frostbyte_neo/yao-meta-skill
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity

refactor: split review studio data helpers

Browse Source
This commit is contained in:
yaojingang
2026-06-14 02:18:09 +08:00
parent d7018dac55
commit 479b098ccf
39 changed files with 700 additions and 596 deletions
Download Patch File Download Diff File Expand all files Collapse all files
registry/index.json
+1 -1
View File
@@ -16,7 +16,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e"
"package_sha256": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49"
}
]
}
registry/packages/yao-meta-skill.json
+3 -3
View File
@@ -16,8 +16,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e",
"archive_sha256": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25"
"package_sha256": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49",
"archive_sha256": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0"
},
"compatibility": {
"openai": "pass",
@@ -48,7 +48,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25",
"archive_sha256": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
reports/adoption_drift_report.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-13T18:04:28Z",
"generated_at": "2026-06-13T18:17:38Z",
"skill_dir": ".",
"privacy_contract": {
"storage": "local-first",
reports/architecture_maintainability.json
+12 -24
View File
@@ -4,27 +4,20 @@
"generated_at": "2026-06-14",
"skill_dir": ".",
"summary": {
"python_file_count": 141,
"script_file_count": 85,
"python_file_count": 143,
"script_file_count": 87,
"test_file_count": 56,
"internal_module_count": 14,
"internal_module_count": 16,
"cli_script_count": 72,
"command_handler_count": 35,
"warn_line_threshold": 900,
"block_line_threshold": 1500,
"largest_file_lines": 1196,
"hotspot_count": 3,
"largest_file_lines": 1159,
"hotspot_count": 2,
"blocker_count": 0,
"decision": "watch-maintainability-hotspots"
},
"largest_files": [
{
"path": "scripts/render_review_studio.py",
"lines": 1196,
"kind": "cli-script",
"severity": "warn",
"recommendation": "Move data loading and large section renderers into focused review_studio_* modules."
},
{
"path": "scripts/yao.py",
"lines": 1159,
@@ -39,6 +32,13 @@
"severity": "warn",
"recommendation": "Split viewer data assembly from HTML section rendering."
},
{
"path": "scripts/render_review_studio.py",
"lines": 887,
"kind": "cli-script",
"severity": "pass",
"recommendation": "Move data loading and large section renderers into focused review_studio_* modules."
},
{
"path": "tests/verify_yao_cli.py",
"lines": 838,
@@ -104,13 +104,6 @@
}
],
"hotspots": [
{
"path": "scripts/render_review_studio.py",
"lines": 1196,
"kind": "cli-script",
"severity": "warn",
"recommendation": "Move data loading and large section renderers into focused review_studio_* modules."
},
{
"path": "scripts/yao.py",
"lines": 1159,
@@ -127,11 +120,6 @@
}
],
"actions": [
{
"path": "scripts/render_review_studio.py",
"severity": "warn",
"action": "Move data loading and large section renderers into focused review_studio_* modules."
},
{
"path": "scripts/yao.py",
"severity": "warn",
reports/architecture_maintainability.md
+6 -7
View File
@@ -5,14 +5,14 @@ Generated at: `2026-06-14`
## Summary
- decision: `watch-maintainability-hotspots`
- python files: `141`
- scripts: `85`
- python files: `143`
- scripts: `87`
- tests: `56`
- internal modules: `14`
- internal modules: `16`
- CLI scripts: `72`
- Yao CLI command handlers: `35`
- largest file lines: `1196`
- hotspots: `3`
- largest file lines: `1159`
- hotspots: `2`
- blockers: `0`
This report keeps maintainability risk visible before the Meta Skill grows more gates, renderers, and CLI commands.
@@ -21,7 +21,6 @@ This report keeps maintainability risk visible before the Meta Skill grows more
| File | Lines | Kind | Severity | Recommended action |
| --- | ---: | --- | --- | --- |
| `scripts/render_review_studio.py` | `1196` | `cli-script` | `warn` | Move data loading and large section renderers into focused review_studio_* modules. |
| `scripts/yao.py` | `1159` | `cli-script` | `warn` | Split command handlers by domain while keeping scripts/yao.py as the thin CLI orchestrator. |
| `scripts/render_review_viewer.py` | `983` | `cli-script` | `warn` | Split viewer data assembly from HTML section rendering. |
@@ -29,9 +28,9 @@ This report keeps maintainability risk visible before the Meta Skill grows more
| File | Lines | Kind | Severity |
| --- | ---: | --- | --- |
| `scripts/render_review_studio.py` | `1196` | `cli-script` | `warn` |
| `scripts/yao.py` | `1159` | `cli-script` | `warn` |
| `scripts/render_review_viewer.py` | `983` | `cli-script` | `warn` |
| `scripts/render_review_studio.py` | `887` | `cli-script` | `pass` |
| `tests/verify_yao_cli.py` | `838` | `test` | `pass` |
| `scripts/skill_report_model.py` | `782` | `internal-module` | `pass` |
| `scripts/compile_skill.py` | `734` | `cli-script` | `pass` |
reports/benchmark_reproducibility.json
+24 -24
View File
@@ -3,24 +3,24 @@
"ok": true,
"generated_at": "2026-06-14",
"skill_dir": ".",
"commit": "7afde5ebafd5b8cb0b00aaaac4943c037fc9dce4",
"commit": "d7018dac5583d8973d8544d5f02906e94e8b1f9b",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 36,
"changed_file_count": 39,
"sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" 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/compiled_targets.json",
" M reports/context_budget.json",
" M reports/install_simulation.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md"
"MM registry/index.json",
"MM registry/packages/yao-meta-skill.json",
"MM reports/adoption_drift_report.json",
"M reports/architecture_maintainability.json",
"M reports/architecture_maintainability.md",
"MM reports/benchmark_reproducibility.json",
"MM reports/benchmark_reproducibility.md",
"M reports/compiled_targets.json",
"MM reports/context_budget.json",
"M reports/install_simulation.json",
"MM reports/output_execution_runs.json",
"MM reports/output_execution_runs.md"
]
},
"summary": {
@@ -42,7 +42,7 @@
"world_class_task_count": 4,
"world_class_ledger_pending_count": 4,
"working_tree_dirty": true,
"changed_file_count": 36
"changed_file_count": 39
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -116,7 +116,7 @@
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7966,
"sha256": "ef773cdb0b4b3e6263b58aa52c8473ee5b5613297bae721ea34da2418f4f6c9b"
"sha256": "e1497671aeac5efe481d21880306d1cd156520f3c6981335a23bea04c4d11e5e"
},
{
"label": "blind_review",
@@ -150,43 +150,43 @@
"label": "trust_report",
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 89598,
"sha256": "043f8314a8c2c8ef992d486384cd22dba5a0284af491fd830ddc91fec54f666a"
"bytes": 90767,
"sha256": "6a3b7738607ffef7d039e1ff913593ec9d5cd0242fc74d430c53bb62dc33df8a"
},
{
"label": "python_compatibility",
"path": "reports/python_compatibility.json",
"exists": true,
"bytes": 18801,
"sha256": "3f071172d13c70acd0b16fe84ae011fee39030da61dd5801009fadead64f2a60"
"bytes": 19050,
"sha256": "648f17271e22805669eebc88486f47e891faa9b1fa9f2bf8cf21b14d00f9e1aa"
},
{
"label": "registry_audit",
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "a55d0fb1c7d6730d1b8009904b59a18eb61a776368a211385b4a5d21b915edf1"
"sha256": "e350e7b2d3d6a971b506c9d2d159059b19e692e0957498a502fe797057ebdb85"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19325,
"sha256": "ff899ad76a6ad8e39a5f15e483135b4a93602ff59984a61f0c807ad627749dad"
"sha256": "144cd592106a66b50e8464b96494f6ed0ad41dba11941a3d7de11765b818a800"
},
{
"label": "install_simulation",
"path": "reports/install_simulation.json",
"exists": true,
"bytes": 8557,
"sha256": "20d6fa71cc492c837a98d383686677c7c2e9cc5885514ab56d5b23819060b746"
"sha256": "097060e129d0d699a2e19c5802b03b14b28134983a87f7d78cc1d525e7e5c683"
},
{
"label": "skill_os2_audit",
"path": "reports/skill_os2_audit.json",
"exists": true,
"bytes": 13946,
"sha256": "48f2206d4eb7598009740e9d4ab9e1f08b9d039cf661bb39ffbc24b2beb2c099"
"sha256": "52aff10d9877c50343b2caca9f2e3f6a721045662b6862551e22f5fe0555d878"
},
{
"label": "world_class_evidence_plan",
reports/benchmark_reproducibility.md
+9 -9
View File
@@ -1,7 +1,7 @@
# Benchmark Reproducibility
Generated at: `2026-06-14`
Commit: `7afde5ebafd5b8cb0b00aaaac4943c037fc9dce4`
Commit: `d7018dac5583d8973d8544d5f02906e94e8b1f9b`
Working tree dirty at generation: `true`
## Summary
@@ -16,7 +16,7 @@ Working tree dirty at generation: `true`
- provider evidence complete: `false`
- human review complete: `false`
- world-class ready: `false`
- changed files at generation: `36`
- changed files at generation: `39`
This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete.
