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

chore: modularize meta skill report surfaces

Browse Source
This commit is contained in:
yaojingang
2026-06-13 19:01:44 +08:00
parent 3fb08802e9
commit 5ba1c93a09
34 changed files with 1960 additions and 1258 deletions
Download Patch File Download Diff File Expand all files Collapse all files
AGENTS.md
+87
View File
@@ -0,0 +1,87 @@
# Agent Instructions
## Project Map
`yao-meta-skill` is the source repository for the Yao Meta Skill / Skill OS. Keep the root `SKILL.md` lean and route depth through the existing project layers:
- `SKILL.md`: public trigger surface, compact workflow, and Skill OS gates.
- `references/`: stable method doctrine and operating guidance.
- `scripts/`: executable logic, report generators, compilers, gates, and CLI entrypoints.
- `evals/`: trigger, output, packaging, semantic, and regression fixtures.
- `skill-ir/`: platform-neutral skill contract and examples.
- `agents/interface.yaml`: portable runtime and trust metadata.
- `security/`: script, dependency, network, permission, and trust policies.
- `registry/`: package metadata, installability evidence, and compatibility metadata.
- `skill_atlas/`: portfolio catalog, route overlap, ownership, stale-skill, and dependency evidence.
- `reports/`: generated review, trust, conformance, registry, overview, and release evidence.
- `docs/`: durable public docs such as migration notes and localized READMEs.
## Verification
Use `make ci-test` as the default full verification command before calling a change done. For focused work, run the smallest relevant target first, then finish with `make ci-test` when generated artifacts, packaging, registry, trust, or report UI changed.
Common focused checks:
- CLI changes: `python3 tests/verify_yao_cli.py`
- Skill overview report changes: `python3 tests/verify_skill_overview.py`
- Review Studio changes: `python3 tests/verify_review_studio.py`
- Trust or script inventory changes: `python3 tests/verify_trust_check.py`
- Packaging or registry changes: `python3 tests/verify_package_verification.py && python3 tests/verify_registry_audit.py`
After source changes that affect scripts, package contents, trust evidence, Review Studio, registry metadata, or generated reports, refresh the release evidence before final sign-off:
```bash
GENERATED_AT="${GENERATED_AT:-$(date +%F)}"
python3 scripts/run_output_execution.py --runner-command '["python3","scripts/local_output_eval_runner.py"]'
python3 scripts/compile_skill.py . --generated-at "$GENERATED_AT"
python3 scripts/cross_packager.py . --platform openai --platform claude --platform generic --expectations evals/packaging_expectations.json --output-dir dist --zip
python3 scripts/simulate_install.py . --package-dir dist --install-root dist/install-simulation --output-json reports/install_simulation.json --output-md reports/install_simulation.md --generated-at "$GENERATED_AT"
python3 scripts/trust_check.py . --output-json reports/security_trust_report.json --output-md reports/security_trust_report.md
python3 scripts/registry_audit.py . --generated-at "$GENERATED_AT"
python3 scripts/verify_package.py . --package-dir dist --expectations evals/packaging_expectations.json --registry-json reports/registry_audit.json --output-json reports/package_verification.json --output-md reports/package_verification.md --require-zip --generated-at "$GENERATED_AT"
python3 scripts/registry_audit.py . --generated-at "$GENERATED_AT"
python3 scripts/upgrade_check.py . --previous-package-json registry/examples/yao-meta-skill-1.0.0.json --current-package-json reports/registry_audit.json --output-json reports/upgrade_check.json --output-md reports/upgrade_check.md --generated-at "$GENERATED_AT"
python3 scripts/render_skill_overview.py .
python3 scripts/render_review_studio.py . --output-html reports/review-studio.html --output-json reports/review-studio.json
```
Clean test-only scratch directories after verification with `rm -rf tests/tmp_*`. Do not clean unrelated untracked files.
## Boundaries
- Do not expand root `SKILL.md` with long method text. Add durable guidance to `references/` or executable behavior to `scripts/`.
- Do not commit private customer work, one-off business skills, or local research reports unless the user explicitly promotes them into examples, fixtures, or public evidence.
- Treat untracked files outside `tests/tmp_*` as user work. Do not delete, move, or overwrite them without explicit approval.
- Do not hand-edit generated evidence when a generator exists. Regenerate the source report instead.
- Do not introduce external chart or UI dependencies for static reports unless the user explicitly approves them. The current report pattern is static HTML, local CSS, and inline SVG.
- Keep package artifacts, registry checksums, install simulation, trust reports, overview reports, and Review Studio evidence in sync after source changes.
## Hotspot Ownership
- `scripts/yao.py`: unified CLI orchestration. Keep command behavior stable; move pure config and side-effect-free helpers into small internal modules.
- `scripts/render_skill_overview.py`: v2 bilingual skill overview report. Preserve `reports/skill-overview.html` / `.json`, `body data-report-lang="zh-CN"`, default Simplified Chinese, English switch, and inline-chart/no-external-dependency behavior.
- `scripts/render_review_studio.py`: Review Studio gate orchestration. Keep gate scoring, evidence links, and action generation separate from layout helpers.
- `scripts/review_studio_layout.py`: Review Studio static layout and CSS contract.
- `scripts/review_studio_formatting.py`: Review Studio dictionary-to-panel formatting and Chinese metric labels.
- `scripts/skill_report_model.py`, `scripts/skill_report_metrics.py`, `scripts/skill_report_charts.py`: skill overview data model, scoring, and inline SVG chart generation.
- `scripts/yao_cli_config.py`: CLI target maps, archetype heuristics, diagnosis copy, and side-effect-free shaping helpers.
New helper modules that are imported by CLI/report scripts but are not standalone commands must declare:
```python
SCRIPT_INTERFACE = "internal-module"
SCRIPT_INTERFACE_REASON = "Imported by <caller> for <purpose>."
```
Then update `tests/verify_trust_check.py` so help-smoke coverage and trust reporting stay explicit.
## Long-Running Work
Stop and surface state instead of retrying when any of these happens:
- Two consecutive checkpoints show no new files, no new passing test, and no new diagnosis.
- The same command fails with the same error three times.
- A required credential, network, package registry, or external service is unavailable.
- A generated package hash, registry checksum, install simulation, or trust summary cannot be reconciled after regeneration.
When stopping, report the exact command, current `git status --short --branch -uall`, and the smallest next diagnostic.
registry/index.json
+1 -1
View File
@@ -15,7 +15,7 @@
"agent-skills-compatible"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe"
"package_sha256": "742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f"
}
]
}
registry/packages/yao-meta-skill.json
+3 -3
View File
@@ -15,8 +15,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe",
"archive_sha256": "4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06"
"package_sha256": "742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f",
"archive_sha256": "7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9"
},
"compatibility": {
"openai": "pass",
@@ -47,7 +47,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06",
"archive_sha256": "7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9",
"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": "2026-06-13T09:57:51Z",
"generated_at": "2026-06-13T10:57:52Z",
"skill_dir": ".",
"privacy_contract": {
"storage": "local-first",
reports/compiled_targets.json
+40 -24
View File
@@ -190,6 +190,8 @@
"scripts/render_social_preview.py",
"scripts/render_system_model.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_layout.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -197,6 +199,7 @@
"scripts/run_output_execution.py",
"scripts/simulate_install.py",
"scripts/skill_report_charts.py",
"scripts/skill_report_layout.py",
"scripts/skill_report_metrics.py",
"scripts/skill_report_model.py",
"scripts/sync_local_install.py",
@@ -205,7 +208,8 @@
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/yao.py",
"scripts/yao_cli_config.py"
],
"assets": [
"templates/basic_skill.md.j2",
@@ -256,7 +260,7 @@
],
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
}
@@ -494,7 +498,7 @@
"strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.",
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
},
@@ -505,7 +509,7 @@
},
"scripts": {
"strategy": "Keep scripts as local package resources; expose help-smoke and permission metadata for reviewer approval before execution.",
"script_count": 62,
"script_count": 66,
"help_smoke_failed_count": 0
},
"permissions": {
@@ -717,7 +721,7 @@
"strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.",
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
},
@@ -728,7 +732,7 @@
},
"scripts": {
"strategy": "Keep scripts as local package resources; expose help-smoke and permission metadata for reviewer approval before execution.",
"script_count": 62,
"script_count": 66,
"help_smoke_failed_count": 0
},
"permissions": {
@@ -975,6 +979,8 @@
"scripts/render_social_preview.py",
"scripts/render_system_model.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_layout.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -982,6 +988,7 @@
"scripts/run_output_execution.py",
"scripts/simulate_install.py",
"scripts/skill_report_charts.py",
"scripts/skill_report_layout.py",
"scripts/skill_report_metrics.py",
"scripts/skill_report_model.py",
"scripts/sync_local_install.py",
@@ -990,7 +997,8 @@
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/yao.py",
"scripts/yao_cli_config.py"
],
"assets": [
"templates/basic_skill.md.j2",
@@ -1041,7 +1049,7 @@
],
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
}
@@ -1279,7 +1287,7 @@
"strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.",
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
},
@@ -1290,7 +1298,7 @@
},
"scripts": {
"strategy": "Scripts remain local package resources and must be reviewed through trust and permission reports before use.",
"script_count": 62,
"script_count": 66,
"help_smoke_failed_count": 0
},
"permissions": {
@@ -1502,7 +1510,7 @@
"strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.",
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
},
@@ -1513,7 +1521,7 @@
},
"scripts": {
"strategy": "Scripts remain local package resources and must be reviewed through trust and permission reports before use.",
"script_count": 62,
"script_count": 66,
"help_smoke_failed_count": 0
},
"permissions": {
@@ -1760,6 +1768,8 @@
"scripts/render_social_preview.py",
"scripts/render_system_model.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_layout.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -1767,6 +1777,7 @@
"scripts/run_output_execution.py",
"scripts/simulate_install.py",
"scripts/skill_report_charts.py",
"scripts/skill_report_layout.py",
"scripts/skill_report_metrics.py",
"scripts/skill_report_model.py",
"scripts/sync_local_install.py",
@@ -1775,7 +1786,8 @@
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/yao.py",
"scripts/yao_cli_config.py"
],
"assets": [
"templates/basic_skill.md.j2",
@@ -1826,7 +1838,7 @@
],
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
}
@@ -2064,7 +2076,7 @@
"strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.",
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
},
@@ -2074,7 +2086,7 @@
},
"scripts": {
"strategy": "Expose script and permission metadata for downstream clients or installers to enforce.",
"script_count": 62,
"script_count": 66,
"help_smoke_failed_count": 0
},
"permissions": {
@@ -2280,7 +2292,7 @@
"strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.",
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
},
@@ -2290,7 +2302,7 @@
},
"scripts": {
"strategy": "Expose script and permission metadata for downstream clients or installers to enforce.",
"script_count": 62,
"script_count": 66,
"help_smoke_failed_count": 0
},
"permissions": {
@@ -2529,6 +2541,8 @@
"scripts/render_social_preview.py",
"scripts/render_system_model.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_layout.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -2536,6 +2550,7 @@
"scripts/run_output_execution.py",
"scripts/simulate_install.py",
"scripts/skill_report_charts.py",
"scripts/skill_report_layout.py",
"scripts/skill_report_metrics.py",
"scripts/skill_report_model.py",
"scripts/sync_local_install.py",
@@ -2544,7 +2559,8 @@
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/yao.py",
"scripts/yao_cli_config.py"
],
"assets": [
"templates/basic_skill.md.j2",
@@ -2595,7 +2611,7 @@
],
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
}
@@ -2833,7 +2849,7 @@
"strategy": "Keep optional directories as relative resources next to SKILL.md.",
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
},
@@ -2844,7 +2860,7 @@
},
"scripts": {
"strategy": "Scripts remain local optional resources and should advertise --help when executable.",
"script_count": 62,
"script_count": 66,
"help_smoke_failed_count": 0
},
"permissions": {
@@ -3049,7 +3065,7 @@
"strategy": "Keep optional directories as relative resources next to SKILL.md.",
