
| python_compatibility | `reports/python_compatibility.json` | present | `6843f5283fd7` |
| registry_audit | `reports/registry_audit.json` | present | `c808e62f5c2b` |
| package_verification | `reports/package_verification.json` | present | `dae6d1bb3e92` |
| install_simulation | `reports/install_simulation.json` | present | `1c3fdea61d50` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `095495b62e56` |
| 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` |
+10 -10
View File
@@ -6,16 +6,16 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 797,
"other_text_tokens": 1047243,
"other_text_tokens": 1047970,
"estimated_initial_load_tokens": 990,
"estimated_total_text_tokens": 1048040,
"deferred_resource_tokens": 485097,
"estimated_total_text_tokens": 1048767,
"deferred_resource_tokens": 485505,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 425119,
"file_count": 124
"estimated_tokens": 425527,
"file_count": 125
},
{
"path": "references",
@@ -36,8 +36,8 @@
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 425119,
"file_count": 124
"estimated_tokens": 425527,
"file_count": 125
}
],
"deferred_resource_governance": {
@@ -59,14 +59,14 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 425119,
"file_count": 124,
"estimated_tokens": 425527,
"file_count": 125,
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
}
],
"summary": "Large deferred resources are indexed and backed by evidence."
},
"relevant_file_count": 636,
"relevant_file_count": 638,
"unused_resource_dirs": [],
"quality_signal_points": 130,
"quality_density": 131.3
+1 -1
View File
@@ -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 | 485097 | `governed` | scripts:425119 | 131.3 | - | ok |
| root | `.` | `production` | 1000 | 990 | 797 | 485505 | `governed` | scripts:425527 | 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 |
+6 -6
View File
@@ -1,5 +1,5 @@
{
"generated_at": "2026-06-16",
"generated_at": "2026-03-31",
"targets": [
{
"label": "root",
@@ -8,12 +8,12 @@
"budget_limit": 1000,
"initial_tokens": 990,
"skill_body_tokens": 797,
"deferred_resource_tokens": 485097,
"deferred_resource_tokens": 485505,
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 425119,
"file_count": 124
"estimated_tokens": 425527,
"file_count": 125
}
],
"deferred_resource_governance": {
@@ -35,8 +35,8 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 425119,
"file_count": 124,
"estimated_tokens": 425527,
"file_count": 125,
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
}
],
+34 -34
View File
@@ -189,12 +189,12 @@
"status": "pass",
"expected": {
"status": "pass",
"detail": "initial load 990/1000; deferred 485097/120000; top deferred scripts 425119; resource governance governed; quality density 131.3",
"detail": "initial load 990/1000; deferred 485505/120000; top deferred scripts 425527; resource governance governed; quality density 131.3",
"evidence": "reports/context_budget.json"
},
"actual": {
"status": "pass",
"detail": "initial load 990/1000; deferred 485097/120000; top deferred scripts 425119; resource governance governed; quality density 131.3",
"detail": "initial load 990/1000; deferred 485505/120000; top deferred scripts 425527; 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": "d3076c3561b01a8eda07bbed87bc0ae2114c9b66",
"actual": "d3076c3561b01a8eda07bbed87bc0ae2114c9b66",
"expected": "129ab2a1c7b128a6a5393d7dc27eb00c0a171f52",
"actual": "129ab2a1c7b128a6a5393d7dc27eb00c0a171f52",
"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": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f",
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"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": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f",
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"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": "d3076c3561b01a8eda07bbed87bc0ae2114c9b66",
"actual": "d3076c3561b01a8eda07bbed87bc0ae2114c9b66",
"expected": "129ab2a1c7b128a6a5393d7dc27eb00c0a171f52",
"actual": "129ab2a1c7b128a6a5393d7dc27eb00c0a171f52",
"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": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f",
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"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": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f",
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"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",
@@ -1512,7 +1512,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 124
"file_count": 125
},
{
"path": "evals",
@@ -1527,7 +1527,7 @@
"file_count": 229
}
],
"file_count": 421,
"file_count": 422,
"folder_count": 4,
"distribution": [
{
@@ -1552,7 +1552,7 @@
},
{
"label": "scripts",
"value": 124
"value": 125
},
{
"label": "evals",
@@ -1600,7 +1600,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 124
"file_count": 125
},
{
"path": "evals",
@@ -1615,7 +1615,7 @@
"file_count": 229
}
],
"file_count": 421,
"file_count": 422,
"folder_count": 4,
"distribution": [
{
@@ -1640,7 +1640,7 @@
},
{
"label": "scripts",
"value": 124
"value": 125
},
{
"label": "evals",
@@ -2404,10 +2404,10 @@
"score `91`",
"`16` gates",
"`3` warnings",
"`38` declared internal modules",
"`86 / 86` CLI help smoke checks passing across `124` scripts",
"`651` zip entries",
"archive with `651` entries",
"`39` declared internal modules",
"`86 / 86` CLI help smoke checks passing across `125` scripts",
"`652` zip entries",
"archive with `652` entries",
"`12` installer permission checks enforced",
"`0` permission failures",
"`25` required artifacts",
+1 -1
View File
@@ -8,7 +8,7 @@
"installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill",
"summary": {
"archive_present": true,
"archive_entry_count": 651,
"archive_entry_count": 652,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
+10 -10
View File
@@ -34,7 +34,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.65,
"duration_ms": 33.16,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -62,7 +62,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.46,
"duration_ms": 30.89,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -85,7 +85,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.83,
"duration_ms": 32.22,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -113,7 +113,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.71,
"duration_ms": 31.79,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -136,7 +136,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.59,
"duration_ms": 30.24,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -164,7 +164,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.85,
"duration_ms": 30.76,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -187,7 +187,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.09,
"duration_ms": 30.56,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -214,7 +214,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.06,
"duration_ms": 30.56,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -237,7 +237,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.18,
"duration_ms": 30.15,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -266,7 +266,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.63,
"duration_ms": 31.43,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
+10 -10
View File
@@ -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 | 32.65 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 33.46 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 33.83 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 32.71 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 33.59 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 32.85 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 33.09 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 33.06 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 33.18 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 32.63 | 98 | 100.0 | pass |
| 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 |
## Next Fixes
+2 -2
View File
@@ -8,8 +8,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"archive_entry_count": 651,
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"archive_entry_count": 652,
"failure_count": 0,
"warning_count": 0
},
+1 -1
View File
@@ -4,7 +4,7 @@
- Package directory: `dist`
- Targets: `4 / 4` adapters present
- Archive present: `True`
- Archive SHA256: `9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf`
- Archive SHA256: `431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19`
- Failures: `0`
- Warnings: `0`
+7 -1
View File
@@ -5,7 +5,7 @@
"root": ".",
"summary": {
"target_python": "3.11",
"file_count": 198,
"file_count": 199,
"issue_count": 0,
"syntax_error_count": 0,
"fstring_311_violation_count": 0,
@@ -130,6 +130,12 @@
"issue_count": 0,
"issues": []
},
{
"path": "scripts/evidence_consistency_skill_os2_review.py",
"ok": true,
"issue_count": 0,
"issues": []
},
{
"path": "scripts/evidence_consistency_world_class.py",
"ok": true,
+1 -1
View File
@@ -6,7 +6,7 @@ Generated at: `2026-06-16`
- decision: `pass`
- target python: `3.11`
- files scanned: `198`
- files scanned: `199`
- issues: `0`
- syntax errors: `0`
- f-string 3.11 violations: `0`
+4 -4
View File
@@ -21,8 +21,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f",
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf"
"package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19"
},
"compatibility": {
"openai": "pass",
@@ -53,7 +53,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"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": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f"
"package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833"