@@ -40,17 +40,17 @@ 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 | `ef773cdb0b4b` |
| output_execution | `reports/output_execution_runs.json` | present | `e1497671aeac` |
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
| review_adjudication | `reports/output_review_adjudication.json` | present | `ddd9af90d42e` |
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
| runtime_conformance | `reports/conformance_matrix.json` | present | `8251329e663d` |
| trust_report | `reports/security_trust_report.json` | present | `043f8314a8c2` |
| python_compatibility | `reports/python_compatibility.json` | present | `3f071172d13c` |
| registry_audit | `reports/registry_audit.json` | present | `a55d0fb1c7d6` |
| package_verification | `reports/package_verification.json` | present | `ff899ad76a6a` |
| install_simulation | `reports/install_simulation.json` | present | `20d6fa71cc49` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `48f2206d4eb7` |
| trust_report | `reports/security_trust_report.json` | present | `6a3b7738607f` |
| python_compatibility | `reports/python_compatibility.json` | present | `648f17271e22` |
| registry_audit | `reports/registry_audit.json` | present | `e350e7b2d3d6` |
| package_verification | `reports/package_verification.json` | present | `144cd592106a` |
| install_simulation | `reports/install_simulation.json` | present | `097060e129d0` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `52aff10d9877` |
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `ed1274b7c18c` |
| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `5ed043491c3d` |
| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `124b9239d7f3` |
reports/compiled_targets.json
+15 -15
View File
@@ -204,9 +204,11 @@
"scripts/render_world_class_evidence_ledger.py",
"scripts/render_world_class_evidence_plan.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_data.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_gates.py",
"scripts/review_studio_layout.py",
"scripts/review_studio_world_class.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -222,9 +224,7 @@
"scripts/trigger_eval.py",
"scripts/trust_check.py",
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/validate_skill.py"
],
"assets": [
"templates/basic_skill.md.j2",
@@ -1045,9 +1045,11 @@
"scripts/render_world_class_evidence_ledger.py",
"scripts/render_world_class_evidence_plan.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_data.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_gates.py",
"scripts/review_studio_layout.py",
"scripts/review_studio_world_class.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -1063,9 +1065,7 @@
"scripts/trigger_eval.py",
"scripts/trust_check.py",
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/validate_skill.py"
],
"assets": [
"templates/basic_skill.md.j2",
@@ -1886,9 +1886,11 @@
"scripts/render_world_class_evidence_ledger.py",
"scripts/render_world_class_evidence_plan.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_data.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_gates.py",
"scripts/review_studio_layout.py",
"scripts/review_studio_world_class.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -1904,9 +1906,7 @@
"scripts/trigger_eval.py",
"scripts/trust_check.py",
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/validate_skill.py"
],
"assets": [
"templates/basic_skill.md.j2",
@@ -2711,9 +2711,11 @@
"scripts/render_world_class_evidence_ledger.py",
"scripts/render_world_class_evidence_plan.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_data.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_gates.py",
"scripts/review_studio_layout.py",
"scripts/review_studio_world_class.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -2729,9 +2731,7 @@
"scripts/trigger_eval.py",
"scripts/trust_check.py",
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/validate_skill.py"
],
"assets": [
"templates/basic_skill.md.j2",
@@ -3536,9 +3536,11 @@
"scripts/render_world_class_evidence_ledger.py",
"scripts/render_world_class_evidence_plan.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_data.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_gates.py",
"scripts/review_studio_layout.py",
"scripts/review_studio_world_class.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -3554,9 +3556,7 @@
"scripts/trigger_eval.py",
"scripts/trust_check.py",
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/validate_skill.py"
],
"assets": [
"templates/basic_skill.md.j2",
reports/context_budget.json
+3 -3
View File
@@ -6,10 +6,10 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 751,
"other_text_tokens": 1083497,
"other_text_tokens": 1084439,
"estimated_initial_load_tokens": 944,
"estimated_total_text_tokens": 1084248,
"relevant_file_count": 469,
"estimated_total_text_tokens": 1085190,
"relevant_file_count": 473,
"unused_resource_dirs": [],
"quality_signal_points": 130,
"quality_density": 137.7
reports/install_simulation.json
+1 -1
View File
@@ -8,7 +8,7 @@
"installed_skill_dir": "[temporary-install-root]/yao-meta-skill",
"summary": {
"archive_present": true,
"archive_entry_count": 553,
"archive_entry_count": 555,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
reports/output_execution_runs.json
+8 -8
View File
@@ -34,7 +34,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.82,
"duration_ms": 27.82,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -62,7 +62,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.73,
"duration_ms": 26.16,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -85,7 +85,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.52,
"duration_ms": 27.01,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -136,7 +136,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.92,
"duration_ms": 25.7,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -164,7 +164,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.58,
"duration_ms": 25.64,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -187,7 +187,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.69,
"duration_ms": 25.83,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -214,7 +214,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.4,
"duration_ms": 26.02,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -237,7 +237,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.48,
"duration_ms": 25.66,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
reports/output_execution_runs.md
+8 -8
View File
@@ -23,15 +23,15 @@ 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 | 25.82 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 25.73 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 25.52 | 36 | 0.0 | pass |
| skill-package-contract | baseline | command | local-output-eval-runner | 27.82 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 26.16 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 27.01 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 25.68 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 25.92 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 25.58 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 25.69 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 25.4 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 25.48 | 37 | 0.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 25.7 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 25.64 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 25.83 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.02 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 25.66 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 25.68 | 98 | 100.0 | pass |
## Next Fixes
reports/package_verification.json
+2 -2
View File
@@ -8,8 +8,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25",
"archive_entry_count": 553,
"archive_sha256": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0",
"archive_entry_count": 555,
"failure_count": 0,
"warning_count": 0
},
reports/package_verification.md
+1 -1
View File
@@ -4,7 +4,7 @@
- Package directory: `dist`
- Targets: `4 / 4` adapters present
- Archive present: `True`
- Archive SHA256: `26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25`
- Archive SHA256: `7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0`
- Failures: `0`
- Warnings: `0`
reports/python_compatibility.json
+13 -1
View File
@@ -5,7 +5,7 @@
"root": ".",
"summary": {
"target_python": "3.11",
"file_count": 144,
"file_count": 146,
"issue_count": 0,
"syntax_error_count": 0,
"fstring_311_violation_count": 0,
@@ -394,6 +394,12 @@
"issue_count": 0,
"issues": []
},
{
"path": "scripts/review_studio_data.py",
"ok": true,
"issue_count": 0,
"issues": []
},
{
"path": "scripts/review_studio_formatting.py",
"ok": true,
@@ -412,6 +418,12 @@
"issue_count": 0,
"issues": []
},
{
"path": "scripts/review_studio_world_class.py",
"ok": true,
"issue_count": 0,
"issues": []
},
{
"path": "scripts/run_conformance_suite.py",
"ok": true,
reports/python_compatibility.md
+1 -1
View File
@@ -6,7 +6,7 @@ Generated at: `2026-06-14`
- decision: `pass`
- target python: `3.11`
- files scanned: `144`
- files scanned: `146`
- issues: `0`
- syntax errors: `0`
- f-string 3.11 violations: `0`
reports/registry_audit.json
+4 -4
View File
@@ -21,8 +21,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e",
"archive_sha256": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25"
"package_sha256": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49",
"archive_sha256": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0"
},
"compatibility": {
"openai": "pass",
@@ -53,7 +53,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25",
"archive_sha256": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0",
"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": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e"
"package_sha256": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49"
}
]
},
reports/registry_audit.md
+2 -2
View File
@@ -6,8 +6,8 @@
- Maturity: `governed`
- Owner: `Yao Team`
- License: `MIT`
- Package SHA256: `18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e`
- Archive SHA256: `26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25`
- Package SHA256: `1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49`
- Archive SHA256: `7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0`
- Install simulated: `True`
## Compatibility
reports/review-studio.html
+8 -8
View File
File diff suppressed because one or more lines are too long
reports/review-studio.json
+131 -93
View File
@@ -59,7 +59,7 @@
"key": "trust-report",
"label": "信任报告",
"status": "pass",
"detail": "0 secrets; 85 scripts; 3 network-capable scripts; 0 help smoke failures",
"detail": "0 secrets; 87 scripts; 3 network-capable scripts; 0 help smoke failures",
"evidence": "reports/security_trust_report.json",
"link": "security_trust_report.md"
},
@@ -67,7 +67,7 @@
"key": "python-compat",
"label": "Python 兼容",
"status": "pass",
"detail": "Python 3.11; 144 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards",
"detail": "Python 3.11; 146 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards",
"evidence": "reports/python_compatibility.json",
"link": "python_compatibility.md"
},
@@ -75,7 +75,7 @@
"key": "architecture-maintainability",
"label": "架构维护",
"status": "warn",
"detail": "141 Python files; 3 hotspots; 0 blockers; largest 1196 lines; 35 CLI handlers",
"detail": "143 Python files; 2 hotspots; 0 blockers; largest 1159 lines; 35 CLI handlers",
"evidence": "reports/architecture_maintainability.json",
"link": "architecture_maintainability.md"
},
@@ -158,7 +158,7 @@
"key": "architecture-maintainability",
"label": "架构维护",
"status": "warn",
