Extract description optimizer reporting

This commit is contained in:
yaojingang
2026-06-16 17:20:19 +08:00
parent 614c048c61
commit c0abbc5e7d
46 changed files with 641 additions and 570 deletions
+1 -1
View File
@@ -16,7 +16,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565"
"package_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad"
}
]
}
+3 -3
View File
@@ -16,8 +16,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565",
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3"
"package_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b"
},
"compatibility": {
"openai": "pass",
@@ -48,7 +48,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
+1 -1
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-16",
"generated_at": "2026-06-16T09:19:42Z",
"skill_dir": ".",
"source_patterns": "reports/user_patterns.json",
"pattern_count": 5,
+1 -1
View File
@@ -1,6 +1,6 @@
# Adaptation Proposals
- Generated at: `2026-06-16`
- Generated at: `2026-06-16T09:19:42Z`
- Pattern report: `reports/user_patterns.json`
- Proposal only: `true`
- Writes repository files: `false`
+1 -1
View File
@@ -1,7 +1,7 @@
{
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-16",
"generated_at": "2026-06-16T09:19:41Z",
"skill_dir": ".",
"privacy_contract": {
"storage": "local-first",
+11 -18
View File
@@ -4,10 +4,10 @@
"generated_at": "2026-06-16",
"skill_dir": ".",
"summary": {
"python_file_count": 201,
"script_file_count": 130,
"python_file_count": 202,
"script_file_count": 131,
"test_file_count": 71,
"internal_module_count": 47,
"internal_module_count": 48,
"cli_script_count": 85,
"command_handler_count": 68,
"entrypoint_command_handler_count": 18,
@@ -16,7 +16,7 @@
"watch_line_threshold": 720,
"block_line_threshold": 1500,
"largest_file_lines": 852,
"watchlist_count": 3,
"watchlist_count": 2,
"hotspot_count": 0,
"blocker_count": 0,
"decision": "pass"
@@ -36,13 +36,6 @@
"severity": "pass",
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/optimize_description.py",
"lines": 723,
"kind": "cli-script",
"severity": "pass",
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "scripts/trust_check.py",
"lines": 714,
@@ -105,6 +98,13 @@
"kind": "cli-script",
"severity": "pass",
"recommendation": "Move data loading and large section renderers into focused review_studio_* modules."
},
{
"path": "scripts/render_reference_synthesis.py",
"lines": 644,
"kind": "cli-script",
"severity": "pass",
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
}
],
"watchlist": [
@@ -121,13 +121,6 @@
"kind": "test",
"severity": "pass",
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/optimize_description.py",
"lines": 723,
"kind": "cli-script",
"severity": "pass",
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
}
],
"hotspots": [],
+5 -6
View File
@@ -5,17 +5,17 @@ Generated at: `2026-06-16`
## Summary
- decision: `pass`
- python files: `201`
- scripts: `130`
- python files: `202`
- scripts: `131`
- tests: `71`
- internal modules: `47`
- internal modules: `48`
- CLI scripts: `85`
- Yao CLI command handlers: `68`
- entrypoint command handlers: `18`
- command modules: `6`
- largest file lines: `852`
- watch threshold lines: `720`
- watchlist: `3`
- watchlist: `2`
- hotspots: `0`
- blockers: `0`
@@ -31,7 +31,6 @@ No file-size hotspots found.
| --- | ---: | --- | --- |
| `tests/verify_review_studio.py` | `852` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
| `tests/verify_yao_cli.py` | `787` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. |
| `scripts/optimize_description.py` | `723` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. |
## Largest Files
@@ -39,7 +38,6 @@ No file-size hotspots found.
| --- | ---: | --- | --- |
| `tests/verify_review_studio.py` | `852` | `test` | `pass` |
| `tests/verify_yao_cli.py` | `787` | `test` | `pass` |
| `scripts/optimize_description.py` | `723` | `cli-script` | `pass` |
| `scripts/trust_check.py` | `714` | `internal-module` | `pass` |
| `scripts/review_studio_gates.py` | `707` | `internal-module` | `pass` |
| `scripts/apply_adaptation.py` | `706` | `cli-script` | `pass` |
@@ -49,6 +47,7 @@ No file-size hotspots found.
| `tests/verify_world_class_evidence_intake.py` | `660` | `test` | `pass` |
| `scripts/render_skill_os2_coverage.py` | `649` | `cli-script` | `pass` |
| `scripts/render_review_studio.py` | `647` | `cli-script` | `pass` |
| `scripts/render_reference_synthesis.py` | `644` | `cli-script` | `pass` |
## Release Rule
+39 -25
View File
@@ -3,23 +3,36 @@
"ok": true,
"generated_at": "2026-06-16",
"skill_dir": ".",
"commit": "ee8e56b1a9617b0dab170514e4b10713e5ebb2a9",
"commit": "614c048c6131d2a9621d8d7532eba030c729cf59",
"git_status": {
"available": true,
"dirty": false,
"changed_file_count": 0,
"sample": [],
"dirty": true,
"changed_file_count": 46,
"sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/adaptation_proposals.json",
" M reports/adaptation_proposals.md",
" M reports/adoption_drift_report.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"
],
"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": "0e40cccb8f5de72083a28e8853b3fc884d2e7d96fefba5ce4a259cb6c3d566fb",
"source_contract_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565",
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"evidence_bundle_sha256": "e6bd4e91ae854686187353a438c569f380201ce20a686c232397070d777e5a3a",
"source_contract_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"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": 46
},
"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": "ee8e56b1a9617b0dab170514e4b10713e5ebb2a9",
"ready": false,
"commit": "614c048c6131d2a9621d8d7532eba030c729cf59",
"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": "0e40cccb8f5de72083a28e8853b3fc884d2e7d96fefba5ce4a259cb6c3d566fb"
"sha256": "e6bd4e91ae854686187353a438c569f380201ce20a686c232397070d777e5a3a"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -137,8 +151,8 @@
"label": "output_execution",
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7966,
"sha256": "c11a575d231035c3ece411b402384e92703769ec146ed1ac0af76c73dd2ed28f"
"bytes": 7965,
"sha256": "b8e864a66ccfb15f2e6706de37988a1f7a5d17a6d3fba481b8719878fb57f8fc"
},
{
"label": "blind_review",
@@ -172,43 +186,43 @@
"label": "trust_report",
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 123371,
"sha256": "33f8c904a6b85e7141452a15b101590300a5863f958b62d922d29d084400efce"
"bytes": 123972,
"sha256": "0f9e8bdbc6d9574d08b7e1fa115c5b0e1ad10c07ae819d5a73ad8fb69efa5ca7"
},
{
"label": "python_compatibility",
"path": "reports/python_compatibility.json",
"exists": true,
"bytes": 26487,
"sha256": "28cfd0264fda6ea6ceba911faa094003b2b0c0f6baf257e93dd36123e9ce918a"
"bytes": 26621,
"sha256": "2858bfaffd071d838d01d615fb03009c1772bebadeb19f8a1747cb2d21277e80"
},
{
"label": "registry_audit",
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "31b2d0371a2ac9c1c84517c1b286ef10c8768499aa77b977dde48c06783cf54e"
"sha256": "e75a341d15e4d89d46bded0cdb5c1ba378b5674df84d9182eef57c5fb6204c9e"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19338,
"sha256": "2805955a86d5bcac055e809fe094a43dd58c436e61f845fe4969d3e939a589b2"
"sha256": "a27941fdb8651371fc7abc69247e15cf8e2863d5805b0538d67c326d4095148f"
},
{
"label": "install_simulation",
"path": "reports/install_simulation.json",
"exists": true,
"bytes": 8604,
"sha256": "736678ef798a0c21e7a25da7c2865f6c314093f7955a73ff853264e5dc001648"
"sha256": "e29ae26bc97c94ec0a9da3ab60f28ef90e23c9d0c53b777810165224e725b452"
},
{
"label": "skill_os2_audit",
"path": "reports/skill_os2_audit.json",
"exists": true,
"bytes": 14310,
"sha256": "56d96bdccbfca7e4f98aaaabc67dccbd4260aec127c43977cf48a819365f9bf1"
"sha256": "4f64f1cd6c78c3c4e69c35bf921f70c246c3ba3003b8ce6d45da69c8f4aef2b6"
},
{
"label": "world_class_evidence_plan",
+19 -18
View File
@@ -1,19 +1,19 @@
# Benchmark Reproducibility
Generated at: `2026-06-16`
Commit: `ee8e56b1a9617b0dab170514e4b10713e5ebb2a9`
Working tree dirty at generation: `false`
Evidence bundle SHA256: `0e40cccb8f5de72083a28e8853b3fc884d2e7d96fefba5ce4a259cb6c3d566fb`
Commit: `614c048c6131d2a9621d8d7532eba030c729cf59`
Working tree dirty at generation: `true`
Evidence bundle SHA256: `e6bd4e91ae854686187353a438c569f380201ce20a686c232397070d777e5a3a`
## Summary
- reproducibility ready: `true`
- release lock ready: `true`
- release lock ready: `false`
- methodology complete: `true`
- required artifacts: `25`
- missing artifacts: `0`
- source contract sha256: `e30f37d1ae30`
- archive sha256: `a96372e32dc1`
- source contract sha256: `a163b6e288c5`
- archive sha256: `5802e5f52255`
- output cases: `5`
- disclosed failure cases: `3`
- reproduction commands: `23`
@@ -22,8 +22,8 @@ Evidence bundle SHA256: `0e40cccb8f5de72083a28e8853b3fc884d2e7d96fefba5ce4a259cb
- 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: `46`
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: `0e40cccb8f5de72083a28e8853b3fc884d2e7d96fefba5ce4a259cb6c3d566fb`
- sha256: `e6bd4e91ae854686187353a438c569f380201ce20a686c232397070d777e5a3a`
## 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 | `c11a575d2310` |
| output_execution | `reports/output_execution_runs.json` | present | `b8e864a66ccf` |
| 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 | `33f8c904a6b8` |
| python_compatibility | `reports/python_compatibility.json` | present | `28cfd0264fda` |