}
]
},
+2 -2
View File
@@ -6,8 +6,8 @@
- Maturity: `governed`
- Owner: `Yao Team`
- License: `MIT`
- Package SHA256: `cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f`
- Archive SHA256: `9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf`
- Package SHA256: `a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833`
- Archive SHA256: `431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19`
- Install simulated: `True`
## Compatibility
+12 -12
View File
@@ -740,12 +740,12 @@
<section>
<h2>核心指标</h2>
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>4 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>124 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>198 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>836 largest lines; 8 watchlist; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock true</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>180 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>651 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>5 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>125 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>199 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>836 largest lines; 8 watchlist; 68 CLI handlers; 18 in entrypoint</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock false</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>180 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>652 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
</section>
<section>
<h2>审查闸门</h2>
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>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</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 990/1000; deferred 485097/120000; top deferred scripts 425119; resource governance governed; quality density 131.3</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 124 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 198 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>195 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 836 lines; 68 CLI handlers; 18 in entrypoint</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>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</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>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</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 990/1000; deferred 485505/120000; top deferred scripts 425527; resource governance governed; quality density 131.3</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 125 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 199 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>196 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 836 lines; 68 CLI handlers; 18 in entrypoint</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>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</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
</section>
<div class="twocol">
@@ -807,17 +807,17 @@
</section>
<section class="twocol">
<div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 485097/120000; top deferred scripts 425119; resource governance governed; quality density 131.3</p></div>
<div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 485505/120000; top deferred scripts 425527; resource governance governed; quality density 131.3</p></div>
<div class="panel"><h2>编译证据</h2><p>Review reports/compiled_targets.md before packaging to inspect target adapter modes, generated files, preserved semantics, warnings, and unsupported features.</p></div>
</section>
<section id="trust" class="twocol">
<div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>124</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f</code></dd></div></dl></div>
<div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>125</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833</code></dd></div></dl></div>
<div class="panel"><h2>安全边界</h2><p>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。</p></div>
</section>
<section class="twocol">
<div class="panel"><h2>Python 兼容</h2><dl class='kv-grid'><div><dt>目标 Python</dt><dd>3.11</dd></div><div><dt>文件数</dt><dd>198</dd></div><div><dt>问题数</dt><dd>0</dd></div><div><dt>语法错误</dt><dd>0</dd></div><div><dt>F-string 3.11</dt><dd>0</dd></div></dl></div>
<div class="panel"><h2>Python 兼容</h2><dl class='kv-grid'><div><dt>目标 Python</dt><dd>3.11</dd></div><div><dt>文件数</dt><dd>199</dd></div><div><dt>问题数</dt><dd>0</dd></div><div><dt>语法错误</dt><dd>0</dd></div><div><dt>F-string 3.11</dt><dd>0</dd></div></dl></div>
<div class="panel"><h2>解释器边界</h2><p>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。</p></div>
</section>
@@ -837,14 +837,14 @@
</section>
<section id="telemetry" class="twocol">
<div class="panel"><h2>运营回路</h2><p>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</p></div>
<div class="panel"><h2>运营回路</h2><p>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</p></div>
<div class="panel"><h2>漂移信号</h2><dl class='kv-grid'><div><dt>事件数</dt><dd>1</dd></div><div><dt>采用率</dt><dd>0</dd></div><div><dt>漏触发</dt><dd>0</dd></div><div><dt>Bad Output Count</dt><dd>0</dd></div><div><dt>风险带</dt><dd>low</dd></div></dl></div>
</section>
<section class="twocol">
<div class="panel"><h2>日常运维</h2><dl class='kv-grid'><div><dt>决策</dt><dd>proposal-review</dd></div><div><dt>提案数</dt><dd>5</dd></div><div><dt>Approval Count</dt><dd>0</dd></div><div><dt>Pending Review Count</dt><dd>0</dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>世界级</dt><dd></dd></div><div><dt>Writes Source Files</dt><dd></dd></div><div><dt>Auto Patch Enabled</dt><dd></dd></div></dl></div>
<div class="panel"><h2>周度队列</h2><dl class='kv-grid'><div><dt>决策</dt><dd>curator-review</dd></div><div><dt>Week Id</dt><dd>2026-W25</dd></div><div><dt>日报数</dt><dd>1</dd></div><div><dt>唯一机会</dt><dd>5</dd></div><div><dt>待批准复核</dt><dd>1</dd></div><div><dt>提案复核</dt><dd>4</dd></div><div><dt>Top Score</dt><dd>88</dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>Writes Source Files</dt><dd></dd></div><div><dt>Auto Patch Enabled</dt><dd></dd></div></dl></div>
<div class="panel"><h2>日常运维</h2><dl class='kv-grid'><div><dt>决策</dt><dd>proposal-review</dd></div><div><dt>提案数</dt><dd>5</dd></div><div><dt>Approval Count</dt><dd>0</dd></div><div><dt>Pending Review Count</dt><dd>0</dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>世界级</dt><dd></dd></div><div><dt>Writes Source Files</dt><dd></dd></div><div><dt>Auto Patch Enabled</dt><dd></dd></div></dl></div>
<div class="panel"><h2>周度队列</h2><dl class='kv-grid'><div><dt>决策</dt><dd>curator-review</dd></div><div><dt>Week Id</dt><dd>2026-W25</dd></div><div><dt>日报数</dt><dd>1</dd></div><div><dt>唯一机会</dt><dd>5</dd></div><div><dt>待批准复核</dt><dd>1</dd></div><div><dt>提案复核</dt><dd>4</dd></div><div><dt>Top Score</dt><dd>88</dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>Writes Source Files</dt><dd></dd></div><div><dt>Auto Patch Enabled</dt><dd></dd></div></dl></div>
</section>
@@ -877,8 +877,8 @@
</section>
<section class="twocol">
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd></dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>可公开声明</dt><dd></dd></div><div><dt>声明阻断</dt><dd>4</dd></div><div><dt>Provider 证据</dt><dd></dd></div><div><dt>人审完成</dt><dd></dd></div><div><dt>世界级就绪</dt><dd></dd></div></dl></div>
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</span></li></ul></div>
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd></dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>可公开声明</dt><dd></dd></div><div><dt>声明阻断</dt><dd>5</dd></div><div><dt>Provider 证据</dt><dd></dd></div><div><dt>人审完成</dt><dd></dd></div><div><dt>世界级就绪</dt><dd></dd></div></dl></div>
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>release lock is not clean or commit is unavailable</span></li><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</span></li></ul></div>
</section>
<section class="twocol">
@@ -898,12 +898,12 @@
<section id="registry" class="twocol">
<div class="panel"><h2>注册审计</h2><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p></div>
<div class="panel"><h2>包体元数据</h2><dl class='kv-grid'><div><dt>名称</dt><dd>yao-meta-skill</dd></div><div><dt>版本</dt><dd>1.1.0</dd></div><div><dt>Maturity</dt><dd>governed</dd></div><div><dt>Owner</dt><dd>Yao Team</dd></div><div><dt>License</dt><dd>MIT</dd></div><div><dt>信任级别</dt><dd>local</dd></div><div><dt>目标平台</dt><dd>openai, claude, generic, agent-skills-compatible, vscode</dd></div><div><dt>兼容通过</dt><dd>6/6</dd></div><div><dt>归档哈希</dt><dd><code>9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf</code></dd></div></dl></div>
<div class="panel"><h2>包体元数据</h2><dl class='kv-grid'><div><dt>名称</dt><dd>yao-meta-skill</dd></div><div><dt>版本</dt><dd>1.1.0</dd></div><div><dt>Maturity</dt><dd>governed</dd></div><div><dt>Owner</dt><dd>Yao Team</dd></div><div><dt>License</dt><dd>MIT</dd></div><div><dt>信任级别</dt><dd>local</dd></div><div><dt>目标平台</dt><dd>openai, claude, generic, agent-skills-compatible, vscode</dd></div><div><dt>兼容通过</dt><dd>6/6</dd></div><div><dt>归档哈希</dt><dd><code>431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19</code></dd></div></dl></div>
</section>
<section id="release" class="twocol">
<div class="panel"><h2>发布路线</h2><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p></div>
<div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>Adapter</dt><dd>4</dd></div><div><dt>归档存在</dt><dd></dd></div><div><dt>Zip 条目</dt><dd>651</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf</code></dd></div></dl></div>
<div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>Adapter</dt><dd>4</dd></div><div><dt>归档存在</dt><dd></dd></div><div><dt>Zip 条目</dt><dd>652</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19</code></dd></div></dl></div>