"detail": "141 Python files; 3 hotspots; 0 blockers; largest 1196 lines; 35 CLI handlers",
"detail": "143 Python files; 2 hotspots; 0 blockers; largest 1159 lines; 35 CLI handlers",
"evidence": "reports/architecture_maintainability.json",
"link": "architecture_maintainability.md"
},
@@ -271,7 +271,7 @@
"path": "scripts/render_review_studio.py",
"label": "Review Studio renderer",
"kind": "source",
"line": 387,
"line": 121,
"exists": true,
"link": "../scripts/render_review_studio.py"
},
@@ -891,7 +891,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 85
"file_count": 87
},
{
"path": "evals",
@@ -906,7 +906,7 @@
"file_count": 195
}
],
"file_count": 344,
"file_count": 346,
"folder_count": 4,
"distribution": [
{
@@ -931,7 +931,7 @@
},
{
"label": "scripts",
"value": 85
"value": 87
},
{
"label": "evals",
@@ -1060,7 +1060,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 85
"file_count": 87
},
{
"path": "evals",
@@ -1360,9 +1360,9 @@
"world_class_task_count": 4,
"world_class_ledger_pending_count": 4,
"working_tree_dirty": true,
"changed_file_count": 36
"changed_file_count": 39
},
"commit": "7afde5ebafd5b8cb0b00aaaac4943c037fc9dce4",
"commit": "d7018dac5583d8973d8544d5f02906e94e8b1f9b",
"missing_artifacts": [],
"limitations": [
"Local command-runner evidence is reproducible but does not replace provider-backed model holdout evidence.",
@@ -1437,9 +1437,9 @@
"failures": []
},
"trust_security": {
"scanned_files": 169,
"script_count": 85,
"internal_module_count": 12,
"scanned_files": 171,
"script_count": 87,
"internal_module_count": 14,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -1457,8 +1457,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 169,
"package_sha256": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e"
"package_hash_file_count": 171,
"package_sha256": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49"
},
"skill_atlas": {
"skill_count": 12,
@@ -1496,8 +1496,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e",
"archive_sha256": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25"
"package_sha256": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49",
"archive_sha256": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0"
},
"compatibility": {
"openai": "pass",
@@ -1528,7 +1528,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25",
"archive_sha256": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1544,8 +1544,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25",
"archive_entry_count": 553,
"archive_sha256": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0",
"archive_entry_count": 555,
"failure_count": 0,
"warning_count": 0
},
@@ -1556,7 +1556,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 553,
"archive_entry_count": 555,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1623,12 +1623,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25"
"to": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e"
"to": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49"
}
]
},
@@ -3745,7 +3745,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.82,
"duration_ms": 27.82,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3773,7 +3773,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.73,
"duration_ms": 26.16,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3796,7 +3796,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.52,
"duration_ms": 27.01,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3847,7 +3847,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.92,
"duration_ms": 25.7,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3875,7 +3875,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.58,
"duration_ms": 25.64,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3898,7 +3898,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.69,
"duration_ms": 25.83,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3925,7 +3925,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.4,
"duration_ms": 26.02,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3948,7 +3948,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.48,
"duration_ms": 25.66,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4408,7 +4408,7 @@
"label": "Trust Security",
"status": "pass",
"objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
"current": "85 scripts; secrets 0; help failures 0",
"current": "87 scripts; secrets 0; help failures 0",
"command": "python3 scripts/yao.py trust .",
"test": "python3 tests/verify_trust_check.py",
"evidence": [
@@ -4482,7 +4482,7 @@
"label": "Registry Distribution",
"status": "pass",
"objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
"current": "archive entries 553; install failures 0",
"current": "archive entries 555; 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": [
@@ -5106,9 +5106,11 @@
"scripts/render_world_class_evidence_ledger.py",
"scripts/render_world_class_evidence_plan.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_data.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_gates.py",
"scripts/review_studio_layout.py",
"scripts/review_studio_world_class.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -5124,9 +5126,7 @@
"scripts/trigger_eval.py",
"scripts/trust_check.py",
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/validate_skill.py"
],
"assets": [
"templates/basic_skill.md.j2",
@@ -5947,9 +5947,11 @@
"scripts/render_world_class_evidence_ledger.py",
"scripts/render_world_class_evidence_plan.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_data.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_gates.py",
"scripts/review_studio_layout.py",
"scripts/review_studio_world_class.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -5965,9 +5967,7 @@
"scripts/trigger_eval.py",
"scripts/trust_check.py",
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/validate_skill.py"
],
"assets": [
"templates/basic_skill.md.j2",
@@ -6788,9 +6788,11 @@
"scripts/render_world_class_evidence_ledger.py",
"scripts/render_world_class_evidence_plan.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_data.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_gates.py",
"scripts/review_studio_layout.py",
"scripts/review_studio_world_class.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -6806,9 +6808,7 @@
"scripts/trigger_eval.py",
"scripts/trust_check.py",
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/validate_skill.py"
],
"assets": [
"templates/basic_skill.md.j2",
@@ -7613,9 +7613,11 @@
"scripts/render_world_class_evidence_ledger.py",
"scripts/render_world_class_evidence_plan.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_data.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_gates.py",
"scripts/review_studio_layout.py",
"scripts/review_studio_world_class.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -7631,9 +7633,7 @@
"scripts/trigger_eval.py",
"scripts/trust_check.py",
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/validate_skill.py"
],
"assets": [
"templates/basic_skill.md.j2",
@@ -8438,9 +8438,11 @@
"scripts/render_world_class_evidence_ledger.py",
"scripts/render_world_class_evidence_plan.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_data.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_gates.py",
"scripts/review_studio_layout.py",
"scripts/review_studio_world_class.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -8456,9 +8458,7 @@
"scripts/trigger_eval.py",
"scripts/trust_check.py",
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/validate_skill.py"
],
"assets": [
"templates/basic_skill.md.j2",
@@ -9655,9 +9655,9 @@
"ok": true,
"skill_dir": ".",
"summary": {
"scanned_files": 169,
"script_count": 85,
"internal_module_count": 12,
"scanned_files": 171,
"script_count": 87,
"internal_module_count": 14,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -9675,8 +9675,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 169,
"package_sha256": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e"
"package_hash_file_count": 171,
"package_sha256": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49"
},
"failures": [],
"warnings": [],
@@ -10525,6 +10525,20 @@
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/review_studio_data.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by render_review_studio.py to load Review Studio source reports and metric cards.",
"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/review_studio_formatting.py",
"interface": "internal-module",
@@ -10567,6 +10581,20 @@
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/review_studio_world_class.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by render_review_studio.py to render world-class evidence cards.",
"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/run_conformance_suite.py",
"interface": "cli",
@@ -10924,7 +10952,7 @@
"checked_count": 73,
"passed_count": 73,
"failed_count": 0,
"skipped_count": 12,
"skipped_count": 14,
"failed_scripts": [],
"results": [
{
@@ -11659,6 +11687,10 @@
}
],
"skipped": [
{
"path": "scripts/review_studio_data.py",
"reason": "internal module"
},
{
"path": "scripts/review_studio_formatting.py",
"reason": "internal module"
@@ -11671,6 +11703,10 @@
"path": "scripts/review_studio_layout.py",
"reason": "internal module"
},
{
"path": "scripts/review_studio_world_class.py",
"reason": "internal module"
},
{
"path": "scripts/skill_report_charts.py",
"reason": "internal module"
@@ -11888,7 +11924,7 @@
"root": ".",
"summary": {
"target_python": "3.11",
"file_count": 144,
"file_count": 146,
"issue_count": 0,
"syntax_error_count": 0,
"fstring_311_violation_count": 0,
@@ -12277,6 +12313,12 @@
"issue_count": 0,
"issues": []
},
{
"path": "scripts/review_studio_data.py",
"ok": true,
"issue_count": 0,
"issues": []
},
{
"path": "scripts/review_studio_formatting.py",
"ok": true,
@@ -12295,6 +12337,12 @@
"issue_count": 0,
"issues": []
},
{
"path": "scripts/review_studio_world_class.py",
"ok": true,
"issue_count": 0,
"issues": []
},
{
"path": "scripts/run_conformance_suite.py",
"ok": true,
@@ -12782,27 +12830,20 @@
"generated_at": "2026-06-14",
"skill_dir": ".",
"summary": {
"python_file_count": 141,
"script_file_count": 85,
"python_file_count": 143,
"script_file_count": 87,
"test_file_count": 56,
"internal_module_count": 14,
"internal_module_count": 16,
"cli_script_count": 72,
"command_handler_count": 35,
"warn_line_threshold": 900,
"block_line_threshold": 1500,
"largest_file_lines": 1196,
"hotspot_count": 3,
"largest_file_lines": 1159,
"hotspot_count": 2,
"blocker_count": 0,
"decision": "watch-maintainability-hotspots"
},
"largest_files": [
{
"path": "scripts/render_review_studio.py",
"lines": 1196,
"kind": "cli-script",
"severity": "warn",
"recommendation": "Move data loading and large section renderers into focused review_studio_* modules."
},
{
"path": "scripts/yao.py",
"lines": 1159,
@@ -12817,6 +12858,13 @@
"severity": "warn",
"recommendation": "Split viewer data assembly from HTML section rendering."
},
{
"path": "scripts/render_review_studio.py",
"lines": 887,
"kind": "cli-script",
"severity": "pass",
"recommendation": "Move data loading and large section renderers into focused review_studio_* modules."
},
{
"path": "tests/verify_yao_cli.py",
"lines": 838,
@@ -12882,13 +12930,6 @@
}
],
"hotspots": [
{
"path": "scripts/render_review_studio.py",
"lines": 1196,
"kind": "cli-script",
"severity": "warn",
"recommendation": "Move data loading and large section renderers into focused review_studio_* modules."
},
{
"path": "scripts/yao.py",
"lines": 1159,
@@ -12905,11 +12946,6 @@
}
],
"actions": [
{
"path": "scripts/render_review_studio.py",
"severity": "warn",
"action": "Move data loading and large section renderers into focused review_studio_* modules."