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
},
@@ -3060,7 +3076,7 @@
},
"scripts": {
"strategy": "Scripts remain local optional resources and should advertise --help when executable.",
"script_count": 62,
"script_count": 66,
"help_smoke_failed_count": 0
},
"permissions": {
reports/context_budget.json
+3 -3
View File
@@ -6,10 +6,10 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 811,
"other_text_tokens": 864534,
"other_text_tokens": 869504,
"estimated_initial_load_tokens": 987,
"estimated_total_text_tokens": 865345,
"relevant_file_count": 316,
"estimated_total_text_tokens": 870315,
"relevant_file_count": 327,
"unused_resource_dirs": [],
"quality_signal_points": 130,
"quality_density": 131.7
reports/install_simulation.json
+1 -1
View File
@@ -8,7 +8,7 @@
"installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill",
"summary": {
"archive_present": true,
"archive_entry_count": 483,
"archive_entry_count": 488,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
reports/output_execution_runs.json
+10 -10
View File
@@ -34,7 +34,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.22,
"duration_ms": 23.11,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -62,7 +62,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.12,
"duration_ms": 23.56,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -85,7 +85,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.12,
"duration_ms": 24.17,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -113,7 +113,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.03,
"duration_ms": 23.84,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -136,7 +136,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.11,
"duration_ms": 22.51,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -164,7 +164,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.68,
"duration_ms": 26.03,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -187,7 +187,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.07,
"duration_ms": 28.48,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -214,7 +214,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.57,
"duration_ms": 23.17,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -237,7 +237,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 29.2,
"duration_ms": 23.94,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -266,7 +266,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.94,
"duration_ms": 22.69,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
reports/output_execution_runs.md
+10 -10
View File
@@ -23,16 +23,16 @@ Command runner evidence is present. This proves the eval harness executed an ext
| Case | Variant | Mode | Model | Duration ms | Tokens | Score | Status |
| --- | --- | --- | --- | ---: | ---: | ---: | --- |
| skill-package-contract | baseline | command | local-output-eval-runner | 27.22 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 27.12 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 27.12 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 30.03 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 27.11 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 26.68 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 27.07 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 27.57 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 29.2 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.94 | 98 | 100.0 | pass |
| skill-package-contract | baseline | command | local-output-eval-runner | 23.11 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 23.56 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 24.17 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 23.84 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 22.51 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 26.03 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 28.48 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 23.17 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 23.94 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 22.69 | 98 | 100.0 | pass |
## Next Fixes
reports/package_verification.json
+2 -2
View File
@@ -8,8 +8,8 @@
"target_count": 3,
"adapter_count": 3,
"archive_present": true,
"archive_sha256": "4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06",
"archive_entry_count": 483,
"archive_sha256": "7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9",
"archive_entry_count": 488,
"failure_count": 0,
"warning_count": 0
},
reports/package_verification.md
+1 -1
View File
@@ -4,7 +4,7 @@
- Package directory: `dist`
- Targets: `3 / 3` adapters present
- Archive present: `True`
- Archive SHA256: `4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06`
- Archive SHA256: `7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9`
- Failures: `0`
- Warnings: `0`
reports/registry_audit.json
+4 -4
View File
@@ -20,8 +20,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe",
"archive_sha256": "4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06"
"package_sha256": "742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f",
"archive_sha256": "7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9"
},
"compatibility": {
"openai": "pass",
@@ -52,7 +52,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06",
"archive_sha256": "7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -76,7 +76,7 @@
"agent-skills-compatible"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe"
"package_sha256": "742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f"
}
]
},
reports/registry_audit.md
+2 -2
View File
@@ -6,8 +6,8 @@
- Maturity: `governed`
- Owner: `Yao Team`
- License: `MIT`
- Package SHA256: `9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe`
- Archive SHA256: `4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06`
- Package SHA256: `742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f`
- Archive SHA256: `7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9`
- Install simulated: `True`
## Compatibility
reports/review-studio.html
+38 -17
View File
@@ -5,7 +5,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>Yao Meta Skill Review Studio 2.0</title>
<style>
:root {
:root {
--ink: #1B365D;
--text: #24201d;
--muted: #746d66;
@@ -102,6 +102,27 @@
background: #fff;
}
.panel p { color: var(--muted); }
.kv-grid {
display: grid;
grid-template-columns: repeat(2, minmax(0, 1fr));
gap: 10px 12px;
margin: 2px 0 0;
}
.kv-grid div {
min-width: 0;
padding: 9px 0 0;
border-top: 1px solid var(--line);
}
.kv-grid dt {
color: var(--muted);
font-size: 13px;
}
.kv-grid dd {
margin: 2px 0 0;
color: var(--ink);
font-size: 15px;
overflow-wrap: anywhere;
}
.issues, .evidence {
list-style: none;
padding: 0;
@@ -198,7 +219,7 @@
font-size: 13px;
}
@media (max-width: 980px) {
.metrics, .gates, .twocol, .actions-grid, .annotations-grid { grid-template-columns: 1fr; }
.metrics, .gates, .twocol, .actions-grid, .annotations-grid, .kv-grid { grid-template-columns: 1fr; }
main { padding: 32px 18px 60px; }
nav { justify-content: flex-start; overflow-x: auto; flex-wrap: nowrap; }
nav a { flex: 0 0 auto; }
@@ -221,12 +242,12 @@
<section>
<h2>核心指标</h2>
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>4 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>4/4</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>3/3</strong><p>0 native enforcement targets</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>62 scripts scanned; secrets found</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>4 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>483 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>3 adapters readable; local install simulation</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>4 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>4/4</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>3/3</strong><p>0 native enforcement targets</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>66 scripts scanned; secrets found</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>4 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>488 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>3 adapters readable; local install simulation</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
</section>
<section>
<h2>审查闸门</h2>
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 987/1000; quality density 131.7</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 62 scripts; 2 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>3/3 targets probed; native 0; metadata fallback 3; residual risks 3</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low</p><footer>reports/adoption_drift_report.json <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>人工批准</h3></div><p>0 active waivers cover current warnings</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 3 adapters</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 987/1000; quality density 131.7</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 66 scripts; 2 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>3/3 targets probed; native 0; metadata fallback 3; residual risks 3</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low</p><footer>reports/adoption_drift_report.json <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>人工批准</h3></div><p>0 active waivers cover current warnings</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 3 adapters</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
</section>
<div class="twocol">
@@ -258,17 +279,17 @@
<section id="trigger" class="twocol">
<div class="panel"><h2>触发实验</h2><p>13 trigger cases; 0 misroutes; 0 ambiguous</p></div>
<div class="panel"><h2>组合治理</h2><p>{&#x27;skill_count&#x27;: 12, &#x27;actionable_skill_count&#x27;: 1, &#x27;route_collision_count&#x27;: 5, &#x27;actionable_route_collision_count&#x27;: 0, &#x27;owner_gap_count&#x27;: 9, &#x27;actionable_owner_gap_count&#x27;: 0, &#x27;stale_count&#x27;: 10, &#x27;actionable_stale_count&#x27;: 0, &#x27;shared_resource_count&#x27;: 0, &#x27;no_route_opportunity_count&#x27;: 0, &#x27;non_actionable_issue_count&#x27;: 24}</p></div>
<div class="panel"><h2>组合治理</h2><dl class='kv-grid'><div><dt>Skill 数</dt><dd>12</dd></div><div><dt>纳入审查</dt><dd>1</dd></div><div><dt>待处理冲突</dt><dd>0</dd></div><div><dt>待处理 owner</dt><dd>0</dd></div><div><dt>待处理过期</dt><dd>0</dd></div><div><dt>非行动项</dt><dd>24</dd></div></dl></div>
</section>
<section id="output" class="twocol">
<div class="panel"><h2>输出实验</h2><p>{&#x27;case_count&#x27;: 5, &#x27;file_backed_case_count&#x27;: 1, &#x27;near_neighbor_case_count&#x27;: 1, &#x27;boundary_case_count&#x27;: 1, &#x27;baseline_pass_rate&#x27;: 0.0, &#x27;with_skill_pass_rate&#x27;: 100.0, &#x27;delta&#x27;: 100.0, &#x27;regression_count&#x27;: 0, &#x27;gate_pass&#x27;: True, &#x27;failure_taxonomy&#x27;: [], &#x27;blind_pair_count&#x27;: 5}</p></div>
<div class="panel"><h2>执行证据</h2><p>{&#x27;case_count&#x27;: 5, &#x27;variant_run_count&#x27;: 10, &#x27;command_executed_count&#x27;: 10, &#x27;model_executed_count&#x27;: 0, &#x27;recorded_fixture_count&#x27;: 0, &#x27;timing_observed_count&#x27;: 10, &#x27;token_observed_count&#x27;: 0, &#x27;token_estimated_count&#x27;: 10, &#x27;baseline_pass_rate&#x27;: 0.0, &#x27;with_skill_pass_rate&#x27;: 100.0, &#x27;delta&#x27;: 100.0, &#x27;regression_count&#x27;: 0, &#x27;failure_count&#x27;: 0, &#x27;gate_pass&#x27;: True}</p></div>
<div class="panel"><h2>输出实验</h2><dl class='kv-grid'><div><dt>案例数</dt><dd>5</dd></div><div><dt>With Skill</dt><dd>100</dd></div><div><dt>Baseline</dt><dd>0</dd></div><div><dt>增益</dt><dd>100</dd></div><div><dt>Gate</dt><dd>是</dd></div></dl></div>
<div class="panel"><h2>执行证据</h2><dl class='kv-grid'><div><dt>运行数</dt><dd>10</dd></div><div><dt>命令执行</dt><dd>10</dd></div><div><dt>模型执行</dt><dd>0</dd></div><div><dt>记录样本</dt><dd>0</dd></div><div><dt>计时样本</dt><dd>10</dd></div><div><dt>估算 Token</dt><dd>10</dd></div></dl></div>
</section>
<section class="twocol">
<div class="panel"><h2>盲评包</h2><p>{&#x27;pair_count&#x27;: 5, &#x27;answer_key_separate&#x27;: True, &#x27;with_skill_hidden_count&#x27;: 5}</p></div>
<div class="panel"><h2>审定报告</h2><p>{&#x27;pair_count&#x27;: 5, &#x27;judgment_count&#x27;: 0, &#x27;pending_count&#x27;: 5, &#x27;agreement_count&#x27;: 0, &#x27;disagreement_count&#x27;: 0, &#x27;invalid_decision_count&#x27;: 0, &#x27;agreement_rate&#x27;: None, &#x27;needs_review&#x27;: True, &#x27;failure_count&#x27;: 0}</p></div>
<div class="panel"><h2>盲评包</h2><dl class='kv-grid'><div><dt>Pair Count</dt><dd>5</dd></div><div><dt>Answer Key Separate</dt><dd>是</dd></div><div><dt>With Skill Hidden Count</dt><dd>5</dd></div></dl></div>
<div class="panel"><h2>审定报告</h2><dl class='kv-grid'><div><dt>Pair Count</dt><dd>5</dd></div><div><dt>Judgment Count</dt><dd>0</dd></div><div><dt>待审</dt><dd>5</dd></div><div><dt>Agreement Count</dt><dd>0</dd></div><div><dt>Disagreement Count</dt><dd>0</dd></div><div><dt>Invalid Decision Count</dt><dd>0</dd></div></dl></div>
</section>
<section class="twocol">
@@ -282,8 +303,8 @@
</section>
<section id="runtime" class="twocol">
<div class="panel"><h2>运行矩阵</h2><p>{&#x27;target_count&#x27;: 5, &#x27;pass_count&#x27;: 5, &#x27;fail_count&#x27;: 0}</p></div>
<div class="panel"><h2>目标编译</h2><p>{&#x27;target_count&#x27;: 4, &#x27;pass_count&#x27;: 4, &#x27;warn_count&#x27;: 0, &#x27;block_count&#x27;: 0, &#x27;failure_count&#x27;: 0, &#x27;warning_count&#x27;: 0}</p></div>