</section>
<section class="twocol">
+154 -115
View File
@@ -43,7 +43,7 @@
"key": "context-budget",
"label": "上下文",
"status": "pass",
"detail": "initial load 990/1000; deferred 485097/120000; top deferred scripts 425119; resource governance governed; quality density 131.3",
"detail": "initial load 990/1000; deferred 485505/120000; top deferred scripts 425527; resource governance governed; quality density 131.3",
"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; 124 scripts; 3 network-capable scripts; 0 help smoke failures",
"detail": "0 secrets; 125 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; 198 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards",
"detail": "Python 3.11; 199 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": "195 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 836 lines; 68 CLI handlers; 18 in entrypoint",
"detail": "196 Python files; 0 hotspots; 8 watchlist files; 0 blockers; largest 836 lines; 68 CLI handlers; 18 in entrypoint",
"evidence": "reports/architecture_maintainability.json",
"link": "architecture_maintainability.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"
},
@@ -1438,7 +1438,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 124
"file_count": 125
},
{
"path": "evals",
@@ -1453,7 +1453,7 @@
"file_count": 229
}
],
"file_count": 421,
"file_count": 422,
"folder_count": 4,
"distribution": [
{
@@ -1478,7 +1478,7 @@
},
{
"label": "scripts",
"value": 124
"value": 125
},
{
"label": "evals",
@@ -1608,7 +1608,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 124
"file_count": 125
},
{
"path": "evals",
@@ -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": "31ae7b678afcfde9e095ddce258b99ab03f16c86602532c7d6f851e16602a4c0",
"source_contract_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f",
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"evidence_bundle_sha256": "f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7",
"source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"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": 43
},
"commit": "d3076c3561b01a8eda07bbed87bc0ae2114c9b66",
"commit": "129ab2a1c7b128a6a5393d7dc27eb00c0a171f52",
"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.",
@@ -2034,9 +2034,9 @@
"failures": []
},
"trust_security": {
"scanned_files": 215,
"script_count": 124,
"internal_module_count": 38,
"scanned_files": 216,
"script_count": 125,
"internal_module_count": 39,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -2054,8 +2054,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 215,
"package_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f"
"package_hash_file_count": 216,
"package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833"
},
"skill_atlas": {
"skill_count": 12,
@@ -2093,8 +2093,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f",
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf"
"package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19"
},
"compatibility": {
"openai": "pass",
@@ -2125,7 +2125,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -2141,8 +2141,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"archive_entry_count": 651,
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"archive_entry_count": 652,
"failure_count": 0,
"warning_count": 0
},
@@ -2153,7 +2153,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 651,
"archive_entry_count": 652,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -2220,12 +2220,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf"
"to": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f"
"to": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833"
}
]
},
@@ -4602,7 +4602,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.65,
"duration_ms": 33.16,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4630,7 +4630,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.46,
"duration_ms": 30.89,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4653,7 +4653,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.83,
"duration_ms": 32.22,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4681,7 +4681,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.71,
"duration_ms": 31.79,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4704,7 +4704,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.59,
"duration_ms": 30.24,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4732,7 +4732,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.85,
"duration_ms": 30.76,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4755,7 +4755,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.09,
"duration_ms": 30.56,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4782,7 +4782,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.06,
"duration_ms": 30.56,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4805,7 +4805,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 33.18,
"duration_ms": 30.15,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4834,7 +4834,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.63,
"duration_ms": 31.43,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5560,23 +5560,36 @@
"ok": true,
"generated_at": "2026-06-16",
"skill_dir": ".",
"commit": "d3076c3561b01a8eda07bbed87bc0ae2114c9b66",
"commit": "129ab2a1c7b128a6a5393d7dc27eb00c0a171f52",
"git_status": {
"available": true,
"dirty": false,
"changed_file_count": 0,
"sample": [],
"dirty": true,
"changed_file_count": 43,
"sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/architecture_maintainability.json",
" M reports/architecture_maintainability.md",
" 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/install_simulation.json",
" M reports/output_execution_runs.json"
],
"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": "31ae7b678afcfde9e095ddce258b99ab03f16c86602532c7d6f851e16602a4c0",
"source_contract_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f",
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"evidence_bundle_sha256": "f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7",
"source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"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": 43
},
"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": "d3076c3561b01a8eda07bbed87bc0ae2114c9b66",
"ready": false,
"commit": "129ab2a1c7b128a6a5393d7dc27eb00c0a171f52",
"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": "31ae7b678afcfde9e095ddce258b99ab03f16c86602532c7d6f851e16602a4c0"
"sha256": "f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -5695,7 +5709,7 @@
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7967,
"sha256": "9cb62bc09a8bf21b99337cbabac7a2aec3d38c19bd498afc25576e8be10d5a83"
"sha256": "326c1b064f877eb7d06afe6f811fea55a12b1b595cfc6b4eeb026074af03bbb0"
},
{
"label": "blind_review",
@@ -5729,43 +5743,43 @@
"label": "trust_report",
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 119700,
"sha256": "f11ef0006e640a8940d970e81a51b2ecee4ef7563b5a731d8960e734a63d3f2d"
"bytes": 120363,
"sha256": "dfe7a658aae962ed16d95d375420f061f632f385387dd2bdcffdb7d979ed85f2"
},
{
"label": "python_compatibility",
"path": "reports/python_compatibility.json",
"exists": true,
"bytes": 25717,
"sha256": "07f236fc1dcd9457f519500dc17697320d3927e7e53b32fb9e08945cd36d547b"
"bytes": 25857,
"sha256": "6843f5283fd7b24f7ee17fcdc16d6a4d737a56abec941b51886b2077f4827162"
},
{
"label": "registry_audit",
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "55b3799ce55a8ea780cf7a40add15b221a0acba12f6f7d36984b1954ee113ab9"
"sha256": "c808e62f5c2b18c0518212a9a55fd55b1f6f1ae1e06e232016b78ddac0c20156"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19338,
"sha256": "8bbb67f796e1bd11141dc16c7f6094f8888d2d3af5a7a1d0e2b4272248458c5f"
"sha256": "dae6d1bb3e92409f8194c06cad5ff212c388508696aeec7bf8b1c8f5eae2a9c9"
},
{
"label": "install_simulation",
"path": "reports/install_simulation.json",
"exists": true,
"bytes": 8604,
"sha256": "edf427265714b5c1700c67f499b1a5f18eef730a638ecf74c624cdce69573125"
"sha256": "1c3fdea61d50ae05224bc7ebeffcf4ec205de213ab0755f6c6593ef76ad59726"
},
{
"label": "skill_os2_audit",
"path": "reports/skill_os2_audit.json",
"exists": true,
"bytes": 14310,
"sha256": "72aee6e0804d5cae471af7669b592d24117ddd1b431cfb5d2dc84418241e54b4"
"sha256": "095495b62e56340e23f08a96152a9c725ea3e1e055bd2d79443ab42cc7129e17"
},
{
"label": "world_class_evidence_plan",
@@ -6097,7 +6111,7 @@
"label": "Trust Security",
"status": "pass",
"objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
"current": "124 scripts; secrets 0; help failures 0",
"current": "125 scripts; secrets 0; help failures 0",
"command": "python3 scripts/yao.py trust .",
"test": "python3 tests/verify_trust_check.py",
"evidence": [
@@ -6171,7 +6185,7 @@
"label": "Registry Distribution",
"status": "pass",
"objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
"current": "archive entries 651; install failures 0",
"current": "archive entries 652; 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": [
@@ -11984,9 +11998,9 @@
"ok": true,
"skill_dir": ".",
"summary": {
"scanned_files": 215,
"script_count": 124,
"internal_module_count": 38,
"scanned_files": 216,
"script_count": 125,
"internal_module_count": 39,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -12004,8 +12018,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 215,
"package_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f"
"package_hash_file_count": 216,
"package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833"
},
"failures": [],
"warnings": [],
@@ -12226,6 +12240,20 @@