},
{
"path": "scripts/yao.py",
"severity": "warn",
@@ -12934,10 +12970,10 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 751,
"other_text_tokens": 1083497,
"other_text_tokens": 1084439,
"estimated_initial_load_tokens": 944,
"estimated_total_text_tokens": 1084248,
"relevant_file_count": 469,
"estimated_total_text_tokens": 1085190,
"relevant_file_count": 473,
"unused_resource_dirs": [],
"quality_signal_points": 130,
"quality_density": 137.7
@@ -13860,9 +13896,11 @@
"scripts/render_world_class_evidence_ledger.py",
"scripts/render_world_class_evidence_plan.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_data.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_gates.py",
"scripts/review_studio_layout.py",
"scripts/review_studio_world_class.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -14781,7 +14819,7 @@
"adoption_drift": {
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-13T18:04:28Z",
"generated_at": "2026-06-13T18:17:38Z",
"skill_dir": ".",
"privacy_contract": {
"storage": "local-first",
@@ -15555,8 +15593,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e",
"archive_sha256": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25"
"package_sha256": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49",
"archive_sha256": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0"
},
"compatibility": {
"openai": "pass",
@@ -15587,7 +15625,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25",
"archive_sha256": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -15612,7 +15650,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e"
"package_sha256": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49"
}
]
},
@@ -15635,8 +15673,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25",
"archive_entry_count": 553,
"archive_sha256": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0",
"archive_entry_count": 555,
"failure_count": 0,
"warning_count": 0
},
@@ -16301,7 +16339,7 @@
"installed_skill_dir": "[temporary-install-root]/yao-meta-skill",
"summary": {
"archive_present": true,
"archive_entry_count": 553,
"archive_entry_count": 555,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -16643,12 +16681,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25"
"to": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e"
"to": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49"
}
]
},
reports/review-viewer.json
+19 -19
View File
@@ -437,7 +437,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 85
"file_count": 87
},
{
"path": "evals",
@@ -452,7 +452,7 @@
"file_count": 195
}
],
"file_count": 344,
"file_count": 346,
"folder_count": 4,
"distribution": [
{
@@ -477,7 +477,7 @@
},
{
"label": "scripts",
"value": 85
"value": 87
},
{
"label": "evals",
@@ -606,7 +606,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 85
"file_count": 87
},
{
"path": "evals",
@@ -906,9 +906,9 @@
"world_class_task_count": 4,
"world_class_ledger_pending_count": 4,
"working_tree_dirty": true,
"changed_file_count": 36
"changed_file_count": 39
},
"commit": "7afde5ebafd5b8cb0b00aaaac4943c037fc9dce4",
"commit": "d7018dac5583d8973d8544d5f02906e94e8b1f9b",
"missing_artifacts": [],
"limitations": [
"Local command-runner evidence is reproducible but does not replace provider-backed model holdout evidence.",
@@ -983,9 +983,9 @@
"failures": []
},
"trust_security": {
"scanned_files": 169,
"script_count": 85,
"internal_module_count": 12,
"scanned_files": 171,
"script_count": 87,
"internal_module_count": 14,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -1003,8 +1003,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 169,
"package_sha256": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e"
"package_hash_file_count": 171,
"package_sha256": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49"
},
"skill_atlas": {
"skill_count": 12,
@@ -1042,8 +1042,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e",
"archive_sha256": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25"
"package_sha256": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49",
"archive_sha256": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0"
},
"compatibility": {
"openai": "pass",
@@ -1074,7 +1074,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25",
"archive_sha256": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1090,8 +1090,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25",
"archive_entry_count": 553,
"archive_sha256": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0",
"archive_entry_count": 555,
"failure_count": 0,
"warning_count": 0
},
@@ -1102,7 +1102,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 553,
"archive_entry_count": 555,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1169,12 +1169,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25"
"to": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e"
"to": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49"
}
]
},
reports/security_trust_report.json
+42 -6
View File
@@ -2,9 +2,9 @@
"ok": true,
"skill_dir": ".",
"summary": {
"scanned_files": 169,
"script_count": 85,
"internal_module_count": 12,
"scanned_files": 171,
"script_count": 87,
"internal_module_count": 14,
"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": 169,
"package_sha256": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e"
"package_hash_file_count": 171,
"package_sha256": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49"
},
"failures": [],
"warnings": [],
@@ -872,6 +872,20 @@
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/review_studio_data.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by render_review_studio.py to load Review Studio source reports and metric cards.",
"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/review_studio_formatting.py",
"interface": "internal-module",
@@ -914,6 +928,20 @@
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/review_studio_world_class.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by render_review_studio.py to render world-class evidence cards.",
"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/run_conformance_suite.py",
"interface": "cli",
@@ -1271,7 +1299,7 @@
"checked_count": 73,
"passed_count": 73,
"failed_count": 0,
"skipped_count": 12,
"skipped_count": 14,
"failed_scripts": [],
"results": [
{
@@ -2006,6 +2034,10 @@
}
],
"skipped": [
{
"path": "scripts/review_studio_data.py",
"reason": "internal module"
},
{
"path": "scripts/review_studio_formatting.py",
"reason": "internal module"
@@ -2018,6 +2050,10 @@
"path": "scripts/review_studio_layout.py",
"reason": "internal module"
},
{
"path": "scripts/review_studio_world_class.py",
"reason": "internal module"
},
{
"path": "scripts/skill_report_charts.py",
"reason": "internal module"
reports/security_trust_report.md
+7 -5
View File
@@ -1,9 +1,9 @@
# Security Trust Report
- OK: `True`
- Scanned files: `169`
- Scripts: `85`
- Internal script modules: `12`
- Scanned files: `171`
- Scripts: `87`
- Internal script modules: `14`
- 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: `169`
- Package SHA256: `18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e`
- Package hash files: `171`
- Package SHA256: `1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49`
## Failures
@@ -121,9 +121,11 @@
| scripts/render_world_class_evidence_ledger.py | cli | True | True | True | False | False | True | False | Renders a machine-checkable ledger for world-class external and human evidence gaps. |
| scripts/render_world_class_evidence_plan.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/resource_boundary_check.py | cli | False | True | True | False | False | False | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/review_studio_data.py | internal-module | True | False | False | False | False | False | False | Imported by render_review_studio.py to load Review Studio source reports and metric cards. |
| scripts/review_studio_formatting.py | internal-module | True | False | False | False | False | False | False | Imported by render_review_studio.py to format report dictionaries as audit UI panels. |
| scripts/review_studio_gates.py | internal-module | True | False | False | False | False | False | False | Imported by render_review_studio.py to keep Review Studio gate evaluation separate from HTML rendering. |
| scripts/review_studio_layout.py | internal-module | True | False | False | False | False | False | False | Imported by render_review_studio.py to keep Review Studio layout and CSS out of gate logic. |
| scripts/review_studio_world_class.py | internal-module | True | False | False | False | False | False | False | Imported by render_review_studio.py to render world-class evidence cards. |
| scripts/run_conformance_suite.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/run_description_optimization_suite.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/run_eval_suite.py | cli | False | True | True | False | False | False | True | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
reports/skill-overview.html
+1 -1
View File
@@ -771,7 +771,7 @@
<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 x="20" y="30" class="chart-title">资产分布</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.8 99.2" 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="0.8 99.2" stroke-dashoffset="-0.8" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-1.7" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-2.5" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="26.4 73.6" stroke-dashoffset="-3.3" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="70.2 29.8" stroke-dashoffset="-29.8" pathLength="100" transform="rotate(-90 130 130)"/><text x="130" y="136" text-anchor="middle">344项</text><text x="235" y="78">SKILL.md</text><text x="235" y="100">README.md</text><text x="235" y="122">agents/interface.yaml</text><text x="235" y="144">manifest.json</text><text x="235" y="166">references</text><text x="235" y="188">scripts</text></svg><figcaption>资产分布图展示当前包体的文件和目录重心。</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 x="20" y="30" class="chart-title">资产分布</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.8 99.2" 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="0.8 99.2" stroke-dashoffset="-0.8" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-1.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-2.4" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="26.0 74.0" stroke-dashoffset="-3.3" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="70.7 29.3" stroke-dashoffset="-29.3" pathLength="100" transform="rotate(-90 130 130)"/><text x="130" y="136" text-anchor="middle">346项</text><text x="235" y="78">SKILL.md</text><text x="235" y="100">README.md</text><text x="235" y="122">agents/interface.yaml</text><text x="235" y="144">manifest.json</text><text x="235" y="166">references</text><text x="235" y="188">scripts</text></svg><figcaption>资产分布图展示当前包体的文件和目录重心。</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>