| registry_audit | `reports/registry_audit.json` | present | `31b2d0371a2a` |
| package_verification | `reports/package_verification.json` | present | `2805955a86d5` |
| install_simulation | `reports/install_simulation.json` | present | `736678ef798a` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `56d96bdccbfc` |
| trust_report | `reports/security_trust_report.json` | present | `0f9e8bdbc6d9` |
| python_compatibility | `reports/python_compatibility.json` | present | `2858bfaffd07` |
| registry_audit | `reports/registry_audit.json` | present | `e75a341d15e4` |
| package_verification | `reports/package_verification.json` | present | `a27941fdb865` |
| install_simulation | `reports/install_simulation.json` | present | `e29ae26bc97c` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `4f64f1cd6c78` |
| 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": 1052541,
"other_text_tokens": 1052782,
"estimated_initial_load_tokens": 990,
"estimated_total_text_tokens": 1053338,
"deferred_resource_tokens": 487219,
"estimated_total_text_tokens": 1053579,
"deferred_resource_tokens": 487270,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 427121,
"file_count": 130
"estimated_tokens": 427172,
"file_count": 131
},
{
"path": "references",
@@ -36,8 +36,8 @@
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 427121,
"file_count": 130
"estimated_tokens": 427172,
"file_count": 131
}
],
"deferred_resource_governance": {
@@ -59,14 +59,14 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 427121,
"file_count": 130,
"estimated_tokens": 427172,
"file_count": 131,
"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": 648,
"relevant_file_count": 650,
"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 | 487219 | `governed` | scripts:427121 | 131.3 | - | ok |
| root | `.` | `production` | 1000 | 990 | 797 | 487270 | `governed` | scripts:427172 | 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": 487219,
"deferred_resource_tokens": 487270,
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 427121,
"file_count": 130
"estimated_tokens": 427172,
"file_count": 131
}
],
"deferred_resource_governance": {
@@ -35,8 +35,8 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 427121,
"file_count": 130,
"estimated_tokens": 427172,
"file_count": 131,
"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 487219/120000; top deferred scripts 427121; resource governance governed; quality density 131.3",
"detail": "initial load 990/1000; deferred 487270/120000; top deferred scripts 427172; resource governance governed; quality density 131.3",
"evidence": "reports/context_budget.json"
},
"actual": {
"status": "pass",
"detail": "initial load 990/1000; deferred 487219/120000; top deferred scripts 427121; resource governance governed; quality density 131.3",
"detail": "initial load 990/1000; deferred 487270/120000; top deferred scripts 427172; 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": "ee8e56b1a9617b0dab170514e4b10713e5ebb2a9",
"actual": "ee8e56b1a9617b0dab170514e4b10713e5ebb2a9",
"expected": "614c048c6131d2a9621d8d7532eba030c729cf59",
"actual": "614c048c6131d2a9621d8d7532eba030c729cf59",
"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": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565",
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"source_contract_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"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": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565",
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"source_contract_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"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": "ee8e56b1a9617b0dab170514e4b10713e5ebb2a9",
"actual": "ee8e56b1a9617b0dab170514e4b10713e5ebb2a9",
"expected": "614c048c6131d2a9621d8d7532eba030c729cf59",
"actual": "614c048c6131d2a9621d8d7532eba030c729cf59",
"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": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565",
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"source_contract_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"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": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565",
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"source_contract_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"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": 130
"file_count": 131
},
{
"path": "evals",
@@ -1527,7 +1527,7 @@
"file_count": 229
}
],
"file_count": 427,
"file_count": 428,
"folder_count": 4,
"distribution": [
{
@@ -1552,7 +1552,7 @@
},
{
"label": "scripts",
"value": 130
"value": 131
},
{
"label": "evals",
@@ -1600,7 +1600,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 130
"file_count": 131
},
{
"path": "evals",
@@ -1615,7 +1615,7 @@
"file_count": 229
}
],
"file_count": 427,
"file_count": 428,
"folder_count": 4,
"distribution": [
{
@@ -1640,7 +1640,7 @@
},
{
"label": "scripts",
"value": 130
"value": 131
},
{
"label": "evals",
@@ -2404,10 +2404,10 @@
"score `91`",
"`16` gates",
"`3` warnings",
"`44` declared internal modules",
"`86 / 86` CLI help smoke checks passing across `130` scripts",
"`657` zip entries",
"archive with `657` entries",
"`45` declared internal modules",
"`86 / 86` CLI help smoke checks passing across `131` scripts",
"`658` zip entries",
"archive with `658` 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": 657,
"archive_entry_count": 658,
"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": 31.58,
"duration_ms": 29.41,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -62,7 +62,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.31,
"duration_ms": 30.5,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -85,7 +85,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.4,
"duration_ms": 29.08,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -113,7 +113,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.32,
"duration_ms": 29.83,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -136,7 +136,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.69,
"duration_ms": 29.48,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -164,7 +164,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.71,
"duration_ms": 29.95,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -187,7 +187,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 31.58,
"duration_ms": 30.2,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -214,7 +214,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 31.42,
"duration_ms": 31.02,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -237,7 +237,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.28,
"duration_ms": 33.87,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -266,7 +266,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 31.74,
"duration_ms": 35.57,
"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 | 31.58 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 32.31 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 32.4 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 32.32 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 32.69 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 32.71 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 31.58 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 31.42 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 32.28 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 31.74 | 98 | 100.0 | pass |
| skill-package-contract | baseline | command | local-output-eval-runner | 29.41 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 30.5 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 29.08 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.83 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 29.48 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 29.95 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 30.2 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 31.02 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 33.87 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 35.57 | 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": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"archive_entry_count": 657,
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"archive_entry_count": 658,
"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: `a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3`
- Archive SHA256: `5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b`
- Failures: `0`
- Warnings: `0`
+7 -1
View File
@@ -5,7 +5,7 @@
"root": ".",
"summary": {
"target_python": "3.11",
"file_count": 204,
"file_count": 205,
"issue_count": 0,
"syntax_error_count": 0,
"fstring_311_violation_count": 0,
@@ -118,6 +118,12 @@
"issue_count": 0,
"issues": []
},
{
"path": "scripts/description_optimizer_reporting.py",
"ok": true,
"issue_count": 0,
"issues": []
},
{
"path": "scripts/diff_eval.py",
"ok": true,
+1 -1
View File
@@ -6,7 +6,7 @@ Generated at: `2026-06-16`
- decision: `pass`
- target python: `3.11`
- files scanned: `204`
- files scanned: `205`
- 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": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565",
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3"
"package_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b"
},