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/evidence_consistency_skill_os2_review.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by render_evidence_consistency.py to keep Skill OS 2.0 review summary drift checks out of the main consistency renderer.",
"has_argparse": false,
"has_main_guard": false,
"uses_input": false,
"uses_network": false,
"uses_file_write": false,
"uses_subprocess": false,
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/evidence_consistency_world_class.py",
"interface": "internal-module",
@@ -13799,7 +13827,7 @@
"checked_count": 86,
"passed_count": 86,
"failed_count": 0,
"skipped_count": 38,
"skipped_count": 39,
"failed_scripts": [],
"results": [
{
@@ -14672,6 +14700,10 @@
"path": "scripts/evidence_consistency_release.py",
"reason": "internal module"
},
{
"path": "scripts/evidence_consistency_skill_os2_review.py",
"reason": "internal module"
},
{
"path": "scripts/evidence_consistency_world_class.py",
"reason": "internal module"
@@ -15011,7 +15043,7 @@
"root": ".",
"summary": {
"target_python": "3.11",
"file_count": 198,
"file_count": 199,
"issue_count": 0,
"syntax_error_count": 0,
"fstring_311_violation_count": 0,
@@ -15136,6 +15168,12 @@
"issue_count": 0,
"issues": []
},
{
"path": "scripts/evidence_consistency_skill_os2_review.py",
"ok": true,
"issue_count": 0,
"issues": []
},
{
"path": "scripts/evidence_consistency_world_class.py",
"ok": true,
@@ -16229,10 +16267,10 @@
"generated_at": "2026-06-16",
"skill_dir": ".",
"summary": {
"python_file_count": 195,
"script_file_count": 124,
"python_file_count": 196,
"script_file_count": 125,
"test_file_count": 71,
"internal_module_count": 41,
"internal_module_count": 42,
"cli_script_count": 85,
"command_handler_count": 68,
"entrypoint_command_handler_count": 18,
@@ -16254,13 +16292,6 @@
"severity": "pass",
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/render_evidence_consistency.py",
"lines": 808,
"kind": "cli-script",
"severity": "pass",
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "scripts/skill_report_model.py",
"lines": 800,
@@ -16275,6 +16306,13 @@
"severity": "pass",
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/render_evidence_consistency.py",
"lines": 766,
"kind": "cli-script",
"severity": "pass",
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "scripts/yao_cli_parser.py",
"lines": 759,
@@ -16340,13 +16378,6 @@
"severity": "pass",
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/render_evidence_consistency.py",
"lines": 808,
"kind": "cli-script",
"severity": "pass",
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "scripts/skill_report_model.py",
"lines": 800,
@@ -16361,6 +16392,13 @@
"severity": "pass",
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/render_evidence_consistency.py",
"lines": 766,
"kind": "cli-script",
"severity": "pass",
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "scripts/yao_cli_parser.py",
"lines": 759,
@@ -16405,16 +16443,16 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 797,
"other_text_tokens": 1047243,
"other_text_tokens": 1047970,
"estimated_initial_load_tokens": 990,
"estimated_total_text_tokens": 1048040,
"deferred_resource_tokens": 485097,
"estimated_total_text_tokens": 1048767,
"deferred_resource_tokens": 485505,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 425119,
"file_count": 124
"estimated_tokens": 425527,
"file_count": 125
},
{
"path": "references",
@@ -16435,8 +16473,8 @@
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 425119,
"file_count": 124
"estimated_tokens": 425527,
"file_count": 125
}
],
"deferred_resource_governance": {
@@ -16458,14 +16496,14 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 425119,
"file_count": 124,
"estimated_tokens": 425527,
"file_count": 125,
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
}
],
"summary": "Large deferred resources are indexed and backed by evidence."
},
"relevant_file_count": 636,
"relevant_file_count": 638,
"unused_resource_dirs": [],
"quality_signal_points": 130,
"quality_density": 131.3
@@ -17344,6 +17382,7 @@
"scripts/emit_telemetry_event.py",
"scripts/evidence_consistency_artifact_roles.py",
"scripts/evidence_consistency_release.py",
"scripts/evidence_consistency_skill_os2_review.py",
"scripts/evidence_consistency_world_class.py",
"scripts/export_skill_ir.py",
"scripts/github_benchmark_scan.py",
@@ -18451,7 +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,
@@ -18468,7 +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,
@@ -18917,7 +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": [
@@ -18966,7 +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,
@@ -18986,7 +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,
@@ -19238,7 +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
@@ -23308,8 +23347,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f",
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf"
"package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19"
},
"compatibility": {
"openai": "pass",
@@ -23340,7 +23379,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -23365,7 +23404,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f"
"package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833"
}
]
},
@@ -23388,8 +23427,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"archive_entry_count": 651,
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"archive_entry_count": 652,
"failure_count": 0,
"warning_count": 0
},
@@ -24054,7 +24093,7 @@
"installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill",
"summary": {
"archive_present": true,
"archive_entry_count": 651,
"archive_entry_count": 652,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -24396,12 +24435,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf"
"to": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f"
"to": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833"
}
]
},
+25 -25
View File
@@ -513,7 +513,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 124
"file_count": 125
},
{
"path": "evals",
@@ -528,7 +528,7 @@
"file_count": 229
}
],
"file_count": 421,
"file_count": 422,
"folder_count": 4,
"distribution": [
{
@@ -553,7 +553,7 @@
},
{
"label": "scripts",
"value": 124
"value": 125
},
{
"label": "evals",
@@ -683,7 +683,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 124
"file_count": 125
},
{
"path": "evals",
@@ -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": "31ae7b678afcfde9e095ddce258b99ab03f16c86602532c7d6f851e16602a4c0",
"source_contract_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f",
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"evidence_bundle_sha256": "f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7",
"source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"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": 43
},
"commit": "d3076c3561b01a8eda07bbed87bc0ae2114c9b66",
"commit": "129ab2a1c7b128a6a5393d7dc27eb00c0a171f52",
"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.",
@@ -1109,9 +1109,9 @@
"failures": []
},
"trust_security": {
"scanned_files": 215,
"script_count": 124,
"internal_module_count": 38,
"scanned_files": 216,
"script_count": 125,
"internal_module_count": 39,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -1129,8 +1129,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 215,
"package_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f"
"package_hash_file_count": 216,
"package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833"
},
"skill_atlas": {
"skill_count": 12,
@@ -1168,8 +1168,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f",
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf"
"package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19"
},
"compatibility": {
"openai": "pass",
@@ -1200,7 +1200,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1216,8 +1216,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"archive_entry_count": 651,
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"archive_entry_count": 652,
"failure_count": 0,
"warning_count": 0
},
@@ -1228,7 +1228,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 651,
"archive_entry_count": 652,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1295,12 +1295,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf"
"to": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f"
"to": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833"
}
]
},
+24 -6
View File
@@ -2,9 +2,9 @@
"ok": true,
"skill_dir": ".",
"summary": {
"scanned_files": 215,
"script_count": 124,
"internal_module_count": 38,
"scanned_files": 216,
"script_count": 125,
"internal_module_count": 39,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -22,8 +22,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 215,
"package_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f"
"package_hash_file_count": 216,
"package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833"
},
"failures": [],
"warnings": [],
@@ -244,6 +244,20 @@
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/evidence_consistency_skill_os2_review.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by render_evidence_consistency.py to keep Skill OS 2.0 review summary drift checks out of the main consistency renderer.",
"has_argparse": false,
"has_main_guard": false,
"uses_input": false,
"uses_network": false,
"uses_file_write": false,
"uses_subprocess": false,
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/evidence_consistency_world_class.py",
"interface": "internal-module",
@@ -1817,7 +1831,7 @@
"checked_count": 86,
"passed_count": 86,
"failed_count": 0,
"skipped_count": 38,
"skipped_count": 39,
"failed_scripts": [],
"results": [
{
@@ -2690,6 +2704,10 @@
"path": "scripts/evidence_consistency_release.py",
"reason": "internal module"
},
{