reports/skill-overview.json
+19 -19
View File
@@ -436,7 +436,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 85
"file_count": 87
},
{
"path": "evals",
@@ -451,7 +451,7 @@
"file_count": 195
}
],
"file_count": 344,
"file_count": 346,
"folder_count": 4,
"distribution": [
{
@@ -476,7 +476,7 @@
},
{
"label": "scripts",
"value": 85
"value": 87
},
{
"label": "evals",
@@ -605,7 +605,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 85
"file_count": 87
},
{
"path": "evals",
@@ -905,9 +905,9 @@
"world_class_task_count": 4,
"world_class_ledger_pending_count": 4,
"working_tree_dirty": true,
"changed_file_count": 36
"changed_file_count": 39
},
"commit": "7afde5ebafd5b8cb0b00aaaac4943c037fc9dce4",
"commit": "d7018dac5583d8973d8544d5f02906e94e8b1f9b",
"missing_artifacts": [],
"limitations": [
"Local command-runner evidence is reproducible but does not replace provider-backed model holdout evidence.",
@@ -982,9 +982,9 @@
"failures": []
},
"trust_security": {
"scanned_files": 169,
"script_count": 85,
"internal_module_count": 12,
"scanned_files": 171,
"script_count": 87,
"internal_module_count": 14,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -1002,8 +1002,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 169,
"package_sha256": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e"
"package_hash_file_count": 171,
"package_sha256": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49"
},
"skill_atlas": {
"skill_count": 12,
@@ -1041,8 +1041,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e",
"archive_sha256": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25"
"package_sha256": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49",
"archive_sha256": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0"
},
"compatibility": {
"openai": "pass",
@@ -1073,7 +1073,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25",
"archive_sha256": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1089,8 +1089,8 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25",
"archive_entry_count": 553,
"archive_sha256": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0",
"archive_entry_count": 555,
"failure_count": 0,
"warning_count": 0
},
@@ -1101,7 +1101,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 553,
"archive_entry_count": 555,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1168,12 +1168,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25"
"to": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e"
"to": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49"
}
]
},
reports/skill_atlas.json
+2
View File
@@ -123,9 +123,11 @@
"scripts/render_world_class_evidence_ledger.py",
"scripts/render_world_class_evidence_plan.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_data.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_gates.py",
"scripts/review_studio_layout.py",
"scripts/review_studio_world_class.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
reports/skill_os2_audit.json
+2 -2
View File
@@ -197,7 +197,7 @@
"key": "trust-security",
"label": "Trust Security",
"status": "pass",
"current": "secrets 0; scripts 85; help failures 0",
"current": "secrets 0; scripts 87; help failures 0",
"target": "Secrets, scripts, dependencies, permissions, and package hash are reviewable",
"evidence": [
{
@@ -281,7 +281,7 @@
"key": "registry-distribution",
"label": "Registry Distribution",
"status": "pass",
"current": "zip entries 553; install failures 0; permission failures 0",
"current": "zip entries 555; install failures 0; permission failures 0",
"target": "Package metadata, archive checksum, package verification, and install simulation pass",
"evidence": [
{
reports/skill_os2_audit.md
+2 -2
View File
@@ -23,11 +23,11 @@ Generated at: `2026-06-14`
| 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 20; 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 85; 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 87; 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 | Packaged adapters expose explicit permission metadata and residual risks | Preserve residual-risk notes until real native enforcement exists. |
| Native Permission Enforcement | external-required | native-enforced targets 0 | At least one target/client enforces approved permissions at runtime | Integrate a real client or 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 553; 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 555; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. |
| Review Studio | pass | decision review; warnings 4; score 89 | One page shows gates, evidence paths, blockers, warnings, actions, waivers, and annotations | Resolve human/external warning gates before claiming full release readiness. |
| Telemetry Drift | pass | events 1; risk low; recipes 5 | Local-first metadata-only event contract, aggregate drift report, hook recipes, and import path | Keep raw JSONL out of distributed packages and use aggregate reports for Atlas. |
| Native Client Telemetry | external-required | external source events 0; adoption samples 0 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. |
reports/skill_os2_coverage.json
+2 -2
View File
@@ -122,7 +122,7 @@
"label": "Trust Security",
"status": "pass",
"objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
"current": "85 scripts; secrets 0; help failures 0",
"current": "87 scripts; secrets 0; help failures 0",
"command": "python3 scripts/yao.py trust .",
"test": "python3 tests/verify_trust_check.py",
"evidence": [
@@ -196,7 +196,7 @@
"label": "Registry Distribution",
"status": "pass",
"objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
"current": "archive entries 553; install failures 0",
"current": "archive entries 555; 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": [
reports/skill_os2_coverage.md
+2 -2
View File
@@ -21,9 +21,9 @@ 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` | 85 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` |
| Trust Security | `pass` | 87 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 553; 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 555; 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 4 | `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` |
reports/upgrade_check.json
+2 -2
View File
@@ -70,12 +70,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "26e0362e174968f9eaeabb4f47304f641610791bc215f4e55d675d3367448b25"
"to": "7ebe0695052701dec068e1070b72aea19c865b039cf65e8773063b335395bdb0"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "18e4ec6cd34d80c2fff0ce51a7a107f15c9dbaa5c6d4e54065aee15dbd0fb00e"
"to": "1636101ae369f5659d9a64e95bb19144e1271912f1ac5ce846fd7b569cb1ff49"
}
]
},
scripts/render_review_studio.py
+2 -311
View File
@@ -6,57 +6,16 @@ import os
from pathlib import Path
from typing import Any
try:
import yaml
except ImportError: # pragma: no cover
yaml = None
from review_studio_data import evidence_paths, insight_cards, load_review_data
from review_studio_formatting import registry_package_summary, render_kv_grid
from review_studio_gates import add_blockers_from_gate, build_gates, status_label, weighted_score
from review_studio_layout import render_review_nav, review_studio_css
from review_studio_world_class import render_world_class_evidence_entries
ROOT = Path(__file__).resolve().parent.parent
def load_json(path: Path) -> dict[str, Any]:
if not path.exists():
return {}
try:
payload = json.loads(path.read_text(encoding="utf-8"))
except json.JSONDecodeError:
return {}
return payload if isinstance(payload, dict) else {}
def load_yaml(path: Path) -> dict[str, Any]:
if not path.exists() or yaml is None:
return {}
payload = yaml.safe_load(path.read_text(encoding="utf-8")) or {}
return payload if isinstance(payload, dict) else {}
def parse_frontmatter(path: Path) -> dict[str, Any]:
if not path.exists():
return {}
lines = path.read_text(encoding="utf-8", errors="replace").splitlines()
if not lines or lines[0].strip() != "---":
return {}
try:
end_index = lines[1:].index("---") + 1
except ValueError:
return {}
text = "\n".join(lines[1:end_index])
if yaml is not None:
payload = yaml.safe_load(text) or {}
return payload if isinstance(payload, dict) else {}
data = {}
for line in text.splitlines():
if ":" in line:
key, value = line.split(":", 1)
data[key.strip()] = value.strip().strip('"')
return data
def display_path(skill_dir: Path, path: Path) -> str:
try:
@@ -115,231 +74,6 @@ def source_refs(
return refs
def evidence_paths(skill_dir: Path) -> dict[str, str]:
rels = {
"skill_overview": "reports/skill-overview.html",
"review_viewer": "reports/review-viewer.html",
"output_eval": "reports/output_quality_scorecard.md",
"output_execution": "reports/output_execution_runs.md",
"output_blind_review": "reports/output_blind_review_pack.md",
"output_review_decisions": "reports/output_review_decisions.json",
"output_review_adjudication": "reports/output_review_adjudication.md",
"benchmark_reproducibility": "reports/benchmark_reproducibility.md",
"skill_os2_coverage": "reports/skill_os2_coverage.md",
"runtime_conformance": "reports/conformance_matrix.md",
"trust_report": "reports/security_trust_report.md",
"python_compatibility": "reports/python_compatibility.md",
"architecture_maintainability": "reports/architecture_maintainability.md",
"permission_policy": "security/permission_policy.md",
"runtime_permissions": "reports/runtime_permission_probes.md",
"skill_atlas": "reports/skill_atlas.html",
"compiled_targets": "reports/compiled_targets.md",
"adoption_drift": "reports/adoption_drift_report.md",
"review_waivers": "reports/review_waivers.md",
"review_annotations": "reports/review_annotations.md",
"world_class_evidence_plan": "reports/world_class_evidence_plan.md",
"world_class_evidence_ledger": "reports/world_class_evidence_ledger.md",
"world_class_evidence_intake": "reports/world_class_evidence_intake.md",
"world_class_claim_guard": "reports/world_class_claim_guard.md",
"registry_audit": "reports/registry_audit.md",
"package_verification": "reports/package_verification.md",
"install_simulation": "reports/install_simulation.md",
"upgrade_check": "reports/upgrade_check.md",
"migration": "docs/migration-v2.md",
"skill_ir": "reports/skill-ir.json",
}
return {key: rel for key, rel in rels.items() if (skill_dir / rel).exists() or (ROOT / rel).exists()}