<div class="panel"><h2>运行矩阵</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>5</dd></div><div><dt>通过数</dt><dd>5</dd></div><div><dt>Fail Count</dt><dd>0</dd></div></dl></div>
<div class="panel"><h2>目标编译</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>通过数</dt><dd>4</dd></div><div><dt>Warn Count</dt><dd>0</dd></div><div><dt>Block Count</dt><dd>0</dd></div><div><dt>失败数</dt><dd>0</dd></div></dl></div>
</section>
<section class="twocol">
@@ -292,7 +313,7 @@
</section>
<section id="trust" class="twocol">
<div class="panel"><h2>信任报告</h2><p>{&#x27;scanned_files&#x27;: 146, &#x27;script_count&#x27;: 62, &#x27;internal_module_count&#x27;: 3, &#x27;secret_findings&#x27;: 0, &#x27;dependency_files&#x27;: [&#x27;requirements-ci.txt&#x27;], &#x27;network_script_count&#x27;: 2, &#x27;network_policy_covered_count&#x27;: 2, &#x27;network_policy_missing_count&#x27;: 0, &#x27;file_write_script_count&#x27;: 47, &#x27;permission_required_count&#x27;: 3, &#x27;permission_approved_count&#x27;: 3, &#x27;permission_missing_count&#x27;: 0, &#x27;permission_invalid_count&#x27;: 0, &#x27;permission_expired_count&#x27;: 0, &#x27;help_smoke_checked_count&#x27;: 59, &#x27;help_smoke_failed_count&#x27;: 0, &#x27;interactive_script_count&#x27;: 0, &#x27;package_hash_scope&#x27;: &#x27;source-contract-without-generated-reports&#x27;, &#x27;package_hash_file_count&#x27;: 146, &#x27;package_sha256&#x27;: &#x27;9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe&#x27;}</p></div>
<div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>66</dd></div><div><dt>网络脚本</dt><dd>2</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f</code></dd></div></dl></div>
<div class="panel"><h2>安全边界</h2><p>高风险 secret、远程 inline execution、缺失依赖策略或无法解释的脚本接口应阻断 governed release。</p></div>
</section>
@@ -303,7 +324,7 @@
<section id="permission-probes" class="twocol">
<div class="panel"><h2>权限探针</h2><p>3/3 targets probed; native 0; metadata fallback 3; residual risks 3</p></div>
<div class="panel"><h2>运行边界</h2><p>{&#x27;target_count&#x27;: 3, &#x27;pass_count&#x27;: 3, &#x27;fail_count&#x27;: 0, &#x27;native_enforcement_count&#x27;: 0, &#x27;metadata_fallback_count&#x27;: 3, &#x27;residual_risk_count&#x27;: 3, &#x27;required_capability_count&#x27;: 3, &#x27;failure_count&#x27;: 0}</p></div>
<div class="panel"><h2>运行边界</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>3</dd></div><div><dt>通过数</dt><dd>3</dd></div><div><dt>原生执行</dt><dd>0</dd></div><div><dt>Metadata fallback</dt><dd>3</dd></div><div><dt>残余风险</dt><dd>3</dd></div><div><dt>失败数</dt><dd>0</dd></div></dl></div>
</section>
<section id="atlas" class="twocol">
@@ -313,22 +334,22 @@
<section id="telemetry" class="twocol">
<div class="panel"><h2>运营回路</h2><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low</p></div>
<div class="panel"><h2>漂移信号</h2><p>{&#x27;event_count&#x27;: 1, &#x27;activation_count&#x27;: 1, &#x27;accepted_count&#x27;: 1, &#x27;edited_count&#x27;: 0, &#x27;rejected_count&#x27;: 0, &#x27;missed_count&#x27;: 0, &#x27;failed_count&#x27;: 0, &#x27;adoption_rate&#x27;: 100.0, &#x27;missed_trigger_count&#x27;: 0, &#x27;wrong_trigger_count&#x27;: 0, &#x27;bad_output_count&#x27;: 0, &#x27;script_error_count&#x27;: 0, &#x27;missing_resource_count&#x27;: 0, &#x27;review_overdue_count&#x27;: 0, &#x27;risk_band&#x27;: &#x27;low&#x27;, &#x27;event_types&#x27;: {&#x27;skill_activation&#x27;: 1}, &#x27;failure_types&#x27;: {}}</p></div>
<div class="panel"><h2>漂移信号</h2><dl class='kv-grid'><div><dt>事件数</dt><dd>1</dd></div><div><dt>采用率</dt><dd>100</dd></div><div><dt>漏触发</dt><dd>0</dd></div><div><dt>Bad Output Count</dt><dd>0</dd></div><div><dt>风险带</dt><dd>low</dd></div></dl></div>
</section>
<section id="waivers" class="twocol">
<div class="panel"><h2>人工批准</h2><p>0 active waivers cover current warnings</p></div>
<div class="panel"><h2>批准台账</h2><p>{&#x27;waiver_count&#x27;: 0, &#x27;active_count&#x27;: 0, &#x27;expired_count&#x27;: 0, &#x27;invalid_count&#x27;: 0, &#x27;covered_gate_count&#x27;: 0, &#x27;covered_gate_keys&#x27;: []}</p></div>
<div class="panel"><h2>批准台账</h2><dl class='kv-grid'><div><dt>Waiver Count</dt><dd>0</dd></div><div><dt>Active Count</dt><dd>0</dd></div><div><dt>Expired Count</dt><dd>0</dd></div><div><dt>Invalid Count</dt><dd>0</dd></div><div><dt>覆盖 Gate</dt><dd>0</dd></div></dl></div>
</section>
<section id="registry" class="twocol">
<div class="panel"><h2>注册审计</h2><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 3 adapters</p></div>
<div class="panel"><h2>包体元数据</h2><p>{&#x27;schema_version&#x27;: &#x27;2.0&#x27;, &#x27;name&#x27;: &#x27;yao-meta-skill&#x27;, &#x27;version&#x27;: &#x27;1.1.0&#x27;, &#x27;description&#x27;: &#x27;Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.&#x27;, &#x27;targets&#x27;: [&#x27;openai&#x27;, &#x27;claude&#x27;, &#x27;generic&#x27;, &#x27;agent-skills-compatible&#x27;], &#x27;maturity&#x27;: &#x27;governed&#x27;, &#x27;owner&#x27;: &#x27;Yao Team&#x27;, &#x27;review_cadence&#x27;: &#x27;quarterly&#x27;, &#x27;trust_level&#x27;: &#x27;local&#x27;, &#x27;license&#x27;: &#x27;MIT&#x27;, &#x27;checksums&#x27;: {&#x27;package_sha256&#x27;: &#x27;9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe&#x27;, &#x27;archive_sha256&#x27;: &#x27;4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06&#x27;}, &#x27;compatibility&#x27;: {&#x27;openai&#x27;: &#x27;pass&#x27;, &#x27;claude&#x27;: &#x27;pass&#x27;, &#x27;agent-skills&#x27;: &#x27;pass&#x27;, &#x27;vscode&#x27;: &#x27;pass&#x27;, &#x27;generic&#x27;: &#x27;pass&#x27;, &#x27;agent-skills-compatible&#x27;: &#x27;pass&#x27;}, &#x27;source&#x27;: {&#x27;skill_dir&#x27;: &#x27;.&#x27;, &#x27;skill_ir&#x27;: &#x27;skill-ir/examples/yao-meta-skill.json&#x27;, &#x27;ir_schema_version&#x27;: &#x27;2.0.0&#x27;, &#x27;canonical_metadata&#x27;: &#x27;agents/interface.yaml&#x27;}, &#x27;artifacts&#x27;: {&#x27;overview_html&#x27;: &#x27;reports/skill-overview.html&#x27;, &#x27;review_studio_html&#x27;: &#x27;reports/review-studio.html&#x27;, &#x27;trust_report&#x27;: &#x27;reports/security_trust_report.md&#x27;, &#x27;conformance_matrix&#x27;: &#x27;reports/conformance_matrix.md&#x27;, &#x27;compiled_targets&#x27;: &#x27;reports/compiled_targets.md&#x27;, &#x27;package_verification&#x27;: &#x27;reports/package_verification.md&#x27;, &#x27;install_simulation&#x27;: &#x27;reports/install_simulation.md&#x27;, &#x27;adoption_drift&#x27;: &#x27;reports/adoption_drift_report.md&#x27;, &#x27;review_waivers&#x27;: &#x27;reports/review_waivers.md&#x27;, &#x27;review_annotations&#x27;: &#x27;reports/review_annotations.md&#x27;, &#x27;package_metadata&#x27;: &#x27;registry/packages/yao-meta-skill.json&#x27;}, &#x27;distribution&#x27;: {&#x27;archive_verified&#x27;: True, &#x27;archive_sha256&#x27;: &#x27;4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06&#x27;, &#x27;package_verification&#x27;: &#x27;reports/package_verification.json&#x27;, &#x27;install_simulated&#x27;: True, &#x27;install_simulation&#x27;: &#x27;reports/install_simulation.json&#x27;}, &#x27;generated_at&#x27;: &#x27;2026-06-13&#x27;}</p></div>
<div class="panel"><h2>包体元数据</h2><dl class='kv-grid'><div><dt>名称</dt><dd>yao-meta-skill</dd></div><div><dt>版本</dt><dd>1.1.0</dd></div><div><dt>Maturity</dt><dd>governed</dd></div><div><dt>Owner</dt><dd>Yao Team</dd></div><div><dt>License</dt><dd>MIT</dd></div><div><dt>信任级别</dt><dd>local</dd></div><div><dt>目标平台</dt><dd>openai, claude, generic, agent-skills-compatible</dd></div><div><dt>兼容通过</dt><dd>6/6</dd></div><div><dt>归档哈希</dt><dd><code>7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9</code></dd></div></dl></div>
</section>
<section id="release" class="twocol">
<div class="panel"><h2>发布路线</h2><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p></div>
<div class="panel"><h2>包体验证</h2><p>{&#x27;target_count&#x27;: 3, &#x27;adapter_count&#x27;: 3, &#x27;archive_present&#x27;: True, &#x27;archive_sha256&#x27;: &#x27;4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06&#x27;, &#x27;archive_entry_count&#x27;: 483, &#x27;failure_count&#x27;: 0, &#x27;warning_count&#x27;: 0}</p></div>
<div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>3</dd></div><div><dt>Adapter</dt><dd>3</dd></div><div><dt>归档存在</dt><dd>是</dd></div><div><dt>Zip 条目</dt><dd>488</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9</code></dd></div></dl></div>
</section>
</main>
</body>
reports/review-studio.json
+163 -71
View File
@@ -59,7 +59,7 @@
"key": "trust-report",
"label": "信任报告",
"status": "pass",
"detail": "0 secrets; 62 scripts; 2 network-capable scripts; 0 help smoke failures",
"detail": "0 secrets; 66 scripts; 2 network-capable scripts; 0 help smoke failures",
"evidence": "reports/security_trust_report.json",
"link": "security_trust_report.md"
},
@@ -581,7 +581,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 62
"file_count": 66
},
{
"path": "evals",
@@ -596,7 +596,7 @@
"file_count": 170
}
],
"file_count": 296,
"file_count": 300,
"folder_count": 4,
"distribution": [
{
@@ -621,7 +621,7 @@
},
{
"label": "scripts",
"value": 62
"value": 66
},
{
"label": "evals",
@@ -750,7 +750,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 62
"file_count": 66
},
{
"path": "evals",
@@ -1068,9 +1068,9 @@
"failures": []
},
"trust_security": {
"scanned_files": 146,
"script_count": 62,
"internal_module_count": 3,
"scanned_files": 150,
"script_count": 66,
"internal_module_count": 7,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -1088,8 +1088,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 146,
"package_sha256": "9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe"
"package_hash_file_count": 150,
"package_sha256": "742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f"
},
"skill_atlas": {
"skill_count": 12,
@@ -1123,8 +1123,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe",
"archive_sha256": "4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06"
"package_sha256": "742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f",
"archive_sha256": "7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9"
},
"compatibility": {
"openai": "pass",
@@ -1155,7 +1155,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06",
"archive_sha256": "7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1171,8 +1171,8 @@
"target_count": 3,
"adapter_count": 3,
"archive_present": true,
"archive_sha256": "4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06",
"archive_entry_count": 483,
"archive_sha256": "7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9",
"archive_entry_count": 488,
"failure_count": 0,
"warning_count": 0
},
@@ -1183,7 +1183,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 483,
"archive_entry_count": 488,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1245,12 +1245,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06"
"to": "7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe"
"to": "742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f"
}
]
},
@@ -2978,7 +2978,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.22,
"duration_ms": 23.11,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3006,7 +3006,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.12,
"duration_ms": 23.56,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3029,7 +3029,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.12,
"duration_ms": 24.17,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3057,7 +3057,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.03,
"duration_ms": 23.84,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3080,7 +3080,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.11,
"duration_ms": 22.51,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3108,7 +3108,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.68,
"duration_ms": 26.03,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3131,7 +3131,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.07,
"duration_ms": 28.48,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3158,7 +3158,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.57,
"duration_ms": 23.17,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3181,7 +3181,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 29.2,
"duration_ms": 23.94,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3210,7 +3210,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.94,
"duration_ms": 22.69,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3702,6 +3702,8 @@
"scripts/render_social_preview.py",
"scripts/render_system_model.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_layout.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -3709,6 +3711,7 @@
"scripts/run_output_execution.py",
"scripts/simulate_install.py",
"scripts/skill_report_charts.py",
"scripts/skill_report_layout.py",
"scripts/skill_report_metrics.py",
"scripts/skill_report_model.py",
"scripts/sync_local_install.py",
@@ -3717,7 +3720,8 @@
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/yao.py",
"scripts/yao_cli_config.py"
],
"assets": [
"templates/basic_skill.md.j2",
@@ -3768,7 +3772,7 @@
],
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
}
@@ -4006,7 +4010,7 @@
"strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.",
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
},
@@ -4017,7 +4021,7 @@
},
"scripts": {
"strategy": "Keep scripts as local package resources; expose help-smoke and permission metadata for reviewer approval before execution.",
"script_count": 62,
"script_count": 66,
"help_smoke_failed_count": 0
},
"permissions": {
@@ -4229,7 +4233,7 @@
"strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.",