"path": "scripts/evidence_consistency_skill_os2_review.py",
"reason": "internal module"
},
{
"path": "scripts/evidence_consistency_world_class.py",
"reason": "internal module"
+6 -5
View File
@@ -1,9 +1,9 @@
# Security Trust Report
- OK: `True`
- Scanned files: `215`
- Scripts: `124`
- Internal script modules: `38`
- Scanned files: `216`
- Scripts: `125`
- Internal script modules: `39`
- Secret findings: `0`
- Network-capable scripts: `3`
- Network policy covered scripts: `3`
@@ -15,8 +15,8 @@
- CLI help smoke failures: `0`
- Interactive scripts: `0`
- Package hash scope: `source-contract-without-generated-reports`
- Package hash files: `215`
- Package SHA256: `cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f`
- Package hash files: `216`
- Package SHA256: `a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833`
## Failures
@@ -77,6 +77,7 @@
| scripts/emit_telemetry_event.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/evidence_consistency_artifact_roles.py | internal-module | True | False | False | False | False | False | False | Imported by render_evidence_consistency.py to compare preflight and Review Studio artifact-role contracts. |
| scripts/evidence_consistency_release.py | internal-module | True | False | False | False | False | False | False | Imported by render_evidence_consistency.py to verify release evidence refresh instructions. |
| scripts/evidence_consistency_skill_os2_review.py | internal-module | True | False | False | False | False | False | False | Imported by render_evidence_consistency.py to keep Skill OS 2.0 review summary drift checks out of the main consistency renderer. |
| scripts/evidence_consistency_world_class.py | internal-module | True | False | False | False | False | False | False | Imported by render_evidence_consistency.py to isolate world-class evidence workflow consistency checks. |
| scripts/export_skill_ir.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/github_benchmark_scan.py | cli | False | True | True | False | True | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
+1 -1
View File
@@ -930,7 +930,7 @@
<p><span data-lang="zh-CN">让 reviewer 快速确认关键文件、目录和资产分布。</span><span data-lang="en">Lets reviewers confirm key files, directories, and asset distribution quickly.</span></p>
</div>
<div class="two-col">
<figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text data-lang="zh-CN" x="20" y="30" class="chart-title">资产分布</text><text data-lang="en" x="20" y="30" class="chart-title">Asset Distribution</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="-0.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="-1.2" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="-1.8" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="21.5 78.5" stroke-dashoffset="-2.5" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="76.1 23.9" stroke-dashoffset="-23.9" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">421</text><text data-lang="en" x="130" y="136" text-anchor="middle">421 items</text><text data-lang="zh-CN" x="235" y="78">SKILL.md</text><text data-lang="en" x="235" y="78">SKILL.md</text><text data-lang="zh-CN" x="235" y="100">README.md</text><text data-lang="en" x="235" y="100">README.md</text><text data-lang="zh-CN" x="235" y="122">agents/interface.yaml</text><text data-lang="en" x="235" y="122">agents/interface.yaml</text><text data-lang="zh-CN" x="235" y="144">manifest.json</text><text data-lang="en" x="235" y="144">manifest.json</text><text data-lang="zh-CN" x="235" y="166">references</text><text data-lang="en" x="235" y="166">references</text><text data-lang="zh-CN" x="235" y="188">scripts</text><text data-lang="en" x="235" y="188">scripts</text></svg><figcaption><span data-lang="zh-CN">资产分布图展示当前包体的文件和目录重心。</span><span data-lang="en">The asset distribution chart shows where files and directories are concentrated.</span></figcaption></figure>
<figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text data-lang="zh-CN" x="20" y="30" class="chart-title">资产分布</text><text data-lang="en" x="20" y="30" class="chart-title">Asset Distribution</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="-0.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="-1.2" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="-1.8" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="21.3 78.7" stroke-dashoffset="-2.4" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="76.2 23.8" stroke-dashoffset="-23.8" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">422</text><text data-lang="en" x="130" y="136" text-anchor="middle">422 items</text><text data-lang="zh-CN" x="235" y="78">SKILL.md</text><text data-lang="en" x="235" y="78">SKILL.md</text><text data-lang="zh-CN" x="235" y="100">README.md</text><text data-lang="en" x="235" y="100">README.md</text><text data-lang="zh-CN" x="235" y="122">agents/interface.yaml</text><text data-lang="en" x="235" y="122">agents/interface.yaml</text><text data-lang="zh-CN" x="235" y="144">manifest.json</text><text data-lang="en" x="235" y="144">manifest.json</text><text data-lang="zh-CN" x="235" y="166">references</text><text data-lang="en" x="235" y="166">references</text><text data-lang="zh-CN" x="235" y="188">scripts</text><text data-lang="en" x="235" y="188">scripts</text></svg><figcaption><span data-lang="zh-CN">资产分布图展示当前包体的文件和目录重心。</span><span data-lang="en">The asset distribution chart shows where files and directories are concentrated.</span></figcaption></figure>
<table>
<thead><tr><th><span data-lang="zh-CN">路径</span><span data-lang="en">Path</span></th><th><span data-lang="zh-CN">作用</span><span data-lang="en">Role</span></th><th><span data-lang="zh-CN">类型</span><span data-lang="en">Type</span></th></tr></thead>
<tbody><tr><td>SKILL.md</td><td><span data-lang="zh-CN">Skill 入口文件</span><span data-lang="en">Skill entrypoint</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>README.md</td><td><span data-lang="zh-CN">人类可读使用说明</span><span data-lang="en">Human-readable usage guide</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>agents/interface.yaml</td><td><span data-lang="zh-CN">跨平台接口元数据</span><span data-lang="en">Neutral interface metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>manifest.json</td><td><span data-lang="zh-CN">生命周期与打包元数据</span><span data-lang="en">Lifecycle and portability metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>references</td><td><span data-lang="zh-CN">扩展指导与复用资料</span><span data-lang="en">Extended guidance and reusable notes</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>scripts</td><td><span data-lang="zh-CN">确定性脚本或本地工具</span><span data-lang="en">Deterministic helpers or local tooling</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>evals</td><td><span data-lang="zh-CN">触发与质量检查</span><span data-lang="en">Trigger and quality checks</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>reports</td><td><span data-lang="zh-CN">生成的证据与总结报告</span><span data-lang="en">Generated evidence and overview artifacts</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr></tbody>
+25 -25
View File
@@ -513,7 +513,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 124
"file_count": 125
},
{
"path": "evals",
@@ -528,7 +528,7 @@
"file_count": 229
}
],
"file_count": 421,
"file_count": 422,
"folder_count": 4,
"distribution": [
{
@@ -553,7 +553,7 @@
},
{
"label": "scripts",
"value": 124
"value": 125
},
{
"label": "evals",
@@ -687,7 +687,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 124
"file_count": 125
},
{
"path": "evals",
@@ -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": "31ae7b678afcfde9e095ddce258b99ab03f16c86602532c7d6f851e16602a4c0",
"source_contract_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f",
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"evidence_bundle_sha256": "f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7",
"source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"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": 43
},
"commit": "d3076c3561b01a8eda07bbed87bc0ae2114c9b66",
"commit": "129ab2a1c7b128a6a5393d7dc27eb00c0a171f52",
"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.",
@@ -1113,9 +1113,9 @@
"failures": []
},
"trust_security": {
"scanned_files": 215,
"script_count": 124,
"internal_module_count": 38,
"scanned_files": 216,
"script_count": 125,
"internal_module_count": 39,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -1133,8 +1133,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 215,
"package_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f"
"package_hash_file_count": 216,
"package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833"
},
"skill_atlas": {
"skill_count": 12,
@@ -1172,8 +1172,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f",
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf"
"package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19"
},
"compatibility": {
"openai": "pass",
@@ -1204,7 +1204,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1220,8 +1220,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"archive_entry_count": 651,
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"archive_entry_count": 652,
"failure_count": 0,
"warning_count": 0
},
@@ -1232,7 +1232,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 651,
"archive_entry_count": 652,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1299,12 +1299,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf"
"to": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f"
"to": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833"
}
]
},
+3 -3
View File
@@ -127,13 +127,13 @@ Next move: add real client or installer permission enforcement integration.