"compatibility": {
"openai": "pass",
@@ -53,7 +53,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"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": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565"
"package_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad"
}
]
},
+2 -2
View File
@@ -6,8 +6,8 @@
- Maturity: `governed`
- Owner: `Yao Team`
- License: `MIT`
- Package SHA256: `e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565`
- Archive SHA256: `a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3`
- Package SHA256: `a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad`
- Archive SHA256: `5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b`
- Install simulated: `True`
## Compatibility
+13 -13
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>20/21</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>130 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>204 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>852 largest lines; 3 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>657 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>131 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>205 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>852 largest lines; 2 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>658 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 487219/120000; top deferred scripts 427121; 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; 130 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; 204 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>201 Python files; 0 hotspots; 3 watchlist files; 0 blockers; largest 852 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 487270/120000; top deferred scripts 427172; 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; 131 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; 205 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>202 Python files; 0 hotspots; 2 watchlist files; 0 blockers; largest 852 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>
<section>
@@ -812,17 +812,17 @@
</section>
<section class="twocol">
<div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 487219/120000; top deferred scripts 427121; resource governance governed; quality density 131.3</p></div>
<div class="panel"><h2>上下文</h2><p>initial load 990/1000; deferred 487270/120000; top deferred scripts 427172; 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>130</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>e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565</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>131</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>a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad</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>204</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>205</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>
@@ -842,14 +842,14 @@
</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>
@@ -877,13 +877,13 @@
</section>
<section class="twocol">
<div class="panel"><h2>蓝图覆盖</h2><dl class='kv-grid'><div><dt>项目数</dt><dd>21</dd></div><div><dt>模块数</dt><dd>8</dd></div><div><dt>建议 PR</dt><dd>13</dd></div><div><dt>通过数</dt><dd>20</dd></div><div><dt>Warn Count</dt><dd>1</dd></div><div><dt>缺失数</dt><dd>0</dd></div><div><dt>Extension Track Count</dt><dd>4</dd></div><div><dt>Extension Covered Count</dt><dd>4</dd></div><div><dt>Extension Partial Count</dt><dd>0</dd></div><div><dt>Extension Planned Count</dt><dd>0</dd></div><div><dt>Adaptive Extension Ready</dt><dd></dd></div><div><dt>本地蓝图</dt><dd></dd></div><div><dt>世界级</dt><dd></dd></div><div><dt>待补证据</dt><dd>4</dd></div></dl></div>
<div class="panel"><h2>蓝图覆盖</h2><dl class='kv-grid'><div><dt>项目数</dt><dd>21</dd></div><div><dt>模块数</dt><dd>8</dd></div><div><dt>建议 PR</dt><dd>13</dd></div><div><dt>通过数</dt><dd>21</dd></div><div><dt>Warn Count</dt><dd>0</dd></div><div><dt>缺失数</dt><dd>0</dd></div><div><dt>Extension Track Count</dt><dd>4</dd></div><div><dt>Extension Covered Count</dt><dd>4</dd></div><div><dt>Extension Partial Count</dt><dd>0</dd></div><div><dt>Extension Planned Count</dt><dd>0</dd></div><div><dt>Adaptive Extension Ready</dt><dd></dd></div><div><dt>本地蓝图</dt><dd></dd></div><div><dt>世界级</dt><dd></dd></div><div><dt>待补证据</dt><dd>4</dd></div></dl></div>
<div class="panel"><h2>覆盖边界</h2><p>蓝图覆盖只证明 2.0 模块、建议 PR、脚本、报告和测试在本地闭环;public world-class 仍以 world-class evidence ledger 的真人和外部证据为准。</p></div>
</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">
@@ -903,12 +903,12 @@
<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>a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3</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>5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b</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>657</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>a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3</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>658</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>5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b</code></dd></div></dl></div>
</section>
<section class="twocol">
+163 -131
View File
@@ -44,7 +44,7 @@
"key": "context-budget",
"label": "上下文",
"status": "pass",
"detail": "initial load 990/1000; deferred 487219/120000; top deferred scripts 427121; resource governance governed; quality density 131.3",
"detail": "initial load 990/1000; deferred 487270/120000; top deferred scripts 427172; resource governance governed; quality density 131.3",
"evidence": "reports/context_budget.json",
"link": "context_budget.md"
},
@@ -60,7 +60,7 @@
"key": "trust-report",
"label": "信任报告",
"status": "pass",
"detail": "0 secrets; 130 scripts; 3 network-capable scripts; 0 help smoke failures",
"detail": "0 secrets; 131 scripts; 3 network-capable scripts; 0 help smoke failures",
"evidence": "reports/security_trust_report.json",
"link": "security_trust_report.md"
},
@@ -68,7 +68,7 @@
"key": "python-compat",
"label": "Python 兼容",
"status": "pass",
"detail": "Python 3.11; 204 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards",
"detail": "Python 3.11; 205 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards",
"evidence": "reports/python_compatibility.json",
"link": "python_compatibility.md"
},
@@ -76,7 +76,7 @@
"key": "architecture-maintainability",
"label": "架构维护",
"status": "pass",
"detail": "201 Python files; 0 hotspots; 3 watchlist files; 0 blockers; largest 852 lines; 68 CLI handlers; 18 in entrypoint",
"detail": "202 Python files; 0 hotspots; 2 watchlist files; 0 blockers; largest 852 lines; 68 CLI handlers; 18 in entrypoint",
"evidence": "reports/architecture_maintainability.json",
"link": "architecture_maintainability.md"
},
@@ -108,7 +108,7 @@
"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"
},
@@ -1484,7 +1484,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 130
"file_count": 131
},
{
"path": "evals",
@@ -1499,7 +1499,7 @@
"file_count": 229
}
],
"file_count": 427,
"file_count": 428,
"folder_count": 4,
"distribution": [
{
@@ -1524,7 +1524,7 @@
},
{
"label": "scripts",
"value": 130
"value": 131
},
{
"label": "evals",
@@ -1654,7 +1654,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 130
"file_count": 131
},
{
"path": "evals",
@@ -1968,13 +1968,13 @@
"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": "0e40cccb8f5de72083a28e8853b3fc884d2e7d96fefba5ce4a259cb6c3d566fb",
"source_contract_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565",
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"evidence_bundle_sha256": "e6bd4e91ae854686187353a438c569f380201ce20a686c232397070d777e5a3a",
"source_contract_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 23,
@@ -1992,11 +1992,11 @@
"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": 46
},
"commit": "ee8e56b1a9617b0dab170514e4b10713e5ebb2a9",
"commit": "614c048c6131d2a9621d8d7532eba030c729cf59",
"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.",
@@ -2080,9 +2080,9 @@
"failures": []
},
"trust_security": {
"scanned_files": 221,
"script_count": 130,
"internal_module_count": 44,
"scanned_files": 222,
"script_count": 131,
"internal_module_count": 45,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -2100,8 +2100,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 221,
"package_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565"
"package_hash_file_count": 222,
"package_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad"
},
"skill_atlas": {
"skill_count": 12,
@@ -2139,8 +2139,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565",
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3"
"package_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b"
},
"compatibility": {
"openai": "pass",
@@ -2171,7 +2171,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -2187,8 +2187,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"archive_entry_count": 657,
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"archive_entry_count": 658,
"failure_count": 0,
"warning_count": 0
},
@@ -2199,7 +2199,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 657,
"archive_entry_count": 658,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -2266,12 +2266,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3"
"to": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565"