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
},
@@ -4240,7 +4244,7 @@
},
"scripts": {
"strategy": "Keep scripts as local package resources; expose help-smoke and permission metadata for reviewer approval before execution.",
"script_count": 62,
"script_count": 66,
"help_smoke_failed_count": 0
},
"permissions": {
@@ -4487,6 +4491,8 @@
"scripts/render_social_preview.py",
"scripts/render_system_model.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_layout.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -4494,6 +4500,7 @@
"scripts/run_output_execution.py",
"scripts/simulate_install.py",
"scripts/skill_report_charts.py",
"scripts/skill_report_layout.py",
"scripts/skill_report_metrics.py",
"scripts/skill_report_model.py",
"scripts/sync_local_install.py",
@@ -4502,7 +4509,8 @@
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/yao.py",
"scripts/yao_cli_config.py"
],
"assets": [
"templates/basic_skill.md.j2",
@@ -4553,7 +4561,7 @@
],
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
}
@@ -4791,7 +4799,7 @@
"strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.",
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
},
@@ -4802,7 +4810,7 @@
},
"scripts": {
"strategy": "Scripts remain local package resources and must be reviewed through trust and permission reports before use.",
"script_count": 62,
"script_count": 66,
"help_smoke_failed_count": 0
},
"permissions": {
@@ -5014,7 +5022,7 @@
"strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.",
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
},
@@ -5025,7 +5033,7 @@
},
"scripts": {
"strategy": "Scripts remain local package resources and must be reviewed through trust and permission reports before use.",
"script_count": 62,
"script_count": 66,
"help_smoke_failed_count": 0
},
"permissions": {
@@ -5272,6 +5280,8 @@
"scripts/render_social_preview.py",
"scripts/render_system_model.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_layout.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -5279,6 +5289,7 @@
"scripts/run_output_execution.py",
"scripts/simulate_install.py",
"scripts/skill_report_charts.py",
"scripts/skill_report_layout.py",
"scripts/skill_report_metrics.py",
"scripts/skill_report_model.py",
"scripts/sync_local_install.py",
@@ -5287,7 +5298,8 @@
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/yao.py",
"scripts/yao_cli_config.py"
],
"assets": [
"templates/basic_skill.md.j2",
@@ -5338,7 +5350,7 @@
],
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
}
@@ -5576,7 +5588,7 @@
"strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.",
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
},
@@ -5586,7 +5598,7 @@
},
"scripts": {
"strategy": "Expose script and permission metadata for downstream clients or installers to enforce.",
"script_count": 62,
"script_count": 66,
"help_smoke_failed_count": 0
},
"permissions": {
@@ -5792,7 +5804,7 @@
"strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.",
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
},
@@ -5802,7 +5814,7 @@
},
"scripts": {
"strategy": "Expose script and permission metadata for downstream clients or installers to enforce.",
"script_count": 62,
"script_count": 66,
"help_smoke_failed_count": 0
},
"permissions": {
@@ -6041,6 +6053,8 @@
"scripts/render_social_preview.py",
"scripts/render_system_model.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_layout.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -6048,6 +6062,7 @@
"scripts/run_output_execution.py",
"scripts/simulate_install.py",
"scripts/skill_report_charts.py",
"scripts/skill_report_layout.py",
"scripts/skill_report_metrics.py",
"scripts/skill_report_model.py",
"scripts/sync_local_install.py",
@@ -6056,7 +6071,8 @@
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/yao.py",
"scripts/yao_cli_config.py"
],
"assets": [
"templates/basic_skill.md.j2",
@@ -6107,7 +6123,7 @@
],
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
}
@@ -6345,7 +6361,7 @@
"strategy": "Keep optional directories as relative resources next to SKILL.md.",
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
},
@@ -6356,7 +6372,7 @@
},
"scripts": {
"strategy": "Scripts remain local optional resources and should advertise --help when executable.",
"script_count": 62,
"script_count": 66,
"help_smoke_failed_count": 0
},
"permissions": {
@@ -6561,7 +6577,7 @@
"strategy": "Keep optional directories as relative resources next to SKILL.md.",
"counts": {
"references": 32,
"scripts": 62,
"scripts": 66,
"assets": 2,
"reports": 41
},
@@ -6572,7 +6588,7 @@
},
"scripts": {
"strategy": "Scripts remain local optional resources and should advertise --help when executable.",
"script_count": 62,
"script_count": 66,
"help_smoke_failed_count": 0
},
"permissions": {
@@ -7136,9 +7152,9 @@
"ok": true,
"skill_dir": ".",
"summary": {
"scanned_files": 146,
"script_count": 62,
"internal_module_count": 3,
"scanned_files": 150,
"script_count": 66,
"internal_module_count": 7,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -7156,8 +7172,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 146,
"package_sha256": "9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe"
"package_hash_file_count": 150,
"package_sha256": "742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f"
},
"failures": [],
"warnings": [],
@@ -7820,6 +7836,34 @@
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/review_studio_formatting.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by render_review_studio.py to format report dictionaries as audit UI panels.",
"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_layout.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by render_review_studio.py to keep Review Studio layout and CSS out of gate logic.",
"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",
@@ -7918,6 +7962,20 @@
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/skill_report_layout.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by render_skill_overview.py to keep overview report layout and CSS out of data rendering.",
"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/skill_report_metrics.py",
"interface": "internal-module",
@@ -8043,6 +8101,20 @@
"uses_subprocess": true,
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/yao_cli_config.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by yao.py for CLI target maps and side-effect-free shaping helpers.",
"has_argparse": false,
"has_main_guard": false,
"uses_input": false,
"uses_network": false,
"uses_file_write": false,
"uses_subprocess": false,
"network_urls": [],
"network_hosts": []
}
],
"dependencies": {
@@ -8078,7 +8150,7 @@
"checked_count": 59,
"passed_count": 59,
"failed_count": 0,
"skipped_count": 3,
"skipped_count": 7,
"failed_scripts": [],
"results": [
{
@@ -8673,10 +8745,22 @@
}
],
"skipped": [
{
"path": "scripts/review_studio_formatting.py",
"reason": "internal module"
},
{
"path": "scripts/review_studio_layout.py",
"reason": "internal module"
},
{
"path": "scripts/skill_report_charts.py",
"reason": "internal module"
},
{
"path": "scripts/skill_report_layout.py",
"reason": "internal module"
},
{
"path": "scripts/skill_report_metrics.py",
"reason": "internal module"
@@ -8684,6 +8768,10 @@
{
"path": "scripts/skill_report_model.py",
"reason": "internal module"
},
{
"path": "scripts/yao_cli_config.py",
"reason": "internal module"
}
]
},
@@ -8848,10 +8936,10 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 811,
"other_text_tokens": 864534,
"other_text_tokens": 869504,
"estimated_initial_load_tokens": 987,
"estimated_total_text_tokens": 865345,
"relevant_file_count": 316,
"estimated_total_text_tokens": 870315,
"relevant_file_count": 327,
"unused_resource_dirs": [],
"quality_signal_points": 130,
"quality_density": 131.7
@@ -9757,6 +9845,8 @@
"scripts/render_social_preview.py",
"scripts/render_system_model.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_layout.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -9764,6 +9854,7 @@
"scripts/run_output_execution.py",
"scripts/simulate_install.py",
"scripts/skill_report_charts.py",
"scripts/skill_report_layout.py",
"scripts/skill_report_metrics.py",
"scripts/skill_report_model.py",
"scripts/sync_local_install.py",
@@ -9773,6 +9864,7 @@
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py",
"scripts/yao_cli_config.py",
"references/artifact-design-doctrine.md",
"references/authoring-discipline.md",
"references/distribution-registry-method.md",
@@ -10554,7 +10646,7 @@
"adoption_drift": {
"ok": true,
"schema_version": "2.0",
"generated_at": "2026-06-13T09:57:51Z",
"generated_at": "2026-06-13T10:57:52Z",
"skill_dir": ".",
"privacy_contract": {
"storage": "local-first",
@@ -10713,8 +10805,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe",
"archive_sha256": "4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06"
"package_sha256": "742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f",
"archive_sha256": "7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9"
},
"compatibility": {
"openai": "pass",
@@ -10745,7 +10837,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06",
"archive_sha256": "7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -10769,7 +10861,7 @@
"agent-skills-compatible"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe"
"package_sha256": "742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f"
}
]
},
@@ -10792,8 +10884,8 @@
"target_count": 3,
"adapter_count": 3,
"archive_present": true,
"archive_sha256": "4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06",
"archive_entry_count": 483,
"archive_sha256": "7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9",
"archive_entry_count": 488,
"failure_count": 0,
"warning_count": 0
},
@@ -11308,7 +11400,7 @@
"installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill",
"summary": {
"archive_present": true,
"archive_entry_count": 483,
"archive_entry_count": 488,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -11489,12 +11581,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06"
"to": "7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe"
"to": "742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f"
}
]
},
reports/security_trust_report.json
+78 -6
View File
@@ -2,9 +2,9 @@
"ok": true,
"skill_dir": ".",
"summary": {
"scanned_files": 146,
"script_count": 62,
"internal_module_count": 3,
"scanned_files": 150,
"script_count": 66,
"internal_module_count": 7,
"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": 146,
"package_sha256": "9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe"
"package_hash_file_count": 150,
"package_sha256": "742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f"
},
"failures": [],
"warnings": [],
@@ -686,6 +686,34 @@
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/review_studio_formatting.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by render_review_studio.py to format report dictionaries as audit UI panels.",
"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_layout.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by render_review_studio.py to keep Review Studio layout and CSS out of gate logic.",
"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",
@@ -784,6 +812,20 @@
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/skill_report_layout.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by render_skill_overview.py to keep overview report layout and CSS out of data rendering.",
"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/skill_report_metrics.py",
"interface": "internal-module",
@@ -909,6 +951,20 @@
"uses_subprocess": true,
"network_urls": [],
"network_hosts": []
},
{
"path": "scripts/yao_cli_config.py",
"interface": "internal-module",
"interface_declared": true,
"interface_reason": "Imported by yao.py for CLI target maps and side-effect-free shaping helpers.",
"has_argparse": false,
"has_main_guard": false,
"uses_input": false,
"uses_network": false,
"uses_file_write": false,
"uses_subprocess": false,
"network_urls": [],
"network_hosts": []
}
],
"dependencies": {
@@ -944,7 +1000,7 @@
"checked_count": 59,
"passed_count": 59,
"failed_count": 0,
"skipped_count": 3,
"skipped_count": 7,
"failed_scripts": [],
"results": [
{
@@ -1539,10 +1595,22 @@
}
],
"skipped": [
{
"path": "scripts/review_studio_formatting.py",
"reason": "internal module"
},
{
"path": "scripts/review_studio_layout.py",
"reason": "internal module"
},
{
"path": "scripts/skill_report_charts.py",
"reason": "internal module"
},
{
"path": "scripts/skill_report_layout.py",
"reason": "internal module"
},
{
"path": "scripts/skill_report_metrics.py",
"reason": "internal module"
@@ -1550,6 +1618,10 @@
{
"path": "scripts/skill_report_model.py",
"reason": "internal module"
},
{
"path": "scripts/yao_cli_config.py",
"reason": "internal module"
}
]
},
reports/security_trust_report.md
+9 -5
View File
@@ -1,9 +1,9 @@
# Security Trust Report
- OK: `True`
- Scanned files: `146`
- Scripts: `62`
- Internal script modules: `3`
- Scanned files: `150`
- Scripts: `66`
- Internal script modules: `7`
- Secret findings: `0`
- Network-capable scripts: `2`
- Network policy covered scripts: `2`
@@ -15,8 +15,8 @@
- CLI help smoke failures: `0`
- Interactive scripts: `0`
- Package hash scope: `source-contract-without-generated-reports`
- Package hash files: `146`
- Package SHA256: `9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe`
- Package hash files: `150`
- Package SHA256: `742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f`
## Failures
@@ -108,6 +108,8 @@