| Output Eval | `5` cases, with-skill pass rate `100`, baseline pass rate `0`, with file-backed, near-neighbor, boundary coverage, `10` local command-runner execution runs, `0` recorded fixture runs, `0` provider model-executed runs in root release evidence, `10` estimated token counts, provider runner v0 available, `5` blind A/B review pairs, a generated `reports/output_review_decisions.json` template, `0 / 5` reviewer decisions pending, `0` answer keys revealed, and `5` pending answers hidden |
| Runtime Conformance | `5 / 5` targets passing |
| Target Compiler | `5 / 5` compiled target contracts generated for OpenAI, Claude, generic, Agent Skills compatible, and VS Code / Copilot outputs, including target permission contracts and target-native behavior contracts |
| Trust | `0` secret findings, `1` pinned dependency file, `38` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `86 / 86` CLI help smoke checks passing across `124` scripts, source-contract hash scope explicit |
| Trust | `0` secret findings, `1` pinned dependency file, `39` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `86 / 86` CLI help smoke checks passing across `125` scripts, source-contract hash scope explicit |
| Permission Governance | `3 / 3` required high-permission capabilities approved, `0` missing, `0` invalid, `0` expired |
| Runtime Permission Probes | `4 / 4` target adapters probed, `0` native-enforcement adapters, `4` explicit metadata fallbacks, `4` residual risks retained for reviewer visibility |
| Skill Atlas | `12` scanned skills, `1` actionable root skill, `1` telemetry report, `0` actionable route collisions, `0` actionable owner gaps, `0` actionable stale skills, `0` actionable drift signals, `24` scoped non-actionable issue signals retained for visibility |
| Registry Audit | package metadata generated with version, owner, license, source checksum, archive checksum, Skill IR provenance, and compatibility matrix |
| Package Verification | `4 / 4` target adapters present, archive verified, `651` zip entries, `0` failures, `0` warnings |
| Install Simulation | archive with `651` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings |
| Package Verification | `4 / 4` target adapters present, archive verified, `652` zip entries, `0` failures, `0` warnings |
| Install Simulation | archive with `652` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings |
| Local Install Sync Preflight | `make sync-local-install` and `make sync-active-install` rebuild the package first, then sync only after install simulation passes with `12` enforced installer permission checks and `0` permission failures |
| Upgrade Check | current package declares `minor` over the 1.0.0 baseline, recommended bump is `minor`, and release notes include added targets plus checksum changes |
| Adoption Drift | `1` metadata-only review event, `1` adoption sample, adoption `100`, risk band `low`; optional `yao.py` CLI capture, external client `telemetry-emit`, `5` `telemetry-hooks` recipes, Browser/Chrome native messaging host, and validated external JSONL import are available but off by default for reproducible release evidence; raw `reports/telemetry_events.jsonl` is gitignored and blocked from zip packages |
+1 -1
View File
@@ -930,7 +930,7 @@
<p><span data-lang="zh-CN">让 reviewer 快速确认关键文件、目录和资产分布。</span><span data-lang="en">Lets reviewers confirm key files, directories, and asset distribution quickly.</span></p>
</div>
<div class="two-col">
<figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text data-lang="zh-CN" x="20" y="30" class="chart-title">资产分布</text><text data-lang="en" x="20" y="30" class="chart-title">Asset Distribution</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="-0.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="-1.2" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="-1.8" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="21.5 78.5" stroke-dashoffset="-2.5" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="76.1 23.9" stroke-dashoffset="-23.9" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">421</text><text data-lang="en" x="130" y="136" text-anchor="middle">421 items</text><text data-lang="zh-CN" x="235" y="78">SKILL.md</text><text data-lang="en" x="235" y="78">SKILL.md</text><text data-lang="zh-CN" x="235" y="100">README.md</text><text data-lang="en" x="235" y="100">README.md</text><text data-lang="zh-CN" x="235" y="122">agents/interface.yaml</text><text data-lang="en" x="235" y="122">agents/interface.yaml</text><text data-lang="zh-CN" x="235" y="144">manifest.json</text><text data-lang="en" x="235" y="144">manifest.json</text><text data-lang="zh-CN" x="235" y="166">references</text><text data-lang="en" x="235" y="166">references</text><text data-lang="zh-CN" x="235" y="188">scripts</text><text data-lang="en" x="235" y="188">scripts</text></svg><figcaption><span data-lang="zh-CN">资产分布图展示当前包体的文件和目录重心。</span><span data-lang="en">The asset distribution chart shows where files and directories are concentrated.</span></figcaption></figure>
<figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text data-lang="zh-CN" x="20" y="30" class="chart-title">资产分布</text><text data-lang="en" x="20" y="30" class="chart-title">Asset Distribution</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="-0.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="-1.2" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.6 99.4" stroke-dashoffset="-1.8" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="21.3 78.7" stroke-dashoffset="-2.4" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="76.2 23.8" stroke-dashoffset="-23.8" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">422</text><text data-lang="en" x="130" y="136" text-anchor="middle">422 items</text><text data-lang="zh-CN" x="235" y="78">SKILL.md</text><text data-lang="en" x="235" y="78">SKILL.md</text><text data-lang="zh-CN" x="235" y="100">README.md</text><text data-lang="en" x="235" y="100">README.md</text><text data-lang="zh-CN" x="235" y="122">agents/interface.yaml</text><text data-lang="en" x="235" y="122">agents/interface.yaml</text><text data-lang="zh-CN" x="235" y="144">manifest.json</text><text data-lang="en" x="235" y="144">manifest.json</text><text data-lang="zh-CN" x="235" y="166">references</text><text data-lang="en" x="235" y="166">references</text><text data-lang="zh-CN" x="235" y="188">scripts</text><text data-lang="en" x="235" y="188">scripts</text></svg><figcaption><span data-lang="zh-CN">资产分布图展示当前包体的文件和目录重心。</span><span data-lang="en">The asset distribution chart shows where files and directories are concentrated.</span></figcaption></figure>
<table>
<thead><tr><th><span data-lang="zh-CN">路径</span><span data-lang="en">Path</span></th><th><span data-lang="zh-CN">作用</span><span data-lang="en">Role</span></th><th><span data-lang="zh-CN">类型</span><span data-lang="en">Type</span></th></tr></thead>
<tbody><tr><td>SKILL.md</td><td><span data-lang="zh-CN">Skill 入口文件</span><span data-lang="en">Skill entrypoint</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>README.md</td><td><span data-lang="zh-CN">人类可读使用说明</span><span data-lang="en">Human-readable usage guide</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>agents/interface.yaml</td><td><span data-lang="zh-CN">跨平台接口元数据</span><span data-lang="en">Neutral interface metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>manifest.json</td><td><span data-lang="zh-CN">生命周期与打包元数据</span><span data-lang="en">Lifecycle and portability metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>references</td><td><span data-lang="zh-CN">扩展指导与复用资料</span><span data-lang="en">Extended guidance and reusable notes</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>scripts</td><td><span data-lang="zh-CN">确定性脚本或本地工具</span><span data-lang="en">Deterministic helpers or local tooling</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>evals</td><td><span data-lang="zh-CN">触发与质量检查</span><span data-lang="en">Trigger and quality checks</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>reports</td><td><span data-lang="zh-CN">生成的证据与总结报告</span><span data-lang="en">Generated evidence and overview artifacts</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr></tbody>
+25 -25
View File
@@ -512,7 +512,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 124
"file_count": 125
},
{
"path": "evals",
@@ -527,7 +527,7 @@