"to": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad"
}
]
},
@@ -4688,7 +4688,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 31.58,
"duration_ms": 29.41,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4716,7 +4716,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.31,
"duration_ms": 30.5,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4739,7 +4739,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.4,
"duration_ms": 29.08,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4767,7 +4767,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.32,
"duration_ms": 29.83,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4790,7 +4790,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.69,
"duration_ms": 29.48,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4818,7 +4818,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.71,
"duration_ms": 29.95,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4841,7 +4841,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 31.58,
"duration_ms": 30.2,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4868,7 +4868,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 31.42,
"duration_ms": 31.02,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4891,7 +4891,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 32.28,
"duration_ms": 33.87,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4920,7 +4920,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 31.74,
"duration_ms": 35.57,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -5646,23 +5646,36 @@
"ok": true,
"generated_at": "2026-06-16",
"skill_dir": ".",
"commit": "ee8e56b1a9617b0dab170514e4b10713e5ebb2a9",
"commit": "614c048c6131d2a9621d8d7532eba030c729cf59",
"git_status": {
"available": true,
"dirty": false,
"changed_file_count": 0,
"sample": [],
"dirty": true,
"changed_file_count": 46,
"sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/adaptation_proposals.json",
" M reports/adaptation_proposals.md",
" M reports/adoption_drift_report.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"
],
"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": "0e40cccb8f5de72083a28e8853b3fc884d2e7d96fefba5ce4a259cb6c3d566fb",
"source_contract_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565",
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"evidence_bundle_sha256": "e6bd4e91ae854686187353a438c569f380201ce20a686c232397070d777e5a3a",
"source_contract_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 23,
@@ -5680,14 +5693,15 @@
"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": 46
},
"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)",
@@ -5696,10 +5710,10 @@
"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": "ee8e56b1a9617b0dab170514e4b10713e5ebb2a9",
"ready": false,
"commit": "614c048c6131d2a9621d8d7532eba030c729cf59",
"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)",
@@ -5707,7 +5721,7 @@
"existing_count": 25,
"missing_count": 0,
"missing_paths": [],
"sha256": "0e40cccb8f5de72083a28e8853b3fc884d2e7d96fefba5ce4a259cb6c3d566fb"
"sha256": "e6bd4e91ae854686187353a438c569f380201ce20a686c232397070d777e5a3a"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -5780,8 +5794,8 @@
"label": "output_execution",
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7966,
"sha256": "c11a575d231035c3ece411b402384e92703769ec146ed1ac0af76c73dd2ed28f"
"bytes": 7965,
"sha256": "b8e864a66ccfb15f2e6706de37988a1f7a5d17a6d3fba481b8719878fb57f8fc"
},
{
"label": "blind_review",
@@ -5815,43 +5829,43 @@
"label": "trust_report",
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 123371,
"sha256": "33f8c904a6b85e7141452a15b101590300a5863f958b62d922d29d084400efce"
"bytes": 123972,
"sha256": "0f9e8bdbc6d9574d08b7e1fa115c5b0e1ad10c07ae819d5a73ad8fb69efa5ca7"
},
{
"label": "python_compatibility",
"path": "reports/python_compatibility.json",
"exists": true,
"bytes": 26487,
"sha256": "28cfd0264fda6ea6ceba911faa094003b2b0c0f6baf257e93dd36123e9ce918a"
"bytes": 26621,
"sha256": "2858bfaffd071d838d01d615fb03009c1772bebadeb19f8a1747cb2d21277e80"
},
{
"label": "registry_audit",
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "31b2d0371a2ac9c1c84517c1b286ef10c8768499aa77b977dde48c06783cf54e"
"sha256": "e75a341d15e4d89d46bded0cdb5c1ba378b5674df84d9182eef57c5fb6204c9e"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19338,
"sha256": "2805955a86d5bcac055e809fe094a43dd58c436e61f845fe4969d3e939a589b2"
"sha256": "a27941fdb8651371fc7abc69247e15cf8e2863d5805b0538d67c326d4095148f"
},
{
"label": "install_simulation",
"path": "reports/install_simulation.json",
"exists": true,
"bytes": 8604,
"sha256": "736678ef798a0c21e7a25da7c2865f6c314093f7955a73ff853264e5dc001648"
"sha256": "e29ae26bc97c94ec0a9da3ab60f28ef90e23c9d0c53b777810165224e725b452"
},
{
"label": "skill_os2_audit",
"path": "reports/skill_os2_audit.json",
"exists": true,
"bytes": 14310,
"sha256": "56d96bdccbfca7e4f98aaaabc67dccbd4260aec127c43977cf48a819365f9bf1"
"sha256": "4f64f1cd6c78c3c4e69c35bf921f70c246c3ba3003b8ce6d45da69c8f4aef2b6"
},
{
"label": "world_class_evidence_plan",
@@ -6060,22 +6074,22 @@
"item_count": 21,
"module_count": 8,
"recommended_pr_count": 13,
"pass_count": 20,
"warn_count": 1,
"pass_count": 21,
"warn_count": 0,
"missing_count": 0,
"extension_track_count": 4,
"extension_partial_count": 0,
"extension_planned_count": 0,
"extension_covered_count": 4,
"adaptive_extension_ready": true,
"local_blueprint_ready": false,
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_evidence_pending_count": 4,
"decision": "continue-implementation"
"decision": "local-blueprint-covered-evidence-pending"
},
"status_counts": {
"pass": 20,
"warn": 1,
"pass": 21,
"warn": 0,
"missing": 0
},
"extension_status_counts": {
@@ -6183,7 +6197,7 @@
"label": "Trust Security",
"status": "pass",
"objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
"current": "130 scripts; secrets 0; help failures 0",
"current": "131 scripts; secrets 0; help failures 0",
"command": "python3 scripts/yao.py trust .",
"test": "python3 tests/verify_trust_check.py",
"evidence": [
@@ -6257,7 +6271,7 @@
"label": "Registry Distribution",
"status": "pass",
"objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
"current": "archive entries 657; install failures 0",
"current": "archive entries 658; 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": [
@@ -6664,7 +6678,7 @@
"key": "evidence-consistency",
"category": "recommended-pr",
"label": "Evidence Consistency",
"status": "warn",
"status": "pass",
"objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
"current": "35 consistency checks",
"command": "make ci-test",
@@ -12070,9 +12084,9 @@
"ok": true,
"skill_dir": ".",
"summary": {
"scanned_files": 221,
"script_count": 130,
"internal_module_count": 44,
"scanned_files": 222,
"script_count": 131,
"internal_module_count": 45,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -12090,8 +12104,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 221,
"package_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565"
"package_hash_file_count": 222,
"package_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad"
},
"failures": [],
"warnings": [],
@@ -12284,6 +12298,20 @@
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/description_optimizer_reporting.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by optimize_description.py to render description optimization reports.",
"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/diff_eval.py",
"interface": "cli",
@@ -13969,7 +13997,7 @@
"checked_count": 86,
"passed_count": 86,
"failed_count": 0,
"skipped_count": 44,
"skipped_count": 45,
"failed_scripts": [],
"results": [
{
@@ -14842,6 +14870,10 @@
"path": "scripts/compile_skill_targets.py",
"reason": "internal module"
},
{
"path": "scripts/description_optimizer_reporting.py",
"reason": "internal module"
},
{
"path": "scripts/evidence_consistency_artifact_roles.py",
"reason": "internal module"
@@ -15205,7 +15237,7 @@
"root": ".",
"summary": {
"target_python": "3.11",
"file_count": 204,
"file_count": 205,
"issue_count": 0,
"syntax_error_count": 0,
"fstring_311_violation_count": 0,
@@ -15318,6 +15350,12 @@
"issue_count": 0,
"issues": []
},
{
"path": "scripts/description_optimizer_reporting.py",
"ok": true,
"issue_count": 0,
"issues": []
},
{
"path": "scripts/diff_eval.py",
"ok": true,
@@ -16459,10 +16497,10 @@
"generated_at": "2026-06-16",
"skill_dir": ".",
"summary": {
"python_file_count": 201,
"script_file_count": 130,
"python_file_count": 202,
"script_file_count": 131,
"test_file_count": 71,
"internal_module_count": 47,
"internal_module_count": 48,
"cli_script_count": 85,
"command_handler_count": 68,
"entrypoint_command_handler_count": 18,
@@ -16471,7 +16509,7 @@
"watch_line_threshold": 720,
"block_line_threshold": 1500,
"largest_file_lines": 852,
"watchlist_count": 3,
"watchlist_count": 2,
"hotspot_count": 0,
"blocker_count": 0,
"decision": "pass"
@@ -16491,13 +16529,6 @@
"severity": "pass",
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/optimize_description.py",
"lines": 723,
"kind": "cli-script",
"severity": "pass",
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
},
{
"path": "scripts/trust_check.py",
"lines": 714,
@@ -16560,6 +16591,13 @@
"kind": "cli-script",
"severity": "pass",
"recommendation": "Move data loading and large section renderers into focused review_studio_* modules."