def load_review_data(skill_dir: Path) -> dict[str, dict[str, Any]]:
reports = skill_dir / "reports"
return {
"overview": load_json(reports / "skill-overview.json"),
"intent_confidence": load_json(reports / "intent-confidence.json"),
"intent_dialogue": load_json(reports / "intent-dialogue.json"),
"route_scorecard": load_json(reports / "route_scorecard.json"),
"output_quality": load_json(reports / "output_quality_scorecard.json"),
"output_execution": load_json(reports / "output_execution_runs.json"),
"output_blind_review": load_json(reports / "output_blind_review_pack.json"),
"output_review_adjudication": load_json(reports / "output_review_adjudication.json"),
"skill_os2_coverage": load_json(reports / "skill_os2_coverage.json"),
"compiled_targets": load_json(reports / "compiled_targets.json"),
"conformance": load_json(reports / "conformance_matrix.json"),
"runtime_permissions": load_json(reports / "runtime_permission_probes.json"),
"trust": load_json(reports / "security_trust_report.json"),
"python_compatibility": load_json(reports / "python_compatibility.json"),
"architecture_maintainability": load_json(reports / "architecture_maintainability.json"),
"context_budget": load_json(reports / "context_budget.json"),
"promotion": load_json(reports / "promotion_decisions.json"),
"atlas": load_json(reports / "skill_atlas.json"),
"adoption_drift": load_json(reports / "adoption_drift_report.json"),
"review_waivers": load_json(reports / "review_waivers.json"),
"review_annotations": load_json(reports / "review_annotations.json"),
"world_class_evidence_ledger": load_json(reports / "world_class_evidence_ledger.json"),
"world_class_evidence_intake": load_json(reports / "world_class_evidence_intake.json"),
"world_class_claim_guard": load_json(reports / "world_class_claim_guard.json"),
"registry": load_json(reports / "registry_audit.json"),
"package_verification": load_json(reports / "package_verification.json"),
"install_simulation": load_json(reports / "install_simulation.json"),
"upgrade_check": load_json(reports / "upgrade_check.json"),
"manifest": load_json(skill_dir / "manifest.json"),
"frontmatter": parse_frontmatter(skill_dir / "SKILL.md"),
"interface": load_yaml(skill_dir / "agents" / "interface.yaml"),
}
def insight_cards(data: dict[str, dict[str, Any]]) -> list[dict[str, str]]:
overview = data["overview"]
output = data["output_quality"].get("summary", {})
output_execution = data["output_execution"].get("summary", {})
output_blind = data["output_blind_review"].get("summary", {})
output_review = data["output_review_adjudication"].get("summary", {})
blueprint = data["skill_os2_coverage"].get("summary", {})
compiled = data["compiled_targets"].get("summary", {})
conformance = data["conformance"].get("summary", {})
runtime_permissions = data["runtime_permissions"].get("summary", {})
trust = data["trust"].get("summary", {})
python_compat = data["python_compatibility"].get("summary", {})
architecture = data["architecture_maintainability"].get("summary", {})
atlas = data["atlas"].get("summary", {})
adoption = data["adoption_drift"].get("summary", {})
waivers = data["review_waivers"].get("summary", {})
annotations = data["review_annotations"].get("summary", {})
intake = data["world_class_evidence_intake"].get("summary", {})
claim_guard = data["world_class_claim_guard"].get("summary", {})
registry = data["registry"].get("package", {})
package_verification = data["package_verification"].get("summary", {})
install_simulation = data["install_simulation"].get("summary", {})
upgrade = data["upgrade_check"].get("summary", {})
cards = [
{
"label": "Skill IR",
"value": str(overview.get("skill_ir", {}).get("schema_version", "missing")),
"detail": f"{overview.get('skill_ir', {}).get('target_count', 0)} targets in platform-neutral contract",
},
{
"label": "Compiler",
"value": f"{compiled.get('pass_count', 0)}/{compiled.get('target_count', 0)}",
"detail": "target contracts compiled from Skill IR",
},
{
"label": "Output Delta",
"value": str(output.get("delta", "n/a")),
"detail": f"{output.get('case_count', 0)} cases; {output.get('file_backed_case_count', 0)} file-backed",
},
{
"label": "Exec Runs",
"value": str(output_execution.get("variant_run_count", 0)),
"detail": (
f"command {output_execution.get('command_executed_count', 0)}; "
f"model {output_execution.get('model_executed_count', 0)}; "
f"recorded {output_execution.get('recorded_fixture_count', 0)}"
),
},
{
"label": "Blind A/B",
"value": str(output_blind.get("pair_count", 0)),
"detail": "review pairs hide baseline vs with-skill labels",
},
{
"label": "Review A/B",
"value": f"{output_review.get('judgment_count', 0)}/{output_review.get('pair_count', 0)}",
"detail": f"adjudication decisions; pending {output_review.get('pending_count', 0)}",
},
{
"label": "Blueprint",
"value": f"{blueprint.get('pass_count', 0)}/{blueprint.get('item_count', 0)}",
"detail": f"2.0 coverage; evidence pending {blueprint.get('world_class_evidence_pending_count', 0)}",
},
{
"label": "Runtime",
"value": f"{conformance.get('pass_count', 0)}/{conformance.get('target_count', 0)}",
"detail": "target conformance pass rate",
},
{
"label": "Perm Probe",
"value": f"{runtime_permissions.get('metadata_fallback_count', 0)}/{runtime_permissions.get('target_count', 0)}",
"detail": f"{runtime_permissions.get('native_enforcement_count', 0)} native enforcement targets",
},
{
"label": "Trust",
"value": str(trust.get("secret_findings", 0)),
"detail": f"{trust.get('script_count', 0)} scripts scanned; secrets found",
},
{
"label": "Py Compat",
"value": str(python_compat.get("issue_count", 0)),
"detail": f"{python_compat.get('file_count', 0)} files scanned for Python {python_compat.get('target_python', '3.11')}",
},
{
"label": "Arch Debt",
"value": str(architecture.get("hotspot_count", 0)),
"detail": (
f"{architecture.get('largest_file_lines', 0)} largest lines; "
f"{architecture.get('command_handler_count', 0)} CLI handlers"
),
},
{
"label": "Atlas",
"value": str(atlas.get("route_collision_count", 0)),
"detail": f"{atlas.get('skill_count', 0)} scanned skills; route collisions",
},
{
"label": "Drift",
"value": str(adoption.get("risk_band", "n/a")),
"detail": f"{adoption.get('event_count', 0)} metadata events; {adoption.get('missed_trigger_count', 0)} missed triggers",
},
{
"label": "Waivers",
"value": str(waivers.get("active_count", 0)),
"detail": f"{waivers.get('covered_gate_count', 0)} gates covered; human risk decisions",
},
{
"label": "Intake",
"value": f"{intake.get('template_pass_count', 0)}/{intake.get('template_count', 0)}",
"detail": (
f"{intake.get('valid_submission_count', 0)} valid submissions; "
f"{intake.get('invalid_submission_count', 0)} invalid"
),
},
{
"label": "Claim Guard",
"value": str(claim_guard.get("violation_count", 0)),
"detail": f"{claim_guard.get('claim_surface_count', 0)} public surfaces scanned",
},
{
"label": "Notes",
"value": f"{annotations.get('open_count', 0)}/{annotations.get('annotation_count', 0)}",
"detail": f"{annotations.get('open_blocker_count', 0)} open blocker annotations",
},
{
"label": "Registry",
"value": str(registry.get("version", "n/a")),
"detail": f"{len(registry.get('targets', []))} targets; {registry.get('license', 'no license')} license",
},
{
"label": "Archive",
"value": "pass" if data["package_verification"].get("ok") else "n/a",
"detail": f"{package_verification.get('archive_entry_count', 0)} zip entries; package verification",
},
{
"label": "Install",
"value": "pass" if data["install_simulation"].get("ok") else "n/a",
"detail": (
f"{install_simulation.get('adapter_count', 0)} adapters; "
f"{install_simulation.get('installer_permission_enforced_count', 0)} permissions enforced; "
f"{install_simulation.get('installer_permission_failure_count', 0)} permission failures"
),
},
{
"label": "Upgrade",
"value": str(upgrade.get("recommended_bump", "n/a")),
"detail": f"declared {upgrade.get('declared_bump', 'n/a')}; {upgrade.get('breaking_change_count', 0)} breaking changes",
},
]
return cards
def render_gate_list(gates: list[dict[str, str]]) -> str:
items = []
for item in gates:
@@ -684,49 +418,6 @@ def render_review_annotations_panel(annotations_report: dict[str, Any]) -> str:
return "".join(cards)
def render_inline_list(items: list[Any], empty_label: str) -> str:
if not items:
return f"<p class='muted'>{html.escape(empty_label)}</p>"
return "<ul>" + "".join(f"<li>{html.escape(str(item))}</li>" for item in items) + "</ul>"
def render_world_class_evidence_entries(ledger: dict[str, Any]) -> str:
entries = ledger.get("entries", []) if isinstance(ledger, dict) else []
if not entries:
return "<p class='muted'>当前没有 world-class 证据条目。</p>"
cards = []
for entry in entries:
observed = entry.get("observed_state", {}) if isinstance(entry.get("observed_state", {}), dict) else {}
observed_summary = "; ".join(f"{key}: {value}" for key, value in observed.items())
status = str(entry.get("status", "pending"))
status_label_text = "已接受" if status == "accepted" else "待补证"
cards.append(
"<article class='world-evidence-card "
+ html.escape(status)
+ "'>"
f"<div><span>{html.escape(status_label_text)} · {html.escape(str(entry.get('category', '')))}</span>"
f"<h3>{html.escape(str(entry.get('label', entry.get('key', 'evidence'))))}</h3></div>"
f"<p>{html.escape(str(entry.get('objective', '')))}</p>"
f"<dl><dt>负责人</dt><dd>{html.escape(str(entry.get('owner', '')))}</dd>"
f"<dt>当前状态</dt><dd>{html.escape(str(entry.get('current', '')))}</dd>"
f"<dt>下一步</dt><dd>{html.escape(str(entry.get('next_action', '')))}</dd>"
f"<dt>观测值</dt><dd>{html.escape(observed_summary or '无')}</dd></dl>"
"<div class='world-evidence-columns'>"
"<div><h4>完成定义</h4>"
+ render_inline_list(entry.get("success_checks", []), "暂无完成定义。")
+ "</div>"
"<div><h4>证据来源</h4>"
+ render_inline_list(entry.get("evidence_artifacts", []), "暂无证据来源。")
+ "</div>"
"<div><h4>隐私约束</h4>"
+ render_inline_list(entry.get("privacy_contract", []), "暂无隐私约束。")
+ "</div>"
"</div>"
"</article>"
)
return "<div class='world-evidence-grid'>" + "".join(cards) + "</div>"
def render_html(report: dict[str, Any]) -> str:
summary = report["summary"]
gates = report["gates"]
scripts/review_studio_data.py
+281
View File
@@ -0,0 +1,281 @@
#!/usr/bin/env python3
"""Data loading and insight card helpers for Review Studio."""
import json
from pathlib import Path
from typing import Any
try:
import yaml
except ImportError: # pragma: no cover
yaml = None
SCRIPT_INTERFACE = "internal-module"
SCRIPT_INTERFACE_REASON = "Imported by render_review_studio.py to load Review Studio source reports and metric cards."