"file_count": 229
}
],
"file_count": 421,
"file_count": 422,
"folder_count": 4,
"distribution": [
{
@@ -552,7 +552,7 @@
},
{
"label": "scripts",
"value": 124
"value": 125
},
{
"label": "evals",
@@ -682,7 +682,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 124
"file_count": 125
},
{
"path": "evals",
@@ -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": "31ae7b678afcfde9e095ddce258b99ab03f16c86602532c7d6f851e16602a4c0",
"source_contract_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f",
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"evidence_bundle_sha256": "f34a437eecd06730398dd77ece23911dcfdf1a0b08bfd4b9dff17640a2fce5c7",
"source_contract_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"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": 43
},
"commit": "d3076c3561b01a8eda07bbed87bc0ae2114c9b66",
"commit": "129ab2a1c7b128a6a5393d7dc27eb00c0a171f52",
"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.",
@@ -1108,9 +1108,9 @@
"failures": []
},
"trust_security": {
"scanned_files": 215,
"script_count": 124,
"internal_module_count": 38,
"scanned_files": 216,
"script_count": 125,
"internal_module_count": 39,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -1128,8 +1128,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 215,
"package_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f"
"package_hash_file_count": 216,
"package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833"
},
"skill_atlas": {
"skill_count": 12,
@@ -1167,8 +1167,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f",
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf"
"package_sha256": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19"
},
"compatibility": {
"openai": "pass",
@@ -1199,7 +1199,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"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": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf",
"archive_entry_count": 651,
"archive_sha256": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19",
"archive_entry_count": 652,
"failure_count": 0,
"warning_count": 0
},
@@ -1227,7 +1227,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 651,
"archive_entry_count": 652,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1294,12 +1294,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf"
"to": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f"
"to": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833"
}
]
},
+1
View File
@@ -79,6 +79,7 @@
"scripts/emit_telemetry_event.py",
"scripts/evidence_consistency_artifact_roles.py",
"scripts/evidence_consistency_release.py",
"scripts/evidence_consistency_skill_os2_review.py",
"scripts/evidence_consistency_world_class.py",
"scripts/export_skill_ir.py",
"scripts/github_benchmark_scan.py",
+3 -3
View File
@@ -197,7 +197,7 @@
"key": "trust-security",
"label": "Trust Security",
"status": "pass",
"current": "secrets 0; scripts 124; help failures 0",
"current": "secrets 0; scripts 125; help failures 0",
"target": "Secrets, scripts, dependencies, permissions, and package hash are reviewable",
"evidence": [
{
@@ -285,7 +285,7 @@
"key": "registry-distribution",
"label": "Registry Distribution",
"status": "pass",
"current": "zip entries 651; install failures 0; permission failures 0",
"current": "zip entries 652; install failures 0; permission failures 0",
"target": "Package metadata, archive checksum, package verification, and install simulation pass",
"evidence": [
{
@@ -307,7 +307,7 @@
"key": "review-studio",
"label": "Review Studio",
"status": "pass",
"current": "decision review; warnings 3; score 91",
"current": "decision review; warnings 4; score 89",
"target": "One page shows gates, evidence paths, blockers, warnings, actions, waivers, and annotations",
"evidence": [
{
+3 -3
View File
@@ -23,12 +23,12 @@ Generated at: `2026-06-16`
| Human Adjudication | human-required | 0/5 decisions; pending 5 | Real reviewer decisions recorded before claiming output review completion | Record real A/B choices in the decision template, then regenerate adjudication. |
| Benchmark Reproducibility | pass | artifacts 25; missing 0; failures 3 | Public methodology, reproducible commands, required artifacts, and failure disclosure are machine-checkable | Keep the manifest current with every benchmark, package, and release evidence change. |
| Runtime Conformance | pass | 5/5 targets pass | Target package structure, metadata, relative paths, and degradation notes pass | Keep target conformance fixtures updated as platform contracts change. |
| Trust Security | pass | secrets 0; scripts 124; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. |
| Trust Security | pass | secrets 0; scripts 125; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. |
| Permission Metadata | pass | 4/4 target probes pass; metadata fallback 4; installer enforcement 4 | Packaged adapters expose explicit permission metadata, residual risks, and installer enforcement evidence when available | Preserve residual-risk notes until real native enforcement exists. |
| 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 651; 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 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. |
| 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. |
| 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. |
+2 -2
View File
@@ -130,7 +130,7 @@
"label": "Trust Security",
"status": "pass",
"objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
"current": "124 scripts; secrets 0; help failures 0",
"current": "125 scripts; secrets 0; help failures 0",
"command": "python3 scripts/yao.py trust .",
"test": "python3 tests/verify_trust_check.py",
"evidence": [
@@ -204,7 +204,7 @@
"label": "Registry Distribution",
"status": "pass",
"objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
"current": "archive entries 651; install failures 0",
"current": "archive entries 652; 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": [
+2 -2
View File
@@ -26,9 +26,9 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
| Skill IR | `pass` | schema 2.0.0; targets 5 | `python3 scripts/yao.py skill-ir .` | `python3 tests/verify_skill_ir.py` |
| Output Eval Lab | `pass` | 5 cases; delta 100.0; execution 10 | `python3 scripts/yao.py output-exec . && python3 scripts/yao.py output-review .` | `python3 tests/verify_output_eval_lab.py` |
| Runtime Conformance | `pass` | 5/5 targets pass | `python3 scripts/yao.py conformance .` | `python3 tests/verify_conformance_suite.py` |
| Trust Security | `pass` | 124 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` |
| Trust Security | `pass` | 125 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` |
| Skill Atlas | `pass` | 12 scanned skills; actionable collisions 0 | `python3 scripts/yao.py skill-atlas --workspace-root .` | `python3 tests/verify_skill_atlas.py` |
| Registry Distribution | `pass` | archive entries 651; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` |
| Registry Distribution | `pass` | archive entries 652; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` |
| Review Studio | `pass` | 16 gates; decision review; warnings 3 | `python3 scripts/yao.py review-studio .` | `python3 tests/verify_review_studio.py` |
| Telemetry Drift | `pass` | events 1; recipes 5; risk low | `python3 scripts/yao.py telemetry-hooks . && python3 scripts/yao.py adoption-drift .` | `python3 tests/verify_telemetry_hooks.py` |
+3 -3
View File
@@ -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": [
+1 -1
View File
@@ -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.
+3 -3
View File
@@ -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
+1 -1
View File
@@ -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`
+2 -2
View File
@@ -70,12 +70,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "9f3a1f4da502d3f315dd7e3a4680312876d126ef07d388cf5707a87f03e5deaf"
"to": "431fec57d9adf43b58e5091e1a205f5ff43b6f14f75f498c9edc8d387d8fcc19"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "cd5b790b3cfa42cd4238d63e2fb428cd148184ee871c92b7f6b0eb603be2335f"
"to": "a8b415ac609bac9263d7572d3e1bf8b1b2bf5156812138dbf617fc07e6200833"
}
]
},
@@ -0,0 +1,83 @@
import ast
from pathlib import Path
from typing import Any
SCRIPT_INTERFACE = "internal-module"
SCRIPT_INTERFACE_REASON = (
"Imported by render_evidence_consistency.py to keep Skill OS 2.0 review summary drift checks "
"out of the main consistency renderer."