},
{
"path": "scripts/render_reference_synthesis.py",
"lines": 644,
"kind": "cli-script",
"severity": "pass",
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
}
],
"watchlist": [
@@ -16576,13 +16614,6 @@
"kind": "test",
"severity": "pass",
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
},
{
"path": "scripts/optimize_description.py",
"lines": 723,
"kind": "cli-script",
"severity": "pass",
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
}
],
"hotspots": [],
@@ -16600,16 +16631,16 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 797,
"other_text_tokens": 1052541,
"other_text_tokens": 1052782,
"estimated_initial_load_tokens": 990,
"estimated_total_text_tokens": 1053338,
"deferred_resource_tokens": 487219,
"estimated_total_text_tokens": 1053579,
"deferred_resource_tokens": 487270,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 427121,
"file_count": 130
"estimated_tokens": 427172,
"file_count": 131
},
{
"path": "references",
@@ -16630,8 +16661,8 @@
"large_deferred_resource_dirs": [
{
"path": "scripts",
"estimated_tokens": 427121,
"file_count": 130
"estimated_tokens": 427172,
"file_count": 131
}
],
"deferred_resource_governance": {
@@ -16653,14 +16684,14 @@
],
"missing": [],
"path": "scripts",
"estimated_tokens": 427121,
"file_count": 130,
"estimated_tokens": 427172,
"file_count": 131,
"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": 648,
"relevant_file_count": 650,
"unused_resource_dirs": [],
"quality_signal_points": 130,
"quality_density": 131.3
@@ -17537,6 +17568,7 @@
"scripts/context_sizer.py",
"scripts/create_iteration_snapshot.py",
"scripts/cross_packager.py",
"scripts/description_optimizer_reporting.py",
"scripts/diff_eval.py",
"scripts/emit_telemetry_event.py",
"scripts/evidence_consistency_artifact_roles.py",
@@ -18555,7 +18587,7 @@
"adoption_drift": {
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-16",
"generated_at": "2026-06-16T09:19:41Z",
"skill_dir": ".",
"privacy_contract": {
"storage": "local-first",
@@ -18639,7 +18671,7 @@
"daily_skillops": {
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-16",
"generated_at": "2026-06-16T09:19:42Z",
"skill_dir": ".",
"decision": "proposal-review",
"source_supplied": false,
@@ -18649,10 +18681,10 @@
"pending_review_count": 0,
"applied_count": 0,
"rollback_count": 0,
"local_blueprint_ready": false,
"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,
@@ -18666,10 +18698,10 @@
"pending_review_count": 0,
"applied_count": 0,
"rollback_count": 0,
"local_blueprint_ready": false,
"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,
@@ -19115,10 +19147,10 @@
"rollback_count": 0
},
"release_state": {
"local_blueprint_ready": false,
"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": [
@@ -19153,7 +19185,7 @@
"weekly_curator": {
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-16",
"generated_at": "2026-06-16T09:19:42Z",
"skill_dir": ".",
"decision": "curator-review",
"week_id": "2026-W25",
@@ -19167,7 +19199,7 @@
"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,
@@ -19187,7 +19219,7 @@
"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,
@@ -19439,7 +19471,7 @@
"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
@@ -19617,7 +19649,7 @@
"adaptation_proposals": {
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-16",
"generated_at": "2026-06-16T09:19:42Z",
"skill_dir": ".",
"source_patterns": "reports/user_patterns.json",
"pattern_count": 5,
@@ -23549,8 +23581,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565",
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3"
"package_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b"
},
"compatibility": {
"openai": "pass",
@@ -23581,7 +23613,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -23606,7 +23638,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565"
"package_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad"
}
]
},
@@ -23629,8 +23661,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"archive_entry_count": 657,
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"archive_entry_count": 658,
"failure_count": 0,
"warning_count": 0
},
@@ -24295,7 +24327,7 @@
"installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill",
"summary": {
"archive_present": true,
"archive_entry_count": 657,
"archive_entry_count": 658,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -24637,12 +24669,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3"
"to": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565"
"to": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad"
}
]
},
+25 -25
View File
@@ -513,7 +513,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 130
"file_count": 131
},
{
"path": "evals",
@@ -528,7 +528,7 @@
"file_count": 229
}
],
"file_count": 427,
"file_count": 428,
"folder_count": 4,
"distribution": [
{
@@ -553,7 +553,7 @@
},
{
"label": "scripts",
"value": 130
"value": 131
},
{
"label": "evals",
@@ -683,7 +683,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 130
"file_count": 131
},
{
"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": "0e40cccb8f5de72083a28e8853b3fc884d2e7d96fefba5ce4a259cb6c3d566fb",
"source_contract_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565",
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"evidence_bundle_sha256": "e6bd4e91ae854686187353a438c569f380201ce20a686c232397070d777e5a3a",
"source_contract_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"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": 46
},
"commit": "ee8e56b1a9617b0dab170514e4b10713e5ebb2a9",
"commit": "614c048c6131d2a9621d8d7532eba030c729cf59",
"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": 221,
"script_count": 130,
"internal_module_count": 44,
"scanned_files": 222,
"script_count": 131,
"internal_module_count": 45,
"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": 221,
"package_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565"
"package_hash_file_count": 222,
"package_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad"
},
"skill_atlas": {
"skill_count": 12,
@@ -1168,8 +1168,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565",
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3"
"package_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b"
},
"compatibility": {
"openai": "pass",
@@ -1200,7 +1200,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"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": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"archive_entry_count": 657,
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"archive_entry_count": 658,
"failure_count": 0,
"warning_count": 0
},
@@ -1228,7 +1228,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 657,
"archive_entry_count": 658,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1295,12 +1295,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3"
"to": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565"
"to": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad"
}
]
},
+24 -6
View File
@@ -2,9 +2,9 @@
"ok": true,
"skill_dir": ".",
"summary": {
"scanned_files": 221,
"script_count": 130,
"internal_module_count": 44,
"scanned_files": 222,
"script_count": 131,
"internal_module_count": 45,
"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": 221,
"package_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565"
"package_hash_file_count": 222,
"package_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad"
},
"failures": [],
"warnings": [],
@@ -216,6 +216,20 @@
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/description_optimizer_reporting.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by optimize_description.py to render description optimization reports.",
"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/diff_eval.py",
"interface": "cli",
@@ -1901,7 +1915,7 @@
"checked_count": 86,
"passed_count": 86,
"failed_count": 0,
"skipped_count": 44,
"skipped_count": 45,
"failed_scripts": [],
"results": [
{
@@ -2774,6 +2788,10 @@
"path": "scripts/compile_skill_targets.py",
"reason": "internal module"
},
{
"path": "scripts/description_optimizer_reporting.py",
"reason": "internal module"
},
{
"path": "scripts/evidence_consistency_artifact_roles.py",
"reason": "internal module"
+6 -5
View File
@@ -1,9 +1,9 @@
# Security Trust Report
- OK: `True`
- Scanned files: `221`
- Scripts: `130`
- Internal script modules: `44`
- Scanned files: `222`
- Scripts: `131`
- Internal script modules: `45`
- 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: `221`
- Package SHA256: `e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565`
- Package hash files: `222`
- Package SHA256: `a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad`
## Failures
@@ -75,6 +75,7 @@
| scripts/context_sizer.py | cli | False | True | True | False | False | False | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/create_iteration_snapshot.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/cross_packager.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/description_optimizer_reporting.py | internal-module | True | False | False | False | False | False | False | Imported by optimize_description.py to render description optimization reports. |
| scripts/diff_eval.py | cli | False | True | True | False | False | False | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| 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. |
+1 -1
View File
@@ -921,7 +921,7 @@
<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="20.7 79.3" 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="76.9 23.1" stroke-dashoffset="-23.1" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">427</text><text data-lang="en" x="130" y="136" text-anchor="middle">427 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="20.6 79.4" 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="77.1 22.9" stroke-dashoffset="-22.9" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">428</text><text data-lang="en" x="130" y="136" text-anchor="middle">428 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": 130
"file_count": 131
},
{
"path": "evals",
@@ -528,7 +528,7 @@