ROOT = Path(__file__).resolve().parent.parent
def load_json(path: Path) -> dict[str, Any]:
if not path.exists():
return {}
try:
payload = json.loads(path.read_text(encoding="utf-8"))
except json.JSONDecodeError:
return {}
return payload if isinstance(payload, dict) else {}
def load_yaml(path: Path) -> dict[str, Any]:
if not path.exists() or yaml is None:
return {}
payload = yaml.safe_load(path.read_text(encoding="utf-8")) or {}
return payload if isinstance(payload, dict) else {}
def parse_frontmatter(path: Path) -> dict[str, Any]:
if not path.exists():
return {}
lines = path.read_text(encoding="utf-8", errors="replace").splitlines()
if not lines or lines[0].strip() != "---":
return {}
try:
end_index = lines[1:].index("---") + 1
except ValueError:
return {}
text = "\n".join(lines[1:end_index])
if yaml is not None:
payload = yaml.safe_load(text) or {}
return payload if isinstance(payload, dict) else {}
data = {}
for line in text.splitlines():
if ":" in line:
key, value = line.split(":", 1)
data[key.strip()] = value.strip().strip('"')
return data
def evidence_paths(skill_dir: Path) -> dict[str, str]:
rels = {
"skill_overview": "reports/skill-overview.html",
"review_viewer": "reports/review-viewer.html",
"output_eval": "reports/output_quality_scorecard.md",
"output_execution": "reports/output_execution_runs.md",
"output_blind_review": "reports/output_blind_review_pack.md",
"output_review_decisions": "reports/output_review_decisions.json",
"output_review_adjudication": "reports/output_review_adjudication.md",
"benchmark_reproducibility": "reports/benchmark_reproducibility.md",
"skill_os2_coverage": "reports/skill_os2_coverage.md",
"runtime_conformance": "reports/conformance_matrix.md",
"trust_report": "reports/security_trust_report.md",
"python_compatibility": "reports/python_compatibility.md",
"architecture_maintainability": "reports/architecture_maintainability.md",
"permission_policy": "security/permission_policy.md",
"runtime_permissions": "reports/runtime_permission_probes.md",
"skill_atlas": "reports/skill_atlas.html",
"compiled_targets": "reports/compiled_targets.md",
"adoption_drift": "reports/adoption_drift_report.md",
"review_waivers": "reports/review_waivers.md",
"review_annotations": "reports/review_annotations.md",
"world_class_evidence_plan": "reports/world_class_evidence_plan.md",
"world_class_evidence_ledger": "reports/world_class_evidence_ledger.md",
"world_class_evidence_intake": "reports/world_class_evidence_intake.md",
"world_class_claim_guard": "reports/world_class_claim_guard.md",
"registry_audit": "reports/registry_audit.md",
"package_verification": "reports/package_verification.md",
"install_simulation": "reports/install_simulation.md",
"upgrade_check": "reports/upgrade_check.md",
"migration": "docs/migration-v2.md",
"skill_ir": "reports/skill-ir.json",
}
return {key: rel for key, rel in rels.items() if (skill_dir / rel).exists() or (ROOT / rel).exists()}
def load_review_data(skill_dir: Path) -> dict[str, dict[str, Any]]:
reports = skill_dir / "reports"
return {
"overview": load_json(reports / "skill-overview.json"),
"intent_confidence": load_json(reports / "intent-confidence.json"),
"intent_dialogue": load_json(reports / "intent-dialogue.json"),
"route_scorecard": load_json(reports / "route_scorecard.json"),
"output_quality": load_json(reports / "output_quality_scorecard.json"),
"output_execution": load_json(reports / "output_execution_runs.json"),
"output_blind_review": load_json(reports / "output_blind_review_pack.json"),
"output_review_adjudication": load_json(reports / "output_review_adjudication.json"),
"skill_os2_coverage": load_json(reports / "skill_os2_coverage.json"),
"compiled_targets": load_json(reports / "compiled_targets.json"),
"conformance": load_json(reports / "conformance_matrix.json"),
"runtime_permissions": load_json(reports / "runtime_permission_probes.json"),
"trust": load_json(reports / "security_trust_report.json"),
"python_compatibility": load_json(reports / "python_compatibility.json"),
"architecture_maintainability": load_json(reports / "architecture_maintainability.json"),
"context_budget": load_json(reports / "context_budget.json"),
"promotion": load_json(reports / "promotion_decisions.json"),
"atlas": load_json(reports / "skill_atlas.json"),
"adoption_drift": load_json(reports / "adoption_drift_report.json"),
"review_waivers": load_json(reports / "review_waivers.json"),
"review_annotations": load_json(reports / "review_annotations.json"),
"world_class_evidence_ledger": load_json(reports / "world_class_evidence_ledger.json"),
"world_class_evidence_intake": load_json(reports / "world_class_evidence_intake.json"),
"world_class_claim_guard": load_json(reports / "world_class_claim_guard.json"),
"registry": load_json(reports / "registry_audit.json"),
"package_verification": load_json(reports / "package_verification.json"),
"install_simulation": load_json(reports / "install_simulation.json"),
"upgrade_check": load_json(reports / "upgrade_check.json"),
"manifest": load_json(skill_dir / "manifest.json"),
"frontmatter": parse_frontmatter(skill_dir / "SKILL.md"),
"interface": load_yaml(skill_dir / "agents" / "interface.yaml"),
}
def insight_cards(data: dict[str, dict[str, Any]]) -> list[dict[str, str]]:
overview = data["overview"]
output = data["output_quality"].get("summary", {})
output_execution = data["output_execution"].get("summary", {})
output_blind = data["output_blind_review"].get("summary", {})
output_review = data["output_review_adjudication"].get("summary", {})
blueprint = data["skill_os2_coverage"].get("summary", {})
compiled = data["compiled_targets"].get("summary", {})
conformance = data["conformance"].get("summary", {})
runtime_permissions = data["runtime_permissions"].get("summary", {})
trust = data["trust"].get("summary", {})
python_compat = data["python_compatibility"].get("summary", {})
architecture = data["architecture_maintainability"].get("summary", {})
atlas = data["atlas"].get("summary", {})
adoption = data["adoption_drift"].get("summary", {})
waivers = data["review_waivers"].get("summary", {})
annotations = data["review_annotations"].get("summary", {})
intake = data["world_class_evidence_intake"].get("summary", {})
claim_guard = data["world_class_claim_guard"].get("summary", {})
registry = data["registry"].get("package", {})
package_verification = data["package_verification"].get("summary", {})
install_simulation = data["install_simulation"].get("summary", {})
upgrade = data["upgrade_check"].get("summary", {})
cards = [
{
"label": "Skill IR",
"value": str(overview.get("skill_ir", {}).get("schema_version", "missing")),
"detail": f"{overview.get('skill_ir', {}).get('target_count', 0)} targets in platform-neutral contract",
},
{
"label": "Compiler",
"value": f"{compiled.get('pass_count', 0)}/{compiled.get('target_count', 0)}",
"detail": "target contracts compiled from Skill IR",
},
{
"label": "Output Delta",
"value": str(output.get("delta", "n/a")),
"detail": f"{output.get('case_count', 0)} cases; {output.get('file_backed_case_count', 0)} file-backed",
},
{
"label": "Exec Runs",
"value": str(output_execution.get("variant_run_count", 0)),
"detail": (
f"command {output_execution.get('command_executed_count', 0)}; "
f"model {output_execution.get('model_executed_count', 0)}; "
f"recorded {output_execution.get('recorded_fixture_count', 0)}"
),
},
{
"label": "Blind A/B",
"value": str(output_blind.get("pair_count", 0)),
"detail": "review pairs hide baseline vs with-skill labels",
},
{
"label": "Review A/B",
"value": f"{output_review.get('judgment_count', 0)}/{output_review.get('pair_count', 0)}",
"detail": f"adjudication decisions; pending {output_review.get('pending_count', 0)}",
},
{
"label": "Blueprint",
"value": f"{blueprint.get('pass_count', 0)}/{blueprint.get('item_count', 0)}",
"detail": f"2.0 coverage; evidence pending {blueprint.get('world_class_evidence_pending_count', 0)}",
},
{
"label": "Runtime",
"value": f"{conformance.get('pass_count', 0)}/{conformance.get('target_count', 0)}",
"detail": "target conformance pass rate",
},
{
"label": "Perm Probe",
"value": f"{runtime_permissions.get('metadata_fallback_count', 0)}/{runtime_permissions.get('target_count', 0)}",
"detail": f"{runtime_permissions.get('native_enforcement_count', 0)} native enforcement targets",
},
{
"label": "Trust",
"value": str(trust.get("secret_findings", 0)),
"detail": f"{trust.get('script_count', 0)} scripts scanned; secrets found",
},
{
"label": "Py Compat",
"value": str(python_compat.get("issue_count", 0)),
"detail": f"{python_compat.get('file_count', 0)} files scanned for Python {python_compat.get('target_python', '3.11')}",
},
{
"label": "Arch Debt",
"value": str(architecture.get("hotspot_count", 0)),
"detail": (
f"{architecture.get('largest_file_lines', 0)} largest lines; "
f"{architecture.get('command_handler_count', 0)} CLI handlers"
),
},
{
"label": "Atlas",
"value": str(atlas.get("route_collision_count", 0)),
"detail": f"{atlas.get('skill_count', 0)} scanned skills; route collisions",
},
{
"label": "Drift",
"value": str(adoption.get("risk_band", "n/a")),
"detail": f"{adoption.get('event_count', 0)} metadata events; {adoption.get('missed_trigger_count', 0)} missed triggers",
},
{
"label": "Waivers",
"value": str(waivers.get("active_count", 0)),
"detail": f"{waivers.get('covered_gate_count', 0)} gates covered; human risk decisions",
},
{
"label": "Intake",
"value": f"{intake.get('template_pass_count', 0)}/{intake.get('template_count', 0)}",
"detail": (
f"{intake.get('valid_submission_count', 0)} valid submissions; "
f"{intake.get('invalid_submission_count', 0)} invalid"
),
},
{
"label": "Claim Guard",
"value": str(claim_guard.get("violation_count", 0)),
"detail": f"{claim_guard.get('claim_surface_count', 0)} public surfaces scanned",
},
{
"label": "Notes",
"value": f"{annotations.get('open_count', 0)}/{annotations.get('annotation_count', 0)}",
"detail": f"{annotations.get('open_blocker_count', 0)} open blocker annotations",
},
{
"label": "Registry",
"value": str(registry.get("version", "n/a")),
"detail": f"{len(registry.get('targets', []))} targets; {registry.get('license', 'no license')} license",
},
{
"label": "Archive",
"value": "pass" if data["package_verification"].get("ok") else "n/a",
"detail": f"{package_verification.get('archive_entry_count', 0)} zip entries; package verification",
},
{
"label": "Install",
"value": "pass" if data["install_simulation"].get("ok") else "n/a",
"detail": (
f"{install_simulation.get('adapter_count', 0)} adapters; "
f"{install_simulation.get('installer_permission_enforced_count', 0)} permissions enforced; "
f"{install_simulation.get('installer_permission_failure_count', 0)} permission failures"
),
},
{
"label": "Upgrade",
"value": str(upgrade.get("recommended_bump", "n/a")),
"detail": f"declared {upgrade.get('declared_bump', 'n/a')}; {upgrade.get('breaking_change_count', 0)} breaking changes",
},
]
return cards
scripts/review_studio_world_class.py
+52
View File
@@ -0,0 +1,52 @@
#!/usr/bin/env python3
"""World-class evidence HTML helpers for Review Studio."""