)
def ci_default_target_count(path: Path) -> int | None:
if not path.exists():
return None
tree = ast.parse(path.read_text(encoding="utf-8"))
for node in tree.body:
if not isinstance(node, ast.Assign):
continue
if not any(isinstance(target, ast.Name) and target.id == "DEFAULT_TARGETS" for target in node.targets):
continue
if isinstance(node.value, (ast.List, ast.Tuple)):
return len(node.value.elts)
return None
def build_skill_os2_review_current_evidence_check(
*,
skill_dir: Path,
skill_os2_review: str,
studio_summary: dict[str, Any],
trust_summary: dict[str, Any],
package_summary: dict[str, Any],
install_summary: dict[str, Any],
benchmark_summary: dict[str, Any],
context_stats: dict[str, Any],
required_text_reports: dict[str, str],
required_reports: dict[str, str],
) -> dict[str, Any]:
ci_target_count = ci_default_target_count(skill_dir / "scripts" / "ci_test.py")
expected_review_snippets = [
f"score `{studio_summary.get('world_class_score')}`",
f"`{studio_summary.get('gate_count')}` gates",
f"`{studio_summary.get('warning_count')}` warnings",
f"`{trust_summary.get('internal_module_count')}` declared internal modules",
(
f"`{trust_summary.get('help_smoke_checked_count')} / {trust_summary.get('help_smoke_checked_count')}` "
f"CLI help smoke checks passing across `{trust_summary.get('script_count')}` scripts"
),
f"`{package_summary.get('archive_entry_count')}` zip entries",
f"archive with `{package_summary.get('archive_entry_count')}` entries",
f"`{install_summary.get('installer_permission_enforced_count')}` installer permission checks enforced",
f"`{install_summary.get('installer_permission_failure_count')}` permission failures",
f"`{benchmark_summary.get('required_artifact_count')}` required artifacts",
f"`{benchmark_summary.get('command_count')}` reproduction commands",
(
f"initial load `{context_stats.get('estimated_initial_load_tokens')}/"
f"{context_stats.get('context_budget_limit')}`"
),
f"target count is `{ci_target_count}`",
]
missing_review_snippets = [snippet for snippet in expected_review_snippets if snippet not in skill_os2_review]
return {
"key": "skill-os-2-review-current-evidence",
"label": "Skill OS 2.0 review summary mirrors current evidence",
"status": "pass" if not missing_review_snippets else "fail",
"expected": expected_review_snippets,
"actual": "all present" if not missing_review_snippets else {"missing": missing_review_snippets},
"paths": [
required_text_reports["skill_os2_review"],
required_reports["review_studio"],
required_reports["package_verification"],
required_reports["install_simulation"],
required_reports["trust"],
required_reports["context_budget"],
required_reports["benchmark"],
"scripts/ci_test.py",
],
"detail": (
"Manual 2.0 review summaries must not drift from generated gate, package, trust, "
"context, benchmark, or CI evidence."
),
}
+14 -56
View File
@@ -1,6 +1,5 @@
#!/usr/bin/env python3
import argparse
import ast
import json
from datetime import date
from pathlib import Path
@@ -8,6 +7,7 @@ from typing import Any
from evidence_consistency_artifact_roles import build_preflight_artifact_role_handoff_checks
from evidence_consistency_release import build_release_evidence_flow_check
from evidence_consistency_skill_os2_review import build_skill_os2_review_current_evidence_check
from evidence_consistency_world_class import build_world_class_workflow_check
from skill_ir_paths import find_skill_ir_path
@@ -103,20 +103,6 @@ def load_text(path: Path) -> tuple[str, str | None]:
return path.read_text(encoding="utf-8"), None
def ci_default_target_count(path: Path) -> int | None:
if not path.exists():
return None
tree = ast.parse(path.read_text(encoding="utf-8"))
for node in tree.body:
if not isinstance(node, ast.Assign):
continue
if not any(isinstance(target, ast.Name) and target.id == "DEFAULT_TARGETS" for target in node.targets):
continue
if isinstance(node.value, (ast.List, ast.Tuple)):
return len(node.value.elts)
return None
def rel_path(path: Path, root: Path) -> str:
try:
return str(path.resolve().relative_to(root.resolve()))
@@ -660,47 +646,19 @@ def build_report(skill_dir: Path, generated_at: str) -> dict[str, Any]:
)
)
skill_os2_review = text_reports.get("skill_os2_review", "")
ci_target_count = ci_default_target_count(skill_dir / "scripts" / "ci_test.py")
expected_review_snippets = [
f"score `{studio_summary.get('world_class_score')}`",
f"`{studio_summary.get('gate_count')}` gates",
f"`{studio_summary.get('warning_count')}` warnings",
f"`{trust_summary.get('internal_module_count')}` declared internal modules",
(
f"`{trust_summary.get('help_smoke_checked_count')} / {trust_summary.get('help_smoke_checked_count')}` "
f"CLI help smoke checks passing across `{trust_summary.get('script_count')}` scripts"
),
f"`{package_summary.get('archive_entry_count')}` zip entries",
f"archive with `{package_summary.get('archive_entry_count')}` entries",
f"`{install_summary.get('installer_permission_enforced_count')}` installer permission checks enforced",
f"`{install_summary.get('installer_permission_failure_count')}` permission failures",
f"`{benchmark_summary.get('required_artifact_count')}` required artifacts",
f"`{benchmark_summary.get('command_count')}` reproduction commands",
(
f"initial load `{context_stats.get('estimated_initial_load_tokens')}/"
f"{context_stats.get('context_budget_limit')}`"
),
f"target count is `{ci_target_count}`",
]
missing_review_snippets = [snippet for snippet in expected_review_snippets if snippet not in skill_os2_review]
add_check(
checks,
key="skill-os-2-review-current-evidence",
label="Skill OS 2.0 review summary mirrors current evidence",
status="pass" if not missing_review_snippets else "fail",
expected=expected_review_snippets,
actual="all present" if not missing_review_snippets else {"missing": missing_review_snippets},
paths=[
REQUIRED_TEXT_REPORTS["skill_os2_review"],
REQUIRED_REPORTS["review_studio"],
REQUIRED_REPORTS["package_verification"],
REQUIRED_REPORTS["install_simulation"],
REQUIRED_REPORTS["trust"],
REQUIRED_REPORTS["context_budget"],
REQUIRED_REPORTS["benchmark"],
"scripts/ci_test.py",
],
detail="Manual 2.0 review summaries must not drift from generated gate, package, trust, context, benchmark, or CI evidence.",
checks.append(
build_skill_os2_review_current_evidence_check(
skill_dir=skill_dir,
skill_os2_review=skill_os2_review,
studio_summary=studio_summary if isinstance(studio_summary, dict) else {},
trust_summary=trust_summary if isinstance(trust_summary, dict) else {},
package_summary=package_summary if isinstance(package_summary, dict) else {},
install_summary=install_summary if isinstance(install_summary, dict) else {},
benchmark_summary=benchmark_summary if isinstance(benchmark_summary, dict) else {},
context_stats=context_stats if isinstance(context_stats, dict) else {},
required_text_reports=REQUIRED_TEXT_REPORTS,
required_reports=REQUIRED_REPORTS,
)
)
status_counts: dict[str, int] = {"pass": 0, "warn": 0, "fail": 0}
for check in checks:
+1
View File
@@ -35,6 +35,7 @@
"scripts/emit_telemetry_event.py",
"scripts/evidence_consistency_artifact_roles.py",
"scripts/evidence_consistency_release.py",
"scripts/evidence_consistency_skill_os2_review.py",
"scripts/evidence_consistency_world_class.py",
"scripts/export_skill_ir.py",
"scripts/github_benchmark_scan.py",
+2
View File
@@ -99,6 +99,7 @@ def main() -> None:
"scripts/review_studio_gates.py",
"scripts/review_studio_layout.py",
"scripts/evidence_consistency_release.py",
"scripts/evidence_consistency_skill_os2_review.py",
"scripts/evidence_consistency_world_class.py",
"scripts/skill_ir_paths.py",
"scripts/skill_report_charts.py",
@@ -126,6 +127,7 @@ def main() -> None:
assert "review_studio_gates.py" not in warning_text, payload["warnings"]
assert "review_studio_layout.py" not in warning_text, payload["warnings"]
assert "evidence_consistency_release.py" not in warning_text, payload["warnings"]
assert "evidence_consistency_skill_os2_review.py" not in warning_text, payload["warnings"]
assert "evidence_consistency_world_class.py" not in warning_text, payload["warnings"]
assert "skill_ir_paths.py" not in warning_text, payload["warnings"]
assert "skill_report_charts.py" not in warning_text, payload["warnings"]