"file_count": 229
}
],
"file_count": 427,
"file_count": 428,
"folder_count": 4,
"distribution": [
{
@@ -553,7 +553,7 @@
},
{
"label": "scripts",
"value": 130
"value": 131
},
{
"label": "evals",
@@ -687,7 +687,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 130
"file_count": 131
},
{
"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": "0e40cccb8f5de72083a28e8853b3fc884d2e7d96fefba5ce4a259cb6c3d566fb",
"source_contract_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565",
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"evidence_bundle_sha256": "e6bd4e91ae854686187353a438c569f380201ce20a686c232397070d777e5a3a",
"source_contract_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"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": 46
},
"commit": "ee8e56b1a9617b0dab170514e4b10713e5ebb2a9",
"commit": "614c048c6131d2a9621d8d7532eba030c729cf59",
"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": 221,
"script_count": 130,
"internal_module_count": 44,
"scanned_files": 222,
"script_count": 131,
"internal_module_count": 45,
"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": 221,
"package_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565"
"package_hash_file_count": 222,
"package_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad"
},
"skill_atlas": {
"skill_count": 12,
@@ -1172,8 +1172,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565",
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3"
"package_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b"
},
"compatibility": {
"openai": "pass",
@@ -1204,7 +1204,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"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": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"archive_entry_count": 657,
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"archive_entry_count": 658,
"failure_count": 0,
"warning_count": 0
},
@@ -1232,7 +1232,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 657,
"archive_entry_count": 658,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1299,12 +1299,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3"
"to": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565"
"to": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad"
}
]
},
+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, `44` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `86 / 86` CLI help smoke checks passing across `130` scripts, source-contract hash scope explicit |
| Trust | `0` secret findings, `1` pinned dependency file, `45` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `86 / 86` CLI help smoke checks passing across `131` 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, `657` zip entries, `0` failures, `0` warnings |
| Install Simulation | archive with `657` 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, `658` zip entries, `0` failures, `0` warnings |
| Install Simulation | archive with `658` 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
@@ -921,7 +921,7 @@
<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="20.7 79.3" 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="76.9 23.1" stroke-dashoffset="-23.1" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">427</text><text data-lang="en" x="130" y="136" text-anchor="middle">427 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="20.6 79.4" 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="77.1 22.9" stroke-dashoffset="-22.9" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">428</text><text data-lang="en" x="130" y="136" text-anchor="middle">428 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": 130
"file_count": 131
},
{
"path": "evals",
@@ -527,7 +527,7 @@
"file_count": 229
}
],
"file_count": 427,
"file_count": 428,
"folder_count": 4,
"distribution": [
{
@@ -552,7 +552,7 @@
},
{
"label": "scripts",
"value": 130
"value": 131
},
{
"label": "evals",
@@ -682,7 +682,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 130
"file_count": 131
},
{
"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": "0e40cccb8f5de72083a28e8853b3fc884d2e7d96fefba5ce4a259cb6c3d566fb",
"source_contract_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565",
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"evidence_bundle_sha256": "e6bd4e91ae854686187353a438c569f380201ce20a686c232397070d777e5a3a",
"source_contract_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"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": 46
},
"commit": "ee8e56b1a9617b0dab170514e4b10713e5ebb2a9",
"commit": "614c048c6131d2a9621d8d7532eba030c729cf59",
"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": 221,
"script_count": 130,
"internal_module_count": 44,
"scanned_files": 222,
"script_count": 131,
"internal_module_count": 45,
"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": 221,
"package_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565"
"package_hash_file_count": 222,
"package_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad"
},
"skill_atlas": {
"skill_count": 12,
@@ -1167,8 +1167,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565",
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3"
"package_sha256": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b"
},
"compatibility": {
"openai": "pass",
@@ -1199,7 +1199,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"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": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3",
"archive_entry_count": 657,
"archive_sha256": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b",
"archive_entry_count": 658,
"failure_count": 0,
"warning_count": 0
},
@@ -1227,7 +1227,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 657,
"archive_entry_count": 658,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1294,12 +1294,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3"
"to": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565"
"to": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad"
}
]
},
+1
View File
@@ -77,6 +77,7 @@
"scripts/context_sizer.py",
"scripts/create_iteration_snapshot.py",
"scripts/cross_packager.py",
"scripts/description_optimizer_reporting.py",
"scripts/diff_eval.py",
"scripts/emit_telemetry_event.py",
"scripts/evidence_consistency_artifact_roles.py",
+2 -2
View File
@@ -197,7 +197,7 @@
"key": "trust-security",
"label": "Trust Security",
"status": "pass",
"current": "secrets 0; scripts 130; help failures 0",
"current": "secrets 0; scripts 131; 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 657; install failures 0; permission failures 0",
"current": "zip entries 658; install failures 0; permission failures 0",
"target": "Package metadata, archive checksum, package verification, and install simulation pass",
"evidence": [
{
+2 -2
View File
@@ -23,11 +23,11 @@ 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 130; 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 131; 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 657; 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. |
| Registry Distribution | pass | zip entries 658; 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. |
| 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. |
+9 -9
View File
@@ -7,22 +7,22 @@
"item_count": 21,
"module_count": 8,
"recommended_pr_count": 13,
"pass_count": 20,
"warn_count": 1,
"pass_count": 21,
"warn_count": 0,
"missing_count": 0,
"extension_track_count": 4,
"extension_partial_count": 0,
"extension_planned_count": 0,
"extension_covered_count": 4,
"adaptive_extension_ready": true,
"local_blueprint_ready": false,
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_evidence_pending_count": 4,
"decision": "continue-implementation"
"decision": "local-blueprint-covered-evidence-pending"
},
"status_counts": {
"pass": 20,
"warn": 1,
"pass": 21,
"warn": 0,
"missing": 0
},
"extension_status_counts": {
@@ -130,7 +130,7 @@
"label": "Trust Security",
"status": "pass",
"objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
"current": "130 scripts; secrets 0; help failures 0",
"current": "131 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 657; install failures 0",
"current": "archive entries 658; 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": [
@@ -611,7 +611,7 @@
"key": "evidence-consistency",
"category": "recommended-pr",
"label": "Evidence Consistency",
"status": "warn",
"status": "pass",
"objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
"current": "35 consistency checks",
"command": "make ci-test",
+8 -8
View File
@@ -4,12 +4,12 @@ Generated at: `2026-06-16`
## Summary
- decision: `continue-implementation`
- local blueprint ready: `false`
- decision: `local-blueprint-covered-evidence-pending`
- local blueprint ready: `true`
- public world-class ready: `false`
- pass: `20` / `21`
- pass: `21` / `21`
- missing: `0`
- warn: `1`
- warn: `0`
- reference extensions: `4`
- extension covered: `4`
- extension partial: `0`
@@ -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` | 130 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` |
| Trust Security | `pass` | 131 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 657; 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 658; 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` |
@@ -48,7 +48,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
| Registry Package Format | `pass` | registry ok True | `make ci-test` | `tests/verify_registry_audit.py` |
| Review Studio 2.0 | `pass` | 16 review gates | `make ci-test` | `tests/verify_review_studio.py` |
| Migration V2 Docs | `pass` | migration guide present | `make ci-test` | `docs review` |
| Evidence Consistency | `warn` | 35 consistency checks | `make ci-test` | `tests/verify_evidence_consistency.py` |
| Evidence Consistency | `pass` | 35 consistency checks | `make ci-test` | `tests/verify_evidence_consistency.py` |
## Reference Extension Tracks
@@ -213,7 +213,7 @@ These extension tracks come from the user-supplied 2.0 reference plan. They are
### Evidence Consistency
- objective: Recommended Skill OS 2.0 implementation PR from the upgrade plan.