import html
from typing import Any
SCRIPT_INTERFACE = "internal-module"
SCRIPT_INTERFACE_REASON = "Imported by render_review_studio.py to render world-class evidence cards."
def render_inline_list(items: list[Any], empty_label: str) -> str:
if not items:
return f"<p class='muted'>{html.escape(empty_label)}</p>"
return "<ul>" + "".join(f"<li>{html.escape(str(item))}</li>" for item in items) + "</ul>"
def render_world_class_evidence_entries(ledger: dict[str, Any]) -> str:
entries = ledger.get("entries", []) if isinstance(ledger, dict) else []
if not entries:
return "<p class='muted'>当前没有 world-class 证据条目。</p>"
cards = []
for entry in entries:
observed = entry.get("observed_state", {}) if isinstance(entry.get("observed_state", {}), dict) else {}
observed_summary = "; ".join(f"{key}: {value}" for key, value in observed.items())
status = str(entry.get("status", "pending"))
status_label_text = "已接受" if status == "accepted" else "待补证"
cards.append(
"<article class='world-evidence-card "
+ html.escape(status)
+ "'>"
f"<div><span>{html.escape(status_label_text)} · {html.escape(str(entry.get('category', '')))}</span>"
f"<h3>{html.escape(str(entry.get('label', entry.get('key', 'evidence'))))}</h3></div>"
f"<p>{html.escape(str(entry.get('objective', '')))}</p>"
f"<dl><dt>负责人</dt><dd>{html.escape(str(entry.get('owner', '')))}</dd>"
f"<dt>当前状态</dt><dd>{html.escape(str(entry.get('current', '')))}</dd>"
f"<dt>下一步</dt><dd>{html.escape(str(entry.get('next_action', '')))}</dd>"
f"<dt>观测值</dt><dd>{html.escape(observed_summary or '无')}</dd></dl>"
"<div class='world-evidence-columns'>"
"<div><h4>完成定义</h4>"
+ render_inline_list(entry.get("success_checks", []), "暂无完成定义。")
+ "</div>"
"<div><h4>证据来源</h4>"
+ render_inline_list(entry.get("evidence_artifacts", []), "暂无证据来源。")
+ "</div>"
"<div><h4>隐私约束</h4>"
+ render_inline_list(entry.get("privacy_contract", []), "暂无隐私约束。")
+ "</div>"
"</div>"
"</article>"
)
return "<div class='world-evidence-grid'>" + "".join(cards) + "</div>"
skill-ir/examples/yao-meta-skill.json
+3 -3
View File
@@ -167,9 +167,11 @@
"scripts/render_world_class_evidence_ledger.py",
"scripts/render_world_class_evidence_plan.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_data.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_gates.py",
"scripts/review_studio_layout.py",
"scripts/review_studio_world_class.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -185,9 +187,7 @@
"scripts/trigger_eval.py",
"scripts/trust_check.py",
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/validate_skill.py"
],
"assets": [
"templates/basic_skill.md.j2",
skill_atlas/catalog.json
+2
View File
@@ -79,9 +79,11 @@
"scripts/render_world_class_evidence_ledger.py",
"scripts/render_world_class_evidence_plan.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_data.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_gates.py",
"scripts/review_studio_layout.py",
"scripts/review_studio_world_class.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
tests/verify_architecture_maintainability.py
+4 -3
View File
@@ -38,14 +38,15 @@ def main() -> None:
payload = json.loads(proc.stdout)
assert payload["ok"], payload
assert payload["summary"]["decision"] == "watch-maintainability-hotspots", payload["summary"]
assert payload["summary"]["hotspot_count"] >= 3, payload["summary"]
assert payload["summary"]["hotspot_count"] == 2, payload["summary"]
assert payload["summary"]["blocker_count"] == 0, payload["summary"]
assert 30 <= payload["summary"]["command_handler_count"] < 50, payload["summary"]
assert payload["summary"]["largest_file_lines"] >= 900, payload["summary"]
assert payload["largest_files"][0]["path"] == "scripts/render_review_studio.py", payload["largest_files"][0]
assert payload["largest_files"][0]["path"] == "scripts/yao.py", payload["largest_files"][0]
assert payload["largest_files"][0]["severity"] == "warn", payload["largest_files"][0]
hotspot_paths = {item["path"] for item in payload["hotspots"]}
assert {"scripts/yao.py", "scripts/render_review_studio.py", "scripts/render_review_viewer.py"} <= hotspot_paths, hotspot_paths
assert {"scripts/yao.py", "scripts/render_review_viewer.py"} <= hotspot_paths, hotspot_paths
assert "scripts/render_review_studio.py" not in hotspot_paths, hotspot_paths
assert output_json.exists(), output_json
markdown = output_md.read_text(encoding="utf-8")
assert "# Architecture Maintainability" in markdown, markdown
tests/verify_review_studio.py
+2 -2
View File
@@ -319,7 +319,7 @@ def main() -> None:
assert python_compat_gate["evidence"] == "reports/python_compatibility.json", python_compat_gate
architecture_gate = next(item for item in payload["gates"] if item["key"] == "architecture-maintainability")
assert architecture_gate["status"] == "warn", architecture_gate
assert "3 hotspots" in architecture_gate["detail"], architecture_gate
assert "2 hotspots" in architecture_gate["detail"], architecture_gate
assert "0 blockers" in architecture_gate["detail"], architecture_gate
assert "CLI handlers" in architecture_gate["detail"], architecture_gate
assert architecture_gate["evidence"] == "reports/architecture_maintainability.json", architecture_gate
@@ -392,7 +392,7 @@ def main() -> None:
assert full_payload["evidence_paths"]["runtime_permissions"] == "reports/runtime_permission_probes.md", full_payload["evidence_paths"]
assert full_payload["data"]["python_compatibility"]["summary"]["target_python"] == "3.11", full_payload["data"]["python_compatibility"]
assert full_payload["data"]["python_compatibility"]["summary"]["issue_count"] == 0, full_payload["data"]["python_compatibility"]
assert full_payload["data"]["architecture_maintainability"]["summary"]["hotspot_count"] >= 3, full_payload["data"]["architecture_maintainability"]
assert full_payload["data"]["architecture_maintainability"]["summary"]["hotspot_count"] == 2, full_payload["data"]["architecture_maintainability"]
assert full_payload["data"]["architecture_maintainability"]["summary"]["blocker_count"] == 0, full_payload["data"]["architecture_maintainability"]
action_keys = {item["gate_key"] for item in full_payload["review_actions"]}
assert action_keys == {"output-lab", "architecture-maintainability", "review-waivers", "world-class-evidence"}, full_payload["review_actions"]
tests/verify_yao_cli.py
+1 -1
View File
@@ -217,7 +217,7 @@ def main() -> None:
"2026-06-14",
)
assert architecture_result["ok"], architecture_result
assert architecture_result["payload"]["summary"]["hotspot_count"] >= 3, architecture_result
assert architecture_result["payload"]["summary"]["hotspot_count"] == 2, architecture_result
assert architecture_result["payload"]["summary"]["blocker_count"] == 0, architecture_result
assert 30 <= architecture_result["payload"]["summary"]["command_handler_count"] < 50, architecture_result