| scripts/render_social_preview.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/render_system_model.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_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_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/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. |
@@ -115,6 +117,7 @@
| scripts/run_output_execution.py | cli | False | True | True | False | False | True | True | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/simulate_install.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/skill_report_charts.py | internal-module | True | False | False | False | False | False | False | Imported by render_skill_overview.py to render inline SVG report charts. |
| scripts/skill_report_layout.py | internal-module | True | False | False | False | False | False | False | Imported by render_skill_overview.py to keep overview report layout and CSS out of data rendering. |
| scripts/skill_report_metrics.py | internal-module | True | False | False | False | False | False | False | Imported by skill_report_model.py to calculate overview report metrics. |
| scripts/skill_report_model.py | internal-module | True | False | False | False | False | False | False | Imported by render_skill_overview.py to build the v2 report data model. |
| scripts/sync_local_install.py | cli | False | True | True | False | False | True | True | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
@@ -124,3 +127,4 @@
| scripts/validate_skill.py | cli | False | True | True | False | False | False | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/verify_package.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/yao.py | cli | False | True | True | False | False | False | True | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
| scripts/yao_cli_config.py | internal-module | True | False | False | False | False | False | False | Imported by yao.py for CLI target maps and side-effect-free shaping helpers. |
reports/skill-overview.html
+3 -3
View File
@@ -5,7 +5,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>yao-meta-skill Skill 生成审计报告</title>
<style>
:root {
:root {
--paper: #ffffff;
--wash: #f8fafc;
--wash-strong: #f2f5f8;
@@ -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="1.0 99.0" 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="1.0 99.0" stroke-dashoffset="-1.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="1.0 99.0" stroke-dashoffset="-2.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="1.0 99.0" stroke-dashoffset="-3.1" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="32.7 67.3" stroke-dashoffset="-4.1" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="63.3 36.7" stroke-dashoffset="-36.7" pathLength="100" transform="rotate(-90 130 130)"/><text x="130" y="136" text-anchor="middle">296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="1.0 99.0" 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="1.0 99.0" stroke-dashoffset="-1.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="1.0 99.0" stroke-dashoffset="-2.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="1.0 99.0" stroke-dashoffset="-2.9" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="31.4 68.6" stroke-dashoffset="-3.9" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="64.7 35.3" stroke-dashoffset="-35.3" pathLength="100" transform="rotate(-90 130 130)"/><text x="130" y="136" text-anchor="middle">300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>
@@ -794,7 +794,7 @@
</section>
</main>
<script>
(function () {
(function () {
var buttons = Array.prototype.slice.call(document.querySelectorAll("[data-set-lang]"));
var navLinks = Array.prototype.slice.call(document.querySelectorAll(".report-nav a"));
var sections = navLinks
reports/skill-overview.json
+17 -17
View File
@@ -433,7 +433,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 62
"file_count": 66
},
{
"path": "evals",
@@ -448,7 +448,7 @@
"file_count": 170
}
],
"file_count": 296,
"file_count": 300,
"folder_count": 4,
"distribution": [
{
@@ -473,7 +473,7 @@
},
{
"label": "scripts",
"value": 62
"value": 66
},
{
"label": "evals",
@@ -602,7 +602,7 @@
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 62
"file_count": 66
},
{
"path": "evals",
@@ -920,9 +920,9 @@
"failures": []
},
"trust_security": {
"scanned_files": 146,
"script_count": 62,
"internal_module_count": 3,
"scanned_files": 150,
"script_count": 66,
"internal_module_count": 7,
"secret_findings": 0,
"dependency_files": [
"requirements-ci.txt"
@@ -940,8 +940,8 @@
"help_smoke_failed_count": 0,
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 146,
"package_sha256": "9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe"
"package_hash_file_count": 150,
"package_sha256": "742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f"
},
"skill_atlas": {
"skill_count": 12,
@@ -975,8 +975,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe",
"archive_sha256": "4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06"
"package_sha256": "742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f",
"archive_sha256": "7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9"
},
"compatibility": {
"openai": "pass",
@@ -1007,7 +1007,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06",
"archive_sha256": "7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1023,8 +1023,8 @@
"target_count": 3,
"adapter_count": 3,
"archive_present": true,
"archive_sha256": "4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06",
"archive_entry_count": 483,
"archive_sha256": "7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9",
"archive_entry_count": 488,
"failure_count": 0,
"warning_count": 0
},
@@ -1035,7 +1035,7 @@
"ok": true,
"summary": {
"archive_present": true,
"archive_entry_count": 483,
"archive_entry_count": 488,
"archive_extracted": true,
"entrypoint_loaded": true,
"manifest_loaded": true,
@@ -1097,12 +1097,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06"
"to": "7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe"
"to": "742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f"
}
]
},
reports/skill_atlas.json
+4
View File
@@ -106,6 +106,8 @@
"scripts/render_social_preview.py",
"scripts/render_system_model.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_layout.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -113,6 +115,7 @@
"scripts/run_output_execution.py",
"scripts/simulate_install.py",
"scripts/skill_report_charts.py",
"scripts/skill_report_layout.py",
"scripts/skill_report_metrics.py",
"scripts/skill_report_model.py",
"scripts/sync_local_install.py",
@@ -122,6 +125,7 @@
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py",
"scripts/yao_cli_config.py",
"references/artifact-design-doctrine.md",
"references/authoring-discipline.md",
"references/distribution-registry-method.md",
reports/upgrade_check.json
+2 -2
View File
@@ -68,12 +68,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "4d1227dc0996a97aa4987761d46081391fe15b36362e19765e1e7aa8e5d41c06"
"to": "7bc83805501d24cf8e5932ef76e0454100398d5a73652e7440be47984d0cf4a9"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "9f1d53dbaeb1c90c80d7ffbbc1d10473e50b8032acda68332fbae551bb246abe"
"to": "742dc905b0d221c4f336e741d168861edaf7b75e97fe1e89f7d454c1cabf928f"
}
]
},
scripts/render_review_studio.py
+107 -229
View File
@@ -18,6 +18,9 @@ except ImportError: # pragma: no cover
compute_permission_governance_status = None
trust_script_inventory = None
from review_studio_formatting import registry_package_summary, render_kv_grid
from review_studio_layout import render_review_nav, review_studio_css
ROOT = Path(__file__).resolve().parent.parent
@@ -1076,24 +1079,7 @@ def render_html(report: dict[str, Any]) -> str:
frontmatter = report["data"]["frontmatter"]
title = overview.get("display_name") or overview.get("title") or frontmatter.get("name") or manifest.get("name") or "Skill"
description = overview.get("description") or frontmatter.get("description", "")
nav = [
("#overview", "审查总览"),
("#intent", "意图画布"),
("#trigger", "触发实验"),
("#output", "输出实验"),
("#actions", "修复动作"),
("#annotations", "审查批注"),
("#runtime", "运行矩阵"),
("#trust", "信任报告"),
("#permissions", "权限批准"),
("#permission-probes", "权限探针"),
("#atlas", "组合治理"),
("#telemetry", "运营回路"),
("#waivers", "人工批准"),
("#registry", "注册审计"),
("#release", "发布路线"),
]
nav_html = "".join(f"<a href='{href}'>{label}</a>" for href, label in nav)
nav_html = render_review_nav()
gates_html = render_gate_list(gates)
metrics_html = render_insights(insights)
blockers_html = render_issue_list("阻断事项", blockers)
@@ -1119,6 +1105,95 @@ def render_html(report: dict[str, Any]) -> str:
)
registry_package = report["data"]["registry"].get("package", {})
package_summary = report["data"]["package_verification"].get("summary", {})
atlas_panel = render_kv_grid(
atlas_summary,
[
"skill_count",
"actionable_skill_count",
"actionable_route_collision_count",
"actionable_owner_gap_count",
"actionable_stale_count",
"non_actionable_issue_count",
],
"skill atlas summary missing",
)
output_panel = render_kv_grid(
output_summary,
["case_count", "with_skill_pass_rate", "baseline_pass_rate", "delta", "gate_pass", "failure_count"],
"output eval scorecard missing",
)
execution_panel = render_kv_grid(
output_execution_summary,
[
"variant_run_count",
"command_executed_count",
"model_executed_count",
"recorded_fixture_count",
"timing_observed_count",
"token_estimated_count",
],
"output execution report missing",
)
blind_panel = render_kv_grid(
output_blind_summary,
["pair_count", "answer_key_separate", "with_skill_hidden_count"],
"blind A/B review pack missing",
)
review_panel = render_kv_grid(
output_review_summary,
["pair_count", "judgment_count", "pending_count", "agreement_count", "disagreement_count", "invalid_decision_count"],
"review adjudication report missing",
)
conformance_panel = render_kv_grid(
conformance_summary,
["target_count", "pass_count", "fail_count", "warning_count", "failure_count"],
"runtime conformance matrix missing",
)
compiled_panel = render_kv_grid(
compiled_summary,
["target_count", "pass_count", "warn_count", "block_count", "failure_count"],
"compiled target report missing",
)
trust_panel = render_kv_grid(
trust_summary,
["secret_findings", "script_count", "network_script_count", "help_smoke_failed_count", "package_sha256"],
"security trust report missing",
)
runtime_boundary_panel = render_kv_grid(
runtime_permissions_summary,
["target_count", "pass_count", "native_enforcement_count", "metadata_fallback_count", "residual_risk_count", "failure_count"],
"runtime permission probe summary missing",
)
adoption_panel = render_kv_grid(
adoption_summary,
["event_count", "adoption_rate", "missed_trigger_count", "bad_output_count", "risk_band"],
"no adoption drift summary",
)
waiver_panel = render_kv_grid(
waiver_summary,
["waiver_count", "active_count", "expired_count", "invalid_count", "covered_gate_count"],
"no review waiver summary",
)
registry_panel = render_kv_grid(
registry_package_summary(registry_package),
[
"name",
"version",
"maturity",
"owner",
"license",
"trust_level",
"targets",
"compatibility_pass_count",
"archive_sha256",
],
"registry package metadata missing",
)
package_panel = render_kv_grid(
package_summary,
["target_count", "adapter_count", "archive_present", "archive_entry_count", "failure_count", "warning_count", "archive_sha256"],
"package verification missing",
)
evidence_html = "".join(
f"<li><strong>{html.escape(key)}</strong><span>{html.escape(value)}</span></li>"
for key, value in report["evidence_paths"].items()
@@ -1130,204 +1205,7 @@ def render_html(report: dict[str, Any]) -> str:
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>{html.escape(str(title))} Review Studio 2.0</title>
<style>
:root {{
--ink: #1B365D;
--text: #24201d;
--muted: #746d66;
--line: #e7ded2;
--soft: #faf8f5;
--pass: #1e6b52;
--warn: #9a6718;
--block: #9b2c2c;
}}
* {{ box-sizing: border-box; }}
html {{ scroll-behavior: smooth; }}
body {{
margin: 0;
background: #ffffff;
color: var(--text);
font-family: Georgia, "Times New Roman", "Songti SC", serif;
line-height: 1.58;
}}
nav {{
position: sticky;
top: 0;
z-index: 10;
display: flex;
gap: 4px;
justify-content: center;
flex-wrap: wrap;
padding: 10px 16px;
background: rgba(255,255,255,0.94);
border-bottom: 1px solid var(--line);
backdrop-filter: blur(10px);
}}
nav a {{
color: var(--ink);
text-decoration: none;
font-size: 14px;
padding: 7px 10px;
border-radius: 6px;
}}
nav a:hover {{ background: var(--soft); }}
main {{ max-width: 1180px; margin: 0 auto; padding: 44px 28px 76px; }}
header {{ border-bottom: 1px solid var(--line); padding-bottom: 28px; margin-bottom: 28px; }}
.eyebrow {{ color: var(--ink); font-size: 14px; letter-spacing: .08em; text-transform: uppercase; }}
h1, h2, h3 {{ color: var(--text); font-weight: 500; margin: 0; letter-spacing: 0; }}
h1 {{ font-size: clamp(34px, 5vw, 64px); line-height: 1.03; max-width: 920px; margin-top: 12px; }}
h2 {{ font-size: 30px; margin-bottom: 14px; }}
h3 {{ font-size: 19px; }}
p {{ margin: 0; }}
.lede {{ max-width: 820px; color: var(--muted); font-size: 20px; margin-top: 18px; }}
.decision {{
display: inline-flex;
align-items: baseline;
gap: 12px;
margin-top: 24px;
padding: 12px 16px;
border: 1px solid var(--line);
border-radius: 8px;
color: var(--ink);
background: var(--soft);
}}
.decision strong {{ font-size: 28px; }}
section {{ padding: 30px 0; border-bottom: 1px solid var(--line); scroll-margin-top: 76px; }}
.metrics, .gates {{