- status: `warn`
- status: `pass`
- existing evidence: `scripts/render_evidence_consistency.py`, `reports/evidence_consistency.json`, `tests/verify_evidence_consistency.py`
- next action: Keep this item covered as the implementation evolves.
+7 -7
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-16",
"generated_at": "2026-06-16T09:19:42Z",
"skill_dir": ".",
"decision": "proposal-review",
"source_supplied": false,
@@ -11,10 +11,10 @@
"pending_review_count": 0,
"applied_count": 0,
"rollback_count": 0,
"local_blueprint_ready": false,
"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,
@@ -28,10 +28,10 @@
"pending_review_count": 0,
"applied_count": 0,
"rollback_count": 0,
"local_blueprint_ready": false,
"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,
@@ -477,10 +477,10 @@
"rollback_count": 0
},
"release_state": {
"local_blueprint_ready": false,
"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": [
+3 -3
View File
@@ -1,6 +1,6 @@
# Daily SkillOps Report
Generated at: `2026-06-16`
Generated at: `2026-06-16T09:19:42Z`
## Summary
@@ -11,10 +11,10 @@ Generated at: `2026-06-16`
- pending approvals: `0`
- applied patches: `0`
- rollbacks: `0`
- local blueprint ready: `false`
- 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.
+4 -4
View File
@@ -1,7 +1,7 @@
{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-16",
"generated_at": "2026-06-16T09:19:42Z",
"skill_dir": ".",
"decision": "curator-review",
"week_id": "2026-W25",
@@ -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
+2 -2
View File
@@ -1,6 +1,6 @@
# Weekly SkillOps Curator Report
Generated at: `2026-06-16`
Generated at: `2026-06-16T09:19:42Z`
Week: `2026-W25`
## Summary
@@ -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": "a96372e32dc1407f1bf71b63c330e9e39a40e52ee15afb7d89c1e0da470a3cd3"
"to": "5802e5f522558cf77666ae59390a28845cf3affd22fa1267b6629891ddeba76b"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "e30f37d1ae301f3d696a70e1fed375ba2e0bb2cfc26a1484c202143842817565"
"to": "a163b6e288c5342e683875b47fdfe62989d3f09241c0c8fd86ae615c6d5da7ad"
}
]
},
+141
View File
@@ -0,0 +1,141 @@
SCRIPT_INTERFACE = "internal-module"
SCRIPT_INTERFACE_REASON = "Imported by optimize_description.py to render description optimization reports."
def render_markdown(report: dict, title: str) -> str:
lines = [
f"# {title}",
"",
f"Winner: `{report['winner']['label']}`",
"",
f"- current tokens: `{report['current_candidate']['estimated_tokens']}`",
f"- winner tokens: `{report['winner']['estimated_tokens']}`",
]
if report["baseline"]:
lines.append(f"- baseline tokens: `{report['baseline']['estimated_tokens']}`")
lines.extend(
[
"",
"## Winner",
"",
report["winner"]["description"],
"",
"## Candidate Ranking",
"",
"| Candidate | Tokens | Dev FP | Dev FN | Dev Near | Holdout FP | Holdout FN |",
"| --- | ---: | ---: | ---: | ---: | ---: | ---: |",
]
)
for candidate in report["candidates"]:
holdout = candidate.get("holdout", {})
lines.append(
f"| `{candidate['label']}` | {candidate['estimated_tokens']} | {candidate['dev']['false_positives']} | {candidate['dev']['false_negatives']} | {candidate['dev']['near_neighbor_pass_rate']} | {holdout.get('false_positives', '-')} | {holdout.get('false_negatives', '-')} |"
)
lines.extend(
[
"",
"## Acceptance Gates",
"",
"| Gate | Winner FP | Winner FN | Current FP | Current FN | Baseline FP | Baseline FN |",
"| --- | ---: | ---: | ---: | ---: | ---: | ---: |",
]
)
for gate_name, gate in (
("Holdout", report["acceptance_gates"]["holdout_non_regression"]),
("Blind Holdout", report["acceptance_gates"]["blind_holdout_non_regression"]),
("Judge Blind Holdout", report["acceptance_gates"]["judge_blind_holdout_non_regression"]),
("Adversarial Holdout", report["acceptance_gates"]["adversarial_holdout_non_regression"]),
):
winner_gate = gate.get("winner") or {}
current_gate = gate.get("current") or {}
baseline_gate = gate.get("baseline") or {}
if not winner_gate and not current_gate and not baseline_gate:
continue
lines.append(
f"| {gate_name} | {winner_gate.get('false_positives', '-')} | {winner_gate.get('false_negatives', '-')} | {current_gate.get('false_positives', '-')} | {current_gate.get('false_negatives', '-')} | {baseline_gate.get('false_positives', '-')} | {baseline_gate.get('false_negatives', '-')} |"
)
lines.extend(
[
"",
"## Calibration",
"",
"| Gate | Winner Gap | Winner Risk | Winner Boundary Rate | Current Gap | Baseline Gap |",
"| --- | ---: | --- | ---: | ---: | ---: |",
]
)
for gate_name, gate in (
("Holdout", report["acceptance_gates"]["holdout_non_regression"]),
("Blind Holdout", report["acceptance_gates"]["blind_holdout_non_regression"]),
("Judge Blind Holdout", report["acceptance_gates"]["judge_blind_holdout_non_regression"]),
("Adversarial Holdout", report["acceptance_gates"]["adversarial_holdout_non_regression"]),
):
winner_calibration = gate.get("winner_calibration") or {}
current_calibration = gate.get("current_calibration") or {}
baseline_calibration = gate.get("baseline_calibration") or {}
if not winner_calibration and not current_calibration and not baseline_calibration:
continue
lines.append(
f"| {gate_name} | {winner_calibration.get('score_gap', '-')} | {winner_calibration.get('risk_band', '-')} | {winner_calibration.get('boundary_case_rate', '-')} | {current_calibration.get('score_gap', '-')} | {baseline_calibration.get('score_gap', '-')} |"
)
lines.extend(
[
"",
"## Judge Blind Summary",
"",
"| Gate | Winner Agreement | Winner Mean Confidence | Current Agreement | Baseline Agreement |",
"| --- | ---: | ---: | ---: | ---: |",
]
)
judge_gate = report["acceptance_gates"]["judge_blind_holdout_non_regression"]
judge_winner = (judge_gate.get("winner") or {}).get("judge_summary") or {}
judge_current = (judge_gate.get("current") or {}).get("judge_summary") or {}
judge_baseline = (judge_gate.get("baseline") or {}).get("judge_summary") or {}
if judge_winner or judge_current or judge_baseline:
lines.append(
f"| Judge Blind Holdout | {judge_winner.get('agreement_rate', '-')} | {judge_winner.get('mean_confidence', '-')} | {judge_current.get('agreement_rate', '-')} | {judge_baseline.get('agreement_rate', '-')} |"
)
lines.extend(
[
"",
"## Family Health",
"",
"| Gate | Winner Clean Families | Winner Weakest Family | Current Clean Families | Baseline Clean Families |",
"| --- | --- | --- | --- | --- |",
]
)
for gate_name, gate in (
("Holdout", report["acceptance_gates"]["holdout_non_regression"]),
("Blind Holdout", report["acceptance_gates"]["blind_holdout_non_regression"]),
("Judge Blind Holdout", report["acceptance_gates"]["judge_blind_holdout_non_regression"]),
("Adversarial Holdout", report["acceptance_gates"]["adversarial_holdout_non_regression"]),
):
winner_health = gate.get("winner_family_health") or {}
current_health = gate.get("current_family_health") or {}
baseline_health = gate.get("baseline_family_health") or {}
if not winner_health and not current_health and not baseline_health:
continue
weakest = winner_health.get("weakest_family") or {}
weakest_label = (
f"{weakest.get('family')} ({weakest.get('errors')} errors)"
if weakest.get("family")
else "-"
)
lines.append(