display: grid;
grid-template-columns: repeat(5, minmax(0, 1fr));
gap: 14px;
}}
.gates {{ grid-template-columns: repeat(4, minmax(0, 1fr)); }}
.metric, .gate {{
border: 1px solid var(--line);
border-radius: 8px;
padding: 16px;
background: #fff;
min-width: 0;
}}
.metric span, .gate span {{ display: block; color: var(--muted); font-size: 13px; }}
.metric strong {{ display: block; color: var(--ink); font-size: 34px; line-height: 1.1; margin: 8px 0; }}
.metric p, .gate p, .gate footer, .issues span, .evidence span {{ color: var(--muted); font-size: 14px; overflow-wrap: anywhere; }}
.gate {{ display: flex; flex-direction: column; gap: 10px; }}
.gate.pass {{ border-top: 4px solid var(--pass); }}
.gate.warn {{ border-top: 4px solid var(--warn); }}
.gate.block {{ border-top: 4px solid var(--block); }}
.gate footer {{ border-top: 1px solid var(--line); padding-top: 10px; }}
a {{ color: var(--ink); }}
.twocol {{
display: grid;
grid-template-columns: minmax(0, 1fr) minmax(0, 1fr);
gap: 22px;
align-items: start;
}}
.panel {{
border: 1px solid var(--line);
border-radius: 8px;
padding: 18px;
background: #fff;
}}
.panel p {{ color: var(--muted); }}
.issues, .evidence {{
list-style: none;
padding: 0;
margin: 0;
display: grid;
gap: 12px;
}}
.issues li, .evidence li {{
border-left: 3px solid var(--line);
padding-left: 12px;
display: grid;
gap: 3px;
}}
.muted {{ color: var(--muted); }}
.actions-grid {{
display: grid;
grid-template-columns: repeat(2, minmax(0, 1fr));
gap: 16px;
}}
.annotations-grid {{
display: grid;
grid-template-columns: repeat(2, minmax(0, 1fr));
gap: 16px;
}}
.action-card {{
border: 1px solid var(--line);
border-radius: 8px;
padding: 18px;
background: #fff;
display: grid;
gap: 10px;
min-width: 0;
}}
.action-card.warn {{ border-left: 4px solid var(--warn); }}
.action-card.block {{ border-left: 4px solid var(--block); }}
.annotation-card {{
border: 1px solid var(--line);
border-radius: 8px;
padding: 18px;
background: #fff;
display: grid;
gap: 10px;
min-width: 0;
}}
.annotation-card.warning {{ border-left: 4px solid var(--warn); }}
.annotation-card.blocker {{ border-left: 4px solid var(--block); }}
.annotation-card.resolved {{ opacity: .72; }}
.action-card span,
.annotation-card span,
.action-card small,
.annotation-card small,
.action-card footer,
.annotation-card footer,
.action-card dd {{
color: var(--muted);
font-size: 14px;
overflow-wrap: anywhere;
}}
.annotation-card dd {{ color: var(--muted); font-size: 14px; overflow-wrap: anywhere; }}
.action-card dl, .annotation-card dl {{
display: grid;
grid-template-columns: 80px minmax(0, 1fr);
gap: 6px 10px;
margin: 0;
}}
.action-card dt, .annotation-card dt {{ color: var(--ink); font-size: 14px; }}
.action-card dd, .annotation-card dd {{ margin: 0; }}
.source-ref-list {{
list-style: none;
padding: 0;
margin: 0;
display: grid;
gap: 6px;
}}
.source-ref-list li {{
display: grid;
gap: 2px;
min-width: 0;
padding: 8px 0 0;
border-top: 1px solid var(--line);
}}
.source-ref-list a,
.source-ref-list span {{
overflow-wrap: anywhere;
font-family: ui-monospace, SFMono-Regular, Menlo, Consolas, monospace;
font-size: 13px;
}}
.source-ref-list small {{
font-size: 12px;
color: var(--muted);
}}
code {{
font-family: ui-monospace, SFMono-Regular, Menlo, Consolas, monospace;
font-size: 13px;
}}
@media (max-width: 980px) {{
.metrics, .gates, .twocol, .actions-grid, .annotations-grid {{ grid-template-columns: 1fr; }}
main {{ padding: 32px 18px 60px; }}
nav {{ justify-content: flex-start; overflow-x: auto; flex-wrap: nowrap; }}
nav a {{ flex: 0 0 auto; }}
}}
{review_studio_css()}
</style>
</head>
<body>
@@ -1383,17 +1261,17 @@ def render_html(report: dict[str, Any]) -> str:
<section id="trigger" class="twocol">
<div class="panel"><h2>触发实验</h2><p>{html.escape(gates[1]['detail'])}</p></div>
<div class="panel"><h2>组合治理</h2><p>{html.escape(str(atlas_summary))}</p></div>
<div class="panel"><h2>组合治理</h2>{atlas_panel}</div>
</section>
<section id="output" class="twocol">
<div class="panel"><h2>输出实验</h2><p>{html.escape(str(output_summary))}</p></div>
<div class="panel"><h2>执行证据</h2><p>{html.escape(str(output_execution_summary or 'output execution report missing'))}</p></div>
<div class="panel"><h2>输出实验</h2>{output_panel}</div>
<div class="panel"><h2>执行证据</h2>{execution_panel}</div>
</section>
<section class="twocol">
<div class="panel"><h2>盲评包</h2><p>{html.escape(str(output_blind_summary or 'blind A/B review pack missing'))}</p></div>
<div class="panel"><h2>审定报告</h2><p>{html.escape(str(output_review_summary or 'review adjudication report missing'))}</p></div>
<div class="panel"><h2>盲评包</h2>{blind_panel}</div>
<div class="panel"><h2>审定报告</h2>{review_panel}</div>
</section>
<section class="twocol">
@@ -1407,8 +1285,8 @@ def render_html(report: dict[str, Any]) -> str:
</section>
<section id="runtime" class="twocol">
<div class="panel"><h2>运行矩阵</h2><p>{html.escape(str(conformance_summary))}</p></div>
<div class="panel"><h2>目标编译</h2><p>{html.escape(str(compiled_summary or 'compiled target report missing'))}</p></div>
<div class="panel"><h2>运行矩阵</h2>{conformance_panel}</div>
<div class="panel"><h2>目标编译</h2>{compiled_panel}</div>
</section>
<section class="twocol">
@@ -1417,7 +1295,7 @@ def render_html(report: dict[str, Any]) -> str:
</section>
<section id="trust" class="twocol">
<div class="panel"><h2>信任报告</h2><p>{html.escape(str(trust_summary))}</p></div>
<div class="panel"><h2>信任报告</h2>{trust_panel}</div>
<div class="panel"><h2>安全边界</h2><p>高风险 secret、远程 inline execution、缺失依赖策略或无法解释的脚本接口应阻断 governed release。</p></div>
</section>
@@ -1428,7 +1306,7 @@ def render_html(report: dict[str, Any]) -> str:
<section id="permission-probes" class="twocol">
<div class="panel"><h2>权限探针</h2><p>{html.escape(gate_details.get('permission-runtime', 'runtime permission probes missing'))}</p></div>
<div class="panel"><h2>运行边界</h2><p>{html.escape(str(runtime_permissions_summary or 'runtime permission probe summary missing'))}</p></div>
<div class="panel"><h2>运行边界</h2>{runtime_boundary_panel}</div>
</section>
<section id="atlas" class="twocol">
@@ -1438,22 +1316,22 @@ def render_html(report: dict[str, Any]) -> str:
<section id="telemetry" class="twocol">
<div class="panel"><h2>运营回路</h2><p>{html.escape(gate_details.get('operations-loop', 'adoption drift report missing'))}</p></div>
<div class="panel"><h2>漂移信号</h2><p>{html.escape(str(adoption_summary or 'no adoption drift summary'))}</p></div>
<div class="panel"><h2>漂移信号</h2>{adoption_panel}</div>
</section>
<section id="waivers" class="twocol">
<div class="panel"><h2>人工批准</h2><p>{html.escape(gate_details.get('review-waivers', 'review waiver ledger missing'))}</p></div>
<div class="panel"><h2>批准台账</h2><p>{html.escape(str(waiver_summary or 'no review waiver summary'))}</p></div>
<div class="panel"><h2>批准台账</h2>{waiver_panel}</div>
</section>
<section id="registry" class="twocol">
<div class="panel"><h2>注册审计</h2><p>{html.escape(gate_details.get('registry-audit', 'registry audit missing'))}</p></div>
<div class="panel"><h2>包体元数据</h2><p>{html.escape(str(registry_package))}</p></div>
<div class="panel"><h2>包体元数据</h2>{registry_panel}</div>
</section>
<section id="release" class="twocol">
<div class="panel"><h2>发布路线</h2><p>{html.escape(gate_details.get('release-notes', 'release notes missing'))}</p></div>
<div class="panel"><h2>包体验证</h2><p>{html.escape(str(package_summary or 'package verification missing'))}</p></div>
<div class="panel"><h2>包体验证</h2>{package_panel}</div>
</section>
</main>
</body>
scripts/render_skill_overview.py
+5 -620
View File
@@ -5,6 +5,7 @@ import json
from pathlib import Path
from skill_report_charts import render_chart_set
from skill_report_layout import render_language_switch, render_report_nav, skill_overview_css, skill_overview_script
from skill_report_model import REPORT_NAV_V2, build_report_model
@@ -279,15 +280,8 @@ def render_roadmap(items: list[dict]) -> str:
def render_html(summary: dict) -> str:
charts = render_chart_set(summary)
nav_html = "".join(
f"<a href=\"#{item['href']}\">{bi_span(item['label'], item['label_en'])}</a>" for item in REPORT_NAV_V2
)
language_switch = (
'<div class="language-switch" aria-label="语言切换">'
'<button type="button" data-set-lang="zh-CN" aria-pressed="true">简体</button>'
'<button type="button" data-set-lang="en" aria-pressed="false">EN</button>'
"</div>"
)
nav_html = render_report_nav(REPORT_NAV_V2)
language_switch = render_language_switch()
skill = summary.get("skill_summary", {})
metadata = summary.get("metadata", {})
scorecard = summary.get("scorecard", {})
@@ -359,580 +353,7 @@ def render_html(summary: dict) -> str:
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>{html.escape(summary['name'])} Skill 生成审计报告</title>
<style>
:root {{
--paper: #ffffff;
--wash: #f8fafc;
--wash-strong: #f2f5f8;
--line: #e6e0d4;
--line-soft: #eee9df;
--brand: #1B365D;
--brand-soft: #EEF3F8;
--brand-mid: #315982;
--ink: #151515;
--text: #2f2d29;
--muted: #68625a;
--faint: #8b857b;
--success: #2f6f5e;
--warn: #8a5a19;
--serif: "TsangerJinKai02", "Source Han Serif SC", "Noto Serif CJK SC", "Songti SC", "STSong", Charter, Georgia, serif;
--mono: "JetBrains Mono", "SF Mono", ui-monospace, Menlo, Consolas, monospace;
--shadow-soft: 0 1px 2px rgba(27, 54, 93, 0.06), 0 16px 44px rgba(27, 54, 93, 0.08);
}}
* {{ box-sizing: border-box; }}
html {{ scroll-behavior: smooth; }}
body {{
margin: 0;
background: #ffffff;
color: var(--ink);
font-family: var(--serif);
line-height: 1.62;
letter-spacing: 0;
-webkit-font-smoothing: antialiased;
-moz-osx-font-smoothing: grayscale;
text-rendering: optimizeLegibility;
}}
body[data-report-lang="zh-CN"] [data-lang="en"],
body[data-report-lang="en"] [data-lang="zh-CN"] {{ display: none !important; }}
.skip-link {{
position: fixed;
left: 18px;
top: 10px;
z-index: 40;
transform: translateY(-140%);
padding: 8px 12px;
border-radius: 8px;
background: var(--brand);
color: #fff;
text-decoration: none;
transition: transform 160ms cubic-bezier(0.16, 1, 0.3, 1);
}}
.skip-link:focus-visible {{ transform: translateY(0); outline: 2px solid var(--brand-mid); outline-offset: 2px; }}
.topbar {{
position: sticky;
top: 0;
z-index: 20;
background: rgba(255, 255, 255, 0.96);
border-bottom: 1px solid var(--line);
}}
.progress-track {{
height: 2px;
background: transparent;
}}
.progress-bar {{
display: block;
width: 100%;
height: 100%;
background: var(--brand);
transition: transform 160ms cubic-bezier(0.16, 1, 0.3, 1);
transform-origin: left center;
transform: scaleX(0);
}}
.topbar-inner {{
max-width: 1240px;
margin: 0 auto;
padding: 9px 28px;
display: grid;
grid-template-columns: minmax(0, 1fr) auto;
gap: 18px;
align-items: center;
}}
.nav-shell {{
display: grid;
grid-template-columns: auto minmax(0, 1fr);
gap: 18px;
align-items: center;
min-width: 0;
}}
.report-mark {{
color: var(--brand);
font-family: var(--mono);
font-size: 11px;
line-height: 1;
text-transform: uppercase;
white-space: nowrap;
}}
.report-nav {{
display: flex;
gap: 4px;
overflow-x: auto;
scrollbar-width: none;
min-width: 0;
}}
.report-nav::-webkit-scrollbar {{ display: none; }}
.report-nav a {{
flex: 0 0 auto;
min-width: 76px;
min-height: 40px;
display: inline-flex;
align-items: center;
justify-content: center;
padding: 0 10px;
color: var(--brand);
text-decoration: none;
text-align: center;
font-size: 13px;
border-radius: 8px;
white-space: nowrap;
transition-property: background-color, color, transform;
transition-duration: 160ms;
transition-timing-function: cubic-bezier(0.16, 1, 0.3, 1);
}}
@media (hover: hover) {{
.report-nav a:hover {{ background: var(--brand-soft); }}
}}
.report-nav a:focus-visible {{
outline: 2px solid var(--brand-mid);
outline-offset: 2px;
background: var(--brand-soft);
}}
.report-nav a[aria-current="true"] {{
background: var(--brand);
color: #ffffff;
}}
.report-nav a[aria-current="true"] span {{ color: #ffffff; }}
.language-switch {{
display: inline-flex;
gap: 3px;
padding: 3px;
border: 1px solid var(--line);
border-radius: 8px;
background: var(--paper);
box-shadow: 0 1px 2px rgba(27, 54, 93, 0.05);
}}
.language-switch button {{
appearance: none;
min-width: 42px;
min-height: 34px;
border: 0;
border-radius: 6px;
padding: 0 10px;
background: transparent;
color: var(--muted);
font: inherit;
font-size: 13px;
cursor: pointer;
transition-property: background-color, color, transform;
transition-duration: 160ms;
transition-timing-function: cubic-bezier(0.16, 1, 0.3, 1);
}}
.language-switch button:active {{ transform: scale(0.96); }}
.language-switch button:focus-visible {{ outline: 2px solid var(--brand-mid); outline-offset: 2px; }}
.language-switch button[aria-pressed="true"] {{
background: var(--brand-soft);
color: var(--brand);
}}
.wrap {{
max-width: 1240px;
margin: 0 auto;
padding: 58px 28px 92px;
}}
.hero {{
padding: 16px 0 34px;
}}
.hero-grid {{
display: grid;
grid-template-columns: minmax(0, 1fr) 360px;
gap: 44px;
align-items: end;
}}
.eyebrow, .report-mark {{
letter-spacing: 0;
}}
.eyebrow {{
margin: 0 0 12px;
color: var(--brand);
font-family: var(--mono);
font-size: 12px;
text-transform: uppercase;
}}
.slug {{
margin: 0 0 18px;
color: var(--faint);
font-family: var(--mono);
font-size: 13px;
overflow-wrap: anywhere;
}}
h1, h2, h3 {{
margin: 0;
font-weight: 500;
letter-spacing: 0;
text-wrap: balance;
}}
h1 {{
max-width: 8em;
color: var(--ink);
font-size: 4rem;
line-height: 1.02;
}}
.lead {{
max-width: 760px;
margin: 20px 0 0;
color: var(--text);
font-size: 1.08rem;
text-wrap: pretty;
}}
.hero-meta, .badges {{
display: flex;