f"| {gate_name} | {winner_health.get('clean_family_count', '-')}/{winner_health.get('family_count', '-')} | {weakest_label} | {current_health.get('clean_family_count', '-')}/{current_health.get('family_count', '-')} | {baseline_health.get('clean_family_count', '-')}/{baseline_health.get('family_count', '-')} |"
)
lines.extend(
[
"",
"## Selection Logic",
"",
"Ordered by:",
]
)
for item in report["selection_logic"]["priority"]:
lines.append(f"- {item}")
return "\n".join(lines) + "\n"
+1 -139
View File
@@ -4,6 +4,7 @@ import json
from pathlib import Path
from context_sizer import estimate_tokens
from description_optimizer_reporting import render_markdown
from judge_blind_eval import evaluate_judge
from trigger_eval import (
compare_reports,
@@ -539,145 +540,6 @@ def optimize(
return report
def render_markdown(report: dict, title: str) -> str:
lines = [
f"# {title}",
"",
f"Winner: `{report['winner']['label']}`",
"",
f"- current tokens: `{report['current_candidate']['estimated_tokens']}`",
f"- winner tokens: `{report['winner']['estimated_tokens']}`",
]
if report["baseline"]:
lines.append(f"- baseline tokens: `{report['baseline']['estimated_tokens']}`")
lines.extend(
[
"",
"## Winner",
"",
report["winner"]["description"],
"",
"## Candidate Ranking",
"",
"| Candidate | Tokens | Dev FP | Dev FN | Dev Near | Holdout FP | Holdout FN |",
"| --- | ---: | ---: | ---: | ---: | ---: | ---: |",
]
)
for candidate in report["candidates"]:
holdout = candidate.get("holdout", {})
lines.append(
f"| `{candidate['label']}` | {candidate['estimated_tokens']} | {candidate['dev']['false_positives']} | {candidate['dev']['false_negatives']} | {candidate['dev']['near_neighbor_pass_rate']} | {holdout.get('false_positives', '-')} | {holdout.get('false_negatives', '-')} |"
)
lines.extend(
[
"",
"## Acceptance Gates",
"",
"| Gate | Winner FP | Winner FN | Current FP | Current FN | Baseline FP | Baseline FN |",
"| --- | ---: | ---: | ---: | ---: | ---: | ---: |",
]
)
for gate_name, gate in (
("Holdout", report["acceptance_gates"]["holdout_non_regression"]),
("Blind Holdout", report["acceptance_gates"]["blind_holdout_non_regression"]),
("Judge Blind Holdout", report["acceptance_gates"]["judge_blind_holdout_non_regression"]),
("Adversarial Holdout", report["acceptance_gates"]["adversarial_holdout_non_regression"]),
):
winner_gate = gate.get("winner") or {}
current_gate = gate.get("current") or {}
baseline_gate = gate.get("baseline") or {}
if not winner_gate and not current_gate and not baseline_gate:
continue
lines.append(
f"| {gate_name} | {winner_gate.get('false_positives', '-')} | {winner_gate.get('false_negatives', '-')} | {current_gate.get('false_positives', '-')} | {current_gate.get('false_negatives', '-')} | {baseline_gate.get('false_positives', '-')} | {baseline_gate.get('false_negatives', '-')} |"
)
lines.extend(
[
"",
"## Calibration",
"",
"| Gate | Winner Gap | Winner Risk | Winner Boundary Rate | Current Gap | Baseline Gap |",
"| --- | ---: | --- | ---: | ---: | ---: |",
]
)
for gate_name, gate in (
("Holdout", report["acceptance_gates"]["holdout_non_regression"]),
("Blind Holdout", report["acceptance_gates"]["blind_holdout_non_regression"]),
("Judge Blind Holdout", report["acceptance_gates"]["judge_blind_holdout_non_regression"]),
("Adversarial Holdout", report["acceptance_gates"]["adversarial_holdout_non_regression"]),
):
winner_calibration = gate.get("winner_calibration") or {}
current_calibration = gate.get("current_calibration") or {}
baseline_calibration = gate.get("baseline_calibration") or {}
if not winner_calibration and not current_calibration and not baseline_calibration:
continue
lines.append(
f"| {gate_name} | {winner_calibration.get('score_gap', '-')} | {winner_calibration.get('risk_band', '-')} | {winner_calibration.get('boundary_case_rate', '-')} | {current_calibration.get('score_gap', '-')} | {baseline_calibration.get('score_gap', '-')} |"
)
lines.extend(
[
"",
"## Judge Blind Summary",
"",
"| Gate | Winner Agreement | Winner Mean Confidence | Current Agreement | Baseline Agreement |",
"| --- | ---: | ---: | ---: | ---: |",
]
)
judge_gate = report["acceptance_gates"]["judge_blind_holdout_non_regression"]
judge_winner = (judge_gate.get("winner") or {}).get("judge_summary") or {}
judge_current = (judge_gate.get("current") or {}).get("judge_summary") or {}
judge_baseline = (judge_gate.get("baseline") or {}).get("judge_summary") or {}
if judge_winner or judge_current or judge_baseline:
lines.append(
f"| Judge Blind Holdout | {judge_winner.get('agreement_rate', '-')} | {judge_winner.get('mean_confidence', '-')} | {judge_current.get('agreement_rate', '-')} | {judge_baseline.get('agreement_rate', '-')} |"
)
lines.extend(
[
"",
"## Family Health",
"",
"| Gate | Winner Clean Families | Winner Weakest Family | Current Clean Families | Baseline Clean Families |",
"| --- | --- | --- | --- | --- |",
]
)
for gate_name, gate in (
("Holdout", report["acceptance_gates"]["holdout_non_regression"]),
("Blind Holdout", report["acceptance_gates"]["blind_holdout_non_regression"]),
("Judge Blind Holdout", report["acceptance_gates"]["judge_blind_holdout_non_regression"]),
("Adversarial Holdout", report["acceptance_gates"]["adversarial_holdout_non_regression"]),
):
winner_health = gate.get("winner_family_health") or {}
current_health = gate.get("current_family_health") or {}
baseline_health = gate.get("baseline_family_health") or {}
if not winner_health and not current_health and not baseline_health:
continue
weakest = winner_health.get("weakest_family") or {}
weakest_label = (
f"{weakest.get('family')} ({weakest.get('errors')} errors)"
if weakest.get("family")
else "-"
)
lines.append(
f"| {gate_name} | {winner_health.get('clean_family_count', '-')}/{winner_health.get('family_count', '-')} | {weakest_label} | {current_health.get('clean_family_count', '-')}/{current_health.get('family_count', '-')} | {baseline_health.get('clean_family_count', '-')}/{baseline_health.get('family_count', '-')} |"
)
lines.extend(
[
"",
"## Selection Logic",
"",
"Ordered by:",
]
)
for item in report["selection_logic"]["priority"]:
lines.append(f"- {item}")
return "\n".join(lines) + "\n"
def main() -> None:
parser = argparse.ArgumentParser(
description="Generate and score description candidates on dev, holdout, blind, and adversarial suites."
+1
View File
@@ -33,6 +33,7 @@
"scripts/context_sizer.py",
"scripts/create_iteration_snapshot.py",
"scripts/cross_packager.py",
"scripts/description_optimizer_reporting.py",
"scripts/diff_eval.py",
"scripts/emit_telemetry_event.py",
"scripts/evidence_consistency_artifact_roles.py",
+2
View File
@@ -97,6 +97,7 @@ def main() -> None:
for internal_module in [
"scripts/build_skill_atlas_layout.py",
"scripts/compile_skill_targets.py",
"scripts/description_optimizer_reporting.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_gates.py",
"scripts/review_studio_layout.py",
@@ -130,6 +131,7 @@ def main() -> None:
warning_text = "\n".join(payload["warnings"])
assert "build_skill_atlas_layout.py" not in warning_text, payload["warnings"]
assert "compile_skill_targets.py" not in warning_text, payload["warnings"]
assert "description_optimizer_reporting.py" not in warning_text, payload["warnings"]
assert "review_studio_formatting.py" not in warning_text, payload["warnings"]
assert "review_studio_gates.py" not in warning_text, payload["warnings"]
assert "review_studio_layout.py" not in warning_text, payload["warnings"]