flex-wrap: wrap;
gap: 8px;
margin-top: 20px;
}}
.hero-meta span, .badges span, .tag {{
display: inline-flex;
align-items: center;
min-height: 30px;
padding: 5px 10px;
border-radius: 6px;
background: var(--brand-soft);
color: var(--brand);
font-size: 13px;
font-variant-numeric: tabular-nums;
}}
.hero-card {{
position: relative;
padding: 22px 22px 24px;
border-radius: 8px;
background: linear-gradient(180deg, #ffffff 0%, #fbfaf7 100%);
box-shadow: var(--shadow-soft);
border: 1px solid var(--line-soft);
}}
.hero-card::before {{
content: "";
position: absolute;
top: 18px;
right: 18px;
width: 38px;
height: 2px;
background: var(--brand);
}}
.score-strip {{
display: grid;
grid-template-columns: repeat(4, minmax(0, 1fr));
gap: 10px;
margin-top: 32px;
padding-top: 20px;
border-top: 1px solid var(--line);
}}
.score-chip {{
padding: 14px 14px 12px;
border-radius: 8px;
background: var(--wash);
border: 1px solid var(--line-soft);
}}
.score-chip span {{
display: block;
color: var(--muted);
font-size: 12px;
}}
.score-chip strong {{
display: block;
margin: 5px 0 8px;
color: var(--brand);
font-family: var(--mono);
font-size: 1.65rem;
font-weight: 500;
line-height: 1;
font-variant-numeric: tabular-nums;
}}
.score-chip i {{
display: block;
height: 3px;
border-radius: 999px;
background: linear-gradient(90deg, var(--brand) var(--score), #dfe6ee var(--score));
}}
.score-chip small {{
display: block;
margin-top: 8px;
color: var(--muted);
font-size: 12px;
line-height: 1.45;
}}
section {{
scroll-margin-top: 78px;
padding-top: 44px;
margin-top: 44px;
border-top: 1px solid var(--line);
}}
section.hero {{
scroll-margin-top: 0;
padding-top: 16px;
margin-top: 0;
border-top: 0;
}}
.section-head {{
display: grid;
grid-template-columns: minmax(0, 246px) minmax(0, 1fr);
gap: 36px;
align-items: start;
}}
h2 {{
color: var(--ink);
font-size: 1.5rem;
line-height: 1.18;
}}
h2::before {{
content: "";
display: block;
width: 32px;
height: 2px;
margin-bottom: 12px;
background: var(--brand);
}}
h3 {{
color: var(--ink);
font-size: 1.02rem;
line-height: 1.3;
margin-bottom: 10px;
}}
.section-head p {{
margin: 12px 0 0;
color: var(--muted);
max-width: 43ch;
text-wrap: pretty;
}}
.two-col, .metric-grid, .chart-grid {{
display: grid;
grid-template-columns: repeat(2, minmax(0, 1fr));
gap: 16px;
align-items: stretch;
}}
.quality-panels {{
margin-top: 16px;
}}
.metrics-stack {{
display: grid;
gap: 18px;
}}
.metrics-lead {{
display: grid;
grid-template-columns: minmax(420px, 1.15fr) minmax(300px, 0.85fr);
gap: 18px;
align-items: stretch;
}}
.metrics-note {{
display: grid;
align-content: start;
gap: 16px;
}}
.metrics-note p {{
margin: 0;
max-width: none;
color: var(--text);
}}
.metric-summary-list {{
margin: 0;
padding: 0;
list-style: none;
display: grid;
gap: 10px;
}}
.metric-summary-list li {{
display: grid;
grid-template-columns: auto minmax(0, 1fr) auto;
gap: 8px 10px;
align-items: baseline;
padding: 10px 0;
border-bottom: 1px solid var(--line-soft);
}}
.metric-summary-list li:last-child {{ border-bottom: 0; }}
.metric-summary-list b {{
color: var(--ink);
font-weight: 500;
}}
.metric-summary-list em {{
color: var(--brand);
font-family: var(--mono);
font-style: normal;
font-variant-numeric: tabular-nums;
}}
.metric-summary-list small {{
grid-column: 2 / 4;
color: var(--muted);
line-height: 1.5;
}}
.metric-status {{
display: inline-flex;
align-items: center;
min-height: 24px;
padding: 2px 7px;
border-radius: 6px;
background: var(--brand-soft);
color: var(--brand);
font-size: 12px;
}}
.metric-grid {{
grid-template-columns: repeat(2, minmax(0, 1fr));
margin-top: 2px;
}}
.list, .compact-list, .step-list {{
margin: 0;
padding-left: 1.15em;
display: grid;
gap: 8px;
}}
.list li::marker, .compact-list li::marker, .step-list li::marker {{ color: var(--brand); }}
.compact-list {{
gap: 6px;
font-size: 13px;
color: var(--muted);
}}
.panel, .metric-card, .roadmap-item {{
background: #ffffff;
border: 1px solid var(--line-soft);
border-radius: 8px;
padding: 22px;
box-shadow: 0 1px 2px rgba(27, 54, 93, 0.04);
}}
.metric-card {{
display: grid;
grid-template-columns: 92px minmax(0, 1fr);
gap: 18px;
align-content: start;
min-height: 0;
}}
.metric-card-head {{
display: grid;
align-content: start;
}}
.metric-card strong {{
display: block;
margin: 8px 0 10px;
color: var(--brand);
font-family: var(--mono);
font-size: 2rem;
font-weight: 500;
line-height: 1;
font-variant-numeric: tabular-nums;
}}
.metric-label {{
color: var(--muted);
font-size: 13px;
}}
.metric-card-body {{
min-width: 0;
}}
.chart-figure {{
margin: 0;
padding: 18px;
border: 1px solid var(--line-soft);
border-radius: 8px;
background: #ffffff;
box-shadow: 0 1px 2px rgba(27, 54, 93, 0.04);
}}
.chart-figure svg {{
width: 100%;
height: auto;
display: block;
overflow: visible;
}}
.chart-figure text {{
fill: var(--ink);
font-family: var(--serif);
font-size: 13px;
}}
.chart-title {{
fill: var(--brand);
font-size: 16px;
font-weight: 500;
}}
.chart-line {{
fill: none;
stroke: var(--brand);
stroke-width: 2;
}}
figcaption {{
margin-top: 12px;
padding-top: 10px;
border-top: 1px solid var(--line-soft);
color: var(--muted);
font-size: 13px;
line-height: 1.5;
text-wrap: pretty;
}}
table {{
width: 100%;
border-collapse: collapse;
font-size: 14px;
}}
th, td {{
padding: 12px 10px;
text-align: left;
border-bottom: 1px solid var(--line-soft);
vertical-align: top;
}}
th {{
color: var(--brand);
font-weight: 500;
font-size: 12px;
}}
td:first-child, th:first-child {{ width: 96px; }}
.roadmap {{
display: grid;
grid-template-columns: repeat(3, minmax(0, 1fr));
gap: 16px;
}}
.step {{
display: inline-flex;
margin-bottom: 12px;
min-height: 28px;
align-items: center;
padding: 3px 8px;
border-radius: 6px;
background: var(--brand-soft);
color: var(--brand);
font-size: 12px;
}}
.unlock {{
margin-top: 14px;
color: var(--muted);
font-size: 13px;
}}
@media (max-width: 980px) {{
.topbar-inner {{
grid-template-columns: minmax(0, 1fr) auto;
padding: 8px 16px;
}}
.nav-shell {{ grid-template-columns: 1fr; gap: 6px; }}
.report-mark {{ display: none; }}
.report-nav a {{ min-width: 72px; }}
.hero-grid, .section-head {{ grid-template-columns: 1fr; }}
.hero-grid {{ gap: 24px; }}
.score-strip {{ grid-template-columns: repeat(2, minmax(0, 1fr)); }}
.metrics-lead, .two-col, .metric-grid, .chart-grid, .roadmap {{ grid-template-columns: 1fr; }}
.metric-card {{ grid-template-columns: 86px minmax(0, 1fr); }}
h1 {{ font-size: 2.75rem; }}
}}
@media (max-width: 540px) {{
.wrap {{ padding: 34px 16px 72px; }}
.topbar-inner {{ gap: 10px; }}
.report-nav {{
display: flex;
gap: 2px;
}}
.report-nav a {{
min-width: 66px;
min-height: 38px;
padding: 0 8px;
font-size: 12px;
}}
.language-switch button {{ min-width: 38px; min-height: 32px; padding: 0 8px; }}
.hero {{ padding-top: 8px; }}
h1 {{ max-width: 8em; font-size: 2.35rem; }}
.lead {{ font-size: 1rem; }}
.hero-meta span, .badges span {{ font-size: 12px; }}
.score-strip {{ grid-template-columns: 1fr; }}
section {{ margin-top: 34px; padding-top: 34px; }}
.panel, .metric-card, .roadmap-item, .chart-figure, .hero-card {{ padding: 18px; }}
.metric-card {{ grid-template-columns: 1fr; gap: 10px; }}
.metric-card strong {{ margin-bottom: 2px; }}
.metric-summary-list li {{ grid-template-columns: auto minmax(0, 1fr) auto; }}
table {{ font-size: 13px; }}
th, td {{ padding: 10px 7px; }}
}}
@media (prefers-reduced-motion: reduce) {{
html {{ scroll-behavior: auto; }}
*, *::before, *::after {{ transition-duration: 0.01ms !important; }}
}}
{skill_overview_css()}
</style>
</head>
<body data-report-lang="zh-CN">
@@ -1148,43 +569,7 @@ def render_html(summary: dict) -> str:
</section>
</main>
<script>
(function () {{
var buttons = Array.prototype.slice.call(document.querySelectorAll("[data-set-lang]"));
var navLinks = Array.prototype.slice.call(document.querySelectorAll(".report-nav a"));
var sections = navLinks
.map(function (link) {{ return document.querySelector(link.getAttribute("href")); }})
.filter(Boolean);
var progressBar = document.querySelector(".progress-bar");
function setLanguage(lang) {{
document.body.setAttribute("data-report-lang", lang);
document.documentElement.setAttribute("lang", lang);
buttons.forEach(function (button) {{
button.setAttribute("aria-pressed", button.getAttribute("data-set-lang") === lang ? "true" : "false");
}});
}}
function updateProgress() {{
var scrollTop = window.scrollY || document.documentElement.scrollTop;
var height = Math.max(1, document.documentElement.scrollHeight - window.innerHeight);
var pct = Math.min(100, Math.max(0, (scrollTop / height) * 100));
if (progressBar) progressBar.style.transform = "scaleX(" + pct / 100 + ")";
var active = sections[0];
sections.forEach(function (section) {{
if (section.getBoundingClientRect().top <= 110) active = section;
}});
navLinks.forEach(function (link) {{
link.setAttribute("aria-current", link.getAttribute("href") === "#" + active.id ? "true" : "false");
}});
}}
buttons.forEach(function (button) {{
button.addEventListener("click", function () {{
setLanguage(button.getAttribute("data-set-lang"));
}});
}});
window.addEventListener("scroll", updateProgress, {{ passive: true }});
window.addEventListener("resize", updateProgress);
setLanguage("zh-CN");
updateProgress();
}})();
{skill_overview_script()}
</script>
</body>
</html>
scripts/review_studio_formatting.py
+133
View File
@@ -0,0 +1,133 @@
#!/usr/bin/env python3
"""Formatting helpers for Review Studio panels."""
import html
from typing import Any
SCRIPT_INTERFACE = "internal-module"
SCRIPT_INTERFACE_REASON = "Imported by render_review_studio.py to format report dictionaries as audit UI panels."
LABELS = {
"actionable_owner_gap_count": "待处理 owner",
"actionable_route_collision_count": "待处理冲突",
"actionable_skill_count": "纳入审查",
"actionable_stale_count": "待处理过期",
"adoption_rate": "采用率",
"adapter_count": "Adapter",
"archive_entry_count": "Zip 条目",
"archive_present": "归档存在",
"archive_sha256": "归档哈希",
"baseline_pass_rate": "Baseline",
"breaking_change_count": "破坏变更",
"case_count": "案例数",
"command_executed_count": "命令执行",
"compatibility_pass_count": "兼容通过",
"covered_gate_count": "覆盖 Gate",
"declared_bump": "声明版本",
"delta": "增益",
"event_count": "事件数",
"failure_count": "失败数",
"gate_pass": "Gate",
"help_smoke_failed_count": "Help 失败",
"install_simulated": "安装模拟",
"license": "License",
"metadata_fallback_count": "Metadata fallback",
"missed_trigger_count": "漏触发",
"model_executed_count": "模型执行",
"name": "名称",
"native_enforcement_count": "原生执行",
"network_script_count": "网络脚本",
"non_actionable_issue_count": "非行动项",
"open_blocker_count": "阻断批注",
"open_count": "开放批注",
"owner": "Owner",
"package_sha256": "包体哈希",
"pass_count": "通过数",
"pending_count": "待审",
"recorded_fixture_count": "记录样本",
"recommended_bump": "建议版本",
"residual_risk_count": "残余风险",
"risk_band": "风险带",
"route_collision_count": "路由冲突",
"script_count": "脚本数",
"secret_findings": "Secret",
"skill_count": "Skill 数",
"target_count": "目标数",
"targets": "目标平台",
"timing_observed_count": "计时样本",
"token_estimated_count": "估算 Token",
"token_observed_count": "真实 Token",
"trust_level": "信任级别",
"variant_run_count": "运行数",
"version": "版本",
"warning_count": "警告数",
"with_skill_pass_rate": "With Skill",
}
def label_for_key(key: str) -> str:
return LABELS.get(key, key.replace("_", " ").title())
def value_text(value: Any) -> str:
if value is None:
return "n/a"
if isinstance(value, bool):
return "是" if value else "否"
if isinstance(value, float):
return str(round(value, 3)).rstrip("0").rstrip(".")
if isinstance(value, list):
return ", ".join(value_text(item) for item in value) if value else "无"
if isinstance(value, dict):
parts = []
for key, nested_value in list(value.items())[:6]:
parts.append(f"{label_for_key(str(key))}: {value_text(nested_value)}")
return "；".join(parts) if parts else "无"
return str(value)
def render_kv_grid(
payload: dict[str, Any],
keys: list[str],
empty: str,
) -> str:
if not payload:
return f"<p class='muted'>{html.escape(empty)}</p>"
rows = []
for key in keys:
if key not in payload:
continue
value = value_text(payload.get(key))
value_html = html.escape(value)
if "sha256" in key or "hash" in key or "checksum" in key:
value_html = f"<code>{value_html}</code>"
rows.append(
"<div>"
f"<dt>{html.escape(label_for_key(key))}</dt>"
f"<dd>{value_html}</dd>"
"</div>"
)
if not rows:
return f"<p class='muted'>{html.escape(empty)}</p>"
return "<dl class='kv-grid'>" + "".join(rows) + "</dl>"
def registry_package_summary(package: dict[str, Any]) -> dict[str, Any]:
if not package:
return {}
compatibility = package.get("compatibility", {}) if isinstance(package.get("compatibility"), dict) else {}
pass_count = sum(1 for status in compatibility.values() if status == "pass")
checksums = package.get("checksums", {}) if isinstance(package.get("checksums"), dict) else {}
return {
"name": package.get("name", ""),
"version": package.get("version", ""),
"maturity": package.get("maturity", ""),
"owner": package.get("owner", ""),
"license": package.get("license", ""),
"trust_level": package.get("trust_level", ""),
"targets": package.get("targets", []),
"compatibility_pass_count": f"{pass_count}/{len(compatibility)}",
"archive_sha256": checksums.get("archive_sha256", ""),
}
scripts/review_studio_layout.py
+259
View File
@@ -0,0 +1,259 @@
#!/usr/bin/env python3
"""Static layout contract for Review Studio HTML."""
import html
SCRIPT_INTERFACE = "internal-module"
SCRIPT_INTERFACE_REASON = "Imported by render_review_studio.py to keep Review Studio layout and CSS out of gate logic."
REVIEW_STUDIO_NAV = [
("#overview", "审查总览"),
("#intent", "意图画布"),
("#trigger", "触发实验"),
("#output", "输出实验"),
("#actions", "修复动作"),
("#annotations", "审查批注"),
("#runtime", "运行矩阵"),
("#trust", "信任报告"),
("#permissions", "权限批准"),
("#permission-probes", "权限探针"),
("#atlas", "组合治理"),
("#telemetry", "运营回路"),
("#waivers", "人工批准"),
("#registry", "注册审计"),
("#release", "发布路线"),
]
def render_review_nav(nav_items: list[tuple[str, str]] | None = None) -> str:
items = REVIEW_STUDIO_NAV if nav_items is None else nav_items
return "".join(
f"<a href='{html.escape(href)}'>{html.escape(label)}</a>"
for href, label in items
)
def review_studio_css() -> str:
return """
:root {
--ink: #1B365D;
--text: #24201d;
--muted: #746d66;
--line: #e7ded2;
--soft: #faf8f5;
--pass: #1e6b52;
--warn: #9a6718;
--block: #9b2c2c;
}
* { box-sizing: border-box; }
html { scroll-behavior: smooth; }
body {
margin: 0;
background: #ffffff;
color: var(--text);
font-family: Georgia, "Times New Roman", "Songti SC", serif;
line-height: 1.58;
}
nav {
position: sticky;
top: 0;
z-index: 10;
display: flex;
gap: 4px;
justify-content: center;
flex-wrap: wrap;
padding: 10px 16px;
background: rgba(255,255,255,0.94);
border-bottom: 1px solid var(--line);
backdrop-filter: blur(10px);
}
nav a {
color: var(--ink);
text-decoration: none;
font-size: 14px;
padding: 7px 10px;
border-radius: 6px;
}
nav a:hover { background: var(--soft); }
main { max-width: 1180px; margin: 0 auto; padding: 44px 28px 76px; }
header { border-bottom: 1px solid var(--line); padding-bottom: 28px; margin-bottom: 28px; }
.eyebrow { color: var(--ink); font-size: 14px; letter-spacing: .08em; text-transform: uppercase; }
h1, h2, h3 { color: var(--text); font-weight: 500; margin: 0; letter-spacing: 0; }
h1 { font-size: clamp(34px, 5vw, 64px); line-height: 1.03; max-width: 920px; margin-top: 12px; }
h2 { font-size: 30px; margin-bottom: 14px; }
h3 { font-size: 19px; }
p { margin: 0; }
.lede { max-width: 820px; color: var(--muted); font-size: 20px; margin-top: 18px; }
.decision {
display: inline-flex;
align-items: baseline;
gap: 12px;
margin-top: 24px;
padding: 12px 16px;
border: 1px solid var(--line);
border-radius: 8px;
color: var(--ink);
background: var(--soft);
}
.decision strong { font-size: 28px; }
section { padding: 30px 0; border-bottom: 1px solid var(--line); scroll-margin-top: 76px; }
.metrics, .gates {
display: grid;
grid-template-columns: repeat(5, minmax(0, 1fr));
gap: 14px;
}
.gates { grid-template-columns: repeat(4, minmax(0, 1fr)); }
.metric, .gate {
border: 1px solid var(--line);
border-radius: 8px;
padding: 16px;
background: #fff;
min-width: 0;
}
.metric span, .gate span { display: block; color: var(--muted); font-size: 13px; }
.metric strong { display: block; color: var(--ink); font-size: 34px; line-height: 1.1; margin: 8px 0; }
.metric p, .gate p, .gate footer, .issues span, .evidence span { color: var(--muted); font-size: 14px; overflow-wrap: anywhere; }
.gate { display: flex; flex-direction: column; gap: 10px; }
.gate.pass { border-top: 4px solid var(--pass); }
.gate.warn { border-top: 4px solid var(--warn); }
.gate.block { border-top: 4px solid var(--block); }
.gate footer { border-top: 1px solid var(--line); padding-top: 10px; }
a { color: var(--ink); }
.twocol {
display: grid;
grid-template-columns: minmax(0, 1fr) minmax(0, 1fr);
gap: 22px;
align-items: start;
}
.panel {
border: 1px solid var(--line);
border-radius: 8px;
padding: 18px;
background: #fff;
}
.panel p { color: var(--muted); }
.kv-grid {
display: grid;
grid-template-columns: repeat(2, minmax(0, 1fr));
gap: 10px 12px;
margin: 2px 0 0;
}
.kv-grid div {
min-width: 0;
padding: 9px 0 0;
border-top: 1px solid var(--line);
}
.kv-grid dt {
color: var(--muted);
font-size: 13px;
}
.kv-grid dd {
margin: 2px 0 0;
color: var(--ink);
font-size: 15px;
overflow-wrap: anywhere;
}
.issues, .evidence {
list-style: none;
padding: 0;
margin: 0;
display: grid;
gap: 12px;
}
.issues li, .evidence li {
border-left: 3px solid var(--line);
padding-left: 12px;
display: grid;
gap: 3px;
}
.muted { color: var(--muted); }
.actions-grid {
display: grid;
grid-template-columns: repeat(2, minmax(0, 1fr));
gap: 16px;
}
.annotations-grid {
display: grid;
grid-template-columns: repeat(2, minmax(0, 1fr));
gap: 16px;
}
.action-card {
border: 1px solid var(--line);
border-radius: 8px;
padding: 18px;
background: #fff;
display: grid;
gap: 10px;
min-width: 0;
}
.action-card.warn { border-left: 4px solid var(--warn); }
.action-card.block { border-left: 4px solid var(--block); }
.annotation-card {
border: 1px solid var(--line);
border-radius: 8px;
padding: 18px;
background: #fff;
display: grid;
gap: 10px;
min-width: 0;
}
.annotation-card.warning { border-left: 4px solid var(--warn); }
.annotation-card.blocker { border-left: 4px solid var(--block); }
.annotation-card.resolved { opacity: .72; }
.action-card span,
.annotation-card span,
.action-card small,
.annotation-card small,
.action-card footer,
.annotation-card footer,
.action-card dd {
color: var(--muted);
font-size: 14px;
overflow-wrap: anywhere;
}
.annotation-card dd { color: var(--muted); font-size: 14px; overflow-wrap: anywhere; }
.action-card dl, .annotation-card dl {
display: grid;
grid-template-columns: 80px minmax(0, 1fr);
gap: 6px 10px;
margin: 0;
}
.action-card dt, .annotation-card dt { color: var(--ink); font-size: 14px; }
.action-card dd, .annotation-card dd { margin: 0; }
.source-ref-list {
list-style: none;
padding: 0;
margin: 0;
display: grid;
gap: 6px;
}
.source-ref-list li {
display: grid;
gap: 2px;
min-width: 0;
padding: 8px 0 0;
border-top: 1px solid var(--line);
}
.source-ref-list a,
.source-ref-list span {
overflow-wrap: anywhere;
font-family: ui-monospace, SFMono-Regular, Menlo, Consolas, monospace;
font-size: 13px;
}
.source-ref-list small {
font-size: 12px;
color: var(--muted);
}
code {
font-family: ui-monospace, SFMono-Regular, Menlo, Consolas, monospace;
font-size: 13px;
}
@media (max-width: 980px) {
.metrics, .gates, .twocol, .actions-grid, .annotations-grid, .kv-grid { grid-template-columns: 1fr; }
main { padding: 32px 18px 60px; }
nav { justify-content: flex-start; overflow-x: auto; flex-wrap: nowrap; }
nav a { flex: 0 0 auto; }
}
""".strip()
scripts/skill_report_layout.py
+653
View File
@@ -0,0 +1,653 @@
#!/usr/bin/env python3
"""Static layout contract for skill overview report HTML."""
import html
from typing import Any
SCRIPT_INTERFACE = "internal-module"
SCRIPT_INTERFACE_REASON = "Imported by render_skill_overview.py to keep overview report layout and CSS out of data rendering."
def bi_span(zh: str, en: str) -> str:
return (
f'<span data-lang="zh-CN">{html.escape(str(zh))}</span>'
f'<span data-lang="en">{html.escape(str(en))}</span>'
)
def render_report_nav(nav_items: list[dict[str, Any]]) -> str:
return "".join(
f"<a href=\"#{html.escape(str(item['href']))}\">{bi_span(str(item['label']), str(item['label_en']))}</a>"
for item in nav_items
)
def render_language_switch() -> str:
return (
'<div class="language-switch" aria-label="语言切换">'
'<button type="button" data-set-lang="zh-CN" aria-pressed="true">简体</button>'
'<button type="button" data-set-lang="en" aria-pressed="false">EN</button>'
"</div>"
)
def skill_overview_css() -> str:
return """
:root {
--paper: #ffffff;
--wash: #f8fafc;
--wash-strong: #f2f5f8;
--line: #e6e0d4;
--line-soft: #eee9df;
--brand: #1B365D;
--brand-soft: #EEF3F8;
--brand-mid: #315982;
--ink: #151515;
--text: #2f2d29;
--muted: #68625a;
--faint: #8b857b;
--success: #2f6f5e;
--warn: #8a5a19;
--serif: "TsangerJinKai02", "Source Han Serif SC", "Noto Serif CJK SC", "Songti SC", "STSong", Charter, Georgia, serif;
--mono: "JetBrains Mono", "SF Mono", ui-monospace, Menlo, Consolas, monospace;
--shadow-soft: 0 1px 2px rgba(27, 54, 93, 0.06), 0 16px 44px rgba(27, 54, 93, 0.08);
}
* { box-sizing: border-box; }
html { scroll-behavior: smooth; }
body {
margin: 0;
background: #ffffff;
color: var(--ink);
font-family: var(--serif);
line-height: 1.62;
letter-spacing: 0;
-webkit-font-smoothing: antialiased;
-moz-osx-font-smoothing: grayscale;
text-rendering: optimizeLegibility;
}
body[data-report-lang="zh-CN"] [data-lang="en"],
body[data-report-lang="en"] [data-lang="zh-CN"] { display: none !important; }
.skip-link {
position: fixed;
left: 18px;
top: 10px;
z-index: 40;
transform: translateY(-140%);
padding: 8px 12px;
border-radius: 8px;
background: var(--brand);
color: #fff;
text-decoration: none;
transition: transform 160ms cubic-bezier(0.16, 1, 0.3, 1);
}
.skip-link:focus-visible { transform: translateY(0); outline: 2px solid var(--brand-mid); outline-offset: 2px; }
.topbar {
position: sticky;
top: 0;
z-index: 20;
background: rgba(255, 255, 255, 0.96);
border-bottom: 1px solid var(--line);
}
.progress-track {
height: 2px;
background: transparent;
}
.progress-bar {
display: block;
width: 100%;
height: 100%;
background: var(--brand);
transition: transform 160ms cubic-bezier(0.16, 1, 0.3, 1);
transform-origin: left center;
transform: scaleX(0);
}
.topbar-inner {
max-width: 1240px;
margin: 0 auto;
padding: 9px 28px;
display: grid;
grid-template-columns: minmax(0, 1fr) auto;
gap: 18px;
align-items: center;
}
.nav-shell {
display: grid;
grid-template-columns: auto minmax(0, 1fr);
gap: 18px;
align-items: center;
min-width: 0;
}
.report-mark {
color: var(--brand);
font-family: var(--mono);
font-size: 11px;
line-height: 1;
text-transform: uppercase;
white-space: nowrap;
}
.report-nav {
display: flex;
gap: 4px;
overflow-x: auto;
scrollbar-width: none;
min-width: 0;
}
.report-nav::-webkit-scrollbar { display: none; }
.report-nav a {
flex: 0 0 auto;
min-width: 76px;
min-height: 40px;
display: inline-flex;
align-items: center;
justify-content: center;
padding: 0 10px;
color: var(--brand);
text-decoration: none;
text-align: center;
font-size: 13px;
border-radius: 8px;
white-space: nowrap;
transition-property: background-color, color, transform;
transition-duration: 160ms;
transition-timing-function: cubic-bezier(0.16, 1, 0.3, 1);
}
@media (hover: hover) {
.report-nav a:hover { background: var(--brand-soft); }
}
.report-nav a:focus-visible {
outline: 2px solid var(--brand-mid);
outline-offset: 2px;
background: var(--brand-soft);
}
.report-nav a[aria-current="true"] {
background: var(--brand);
color: #ffffff;
}
.report-nav a[aria-current="true"] span { color: #ffffff; }
.language-switch {
display: inline-flex;
gap: 3px;
padding: 3px;
border: 1px solid var(--line);
border-radius: 8px;
background: var(--paper);
box-shadow: 0 1px 2px rgba(27, 54, 93, 0.05);
}
.language-switch button {
appearance: none;
min-width: 42px;
min-height: 34px;
border: 0;
border-radius: 6px;
padding: 0 10px;
background: transparent;
color: var(--muted);
font: inherit;
font-size: 13px;
cursor: pointer;
transition-property: background-color, color, transform;
transition-duration: 160ms;
transition-timing-function: cubic-bezier(0.16, 1, 0.3, 1);
}
.language-switch button:active { transform: scale(0.96); }
.language-switch button:focus-visible { outline: 2px solid var(--brand-mid); outline-offset: 2px; }
.language-switch button[aria-pressed="true"] {
background: var(--brand-soft);
color: var(--brand);
}
.wrap {
max-width: 1240px;
margin: 0 auto;
padding: 58px 28px 92px;
}
.hero {
padding: 16px 0 34px;
}
.hero-grid {
display: grid;
grid-template-columns: minmax(0, 1fr) 360px;
gap: 44px;
align-items: end;
}
.eyebrow, .report-mark {
letter-spacing: 0;
}
.eyebrow {
margin: 0 0 12px;
color: var(--brand);
font-family: var(--mono);
font-size: 12px;
text-transform: uppercase;
}
.slug {
margin: 0 0 18px;
color: var(--faint);
font-family: var(--mono);
font-size: 13px;
overflow-wrap: anywhere;
}
h1, h2, h3 {
margin: 0;
font-weight: 500;
letter-spacing: 0;
text-wrap: balance;
}
h1 {
max-width: 8em;
color: var(--ink);
font-size: 4rem;
line-height: 1.02;
}
.lead {
max-width: 760px;
margin: 20px 0 0;
color: var(--text);
font-size: 1.08rem;
text-wrap: pretty;
}
.hero-meta, .badges {
display: flex;
flex-wrap: wrap;
gap: 8px;
margin-top: 20px;
}
.hero-meta span, .badges span, .tag {
display: inline-flex;
align-items: center;
min-height: 30px;
padding: 5px 10px;
border-radius: 6px;
background: var(--brand-soft);
color: var(--brand);
font-size: 13px;
font-variant-numeric: tabular-nums;
}
.hero-card {
position: relative;
padding: 22px 22px 24px;
border-radius: 8px;
background: linear-gradient(180deg, #ffffff 0%, #fbfaf7 100%);
box-shadow: var(--shadow-soft);
border: 1px solid var(--line-soft);
}
.hero-card::before {
content: "";
position: absolute;
top: 18px;
right: 18px;
width: 38px;
height: 2px;
background: var(--brand);
}
.score-strip {
display: grid;
grid-template-columns: repeat(4, minmax(0, 1fr));
gap: 10px;
margin-top: 32px;
padding-top: 20px;
border-top: 1px solid var(--line);
}
.score-chip {
padding: 14px 14px 12px;
border-radius: 8px;
background: var(--wash);
border: 1px solid var(--line-soft);
}
.score-chip span {
display: block;
color: var(--muted);
font-size: 12px;
}
.score-chip strong {
display: block;
margin: 5px 0 8px;
color: var(--brand);
font-family: var(--mono);
font-size: 1.65rem;
font-weight: 500;
line-height: 1;
font-variant-numeric: tabular-nums;
}
.score-chip i {
display: block;
height: 3px;
border-radius: 999px;
background: linear-gradient(90deg, var(--brand) var(--score), #dfe6ee var(--score));
}
.score-chip small {
display: block;
margin-top: 8px;
color: var(--muted);
font-size: 12px;
line-height: 1.45;
}
section {
scroll-margin-top: 78px;
padding-top: 44px;
margin-top: 44px;
border-top: 1px solid var(--line);
}
section.hero {
scroll-margin-top: 0;
padding-top: 16px;
margin-top: 0;
border-top: 0;
}
.section-head {
display: grid;
grid-template-columns: minmax(0, 246px) minmax(0, 1fr);
gap: 36px;
align-items: start;
}
h2 {
color: var(--ink);
font-size: 1.5rem;
line-height: 1.18;
}
h2::before {
content: "";
display: block;
width: 32px;
height: 2px;
margin-bottom: 12px;
background: var(--brand);
}
h3 {
color: var(--ink);
font-size: 1.02rem;
line-height: 1.3;
margin-bottom: 10px;
}
.section-head p {
margin: 12px 0 0;
color: var(--muted);
max-width: 43ch;
text-wrap: pretty;
}
.two-col, .metric-grid, .chart-grid {
display: grid;
grid-template-columns: repeat(2, minmax(0, 1fr));
gap: 16px;
align-items: stretch;
}
.quality-panels {
margin-top: 16px;
}
.metrics-stack {
display: grid;
gap: 18px;
}
.metrics-lead {
display: grid;
grid-template-columns: minmax(420px, 1.15fr) minmax(300px, 0.85fr);
gap: 18px;
align-items: stretch;
}
.metrics-note {
display: grid;
align-content: start;
gap: 16px;
}
.metrics-note p {
margin: 0;
max-width: none;
color: var(--text);
}
.metric-summary-list {
margin: 0;
padding: 0;
list-style: none;
display: grid;
gap: 10px;
}
.metric-summary-list li {
display: grid;
grid-template-columns: auto minmax(0, 1fr) auto;
gap: 8px 10px;
align-items: baseline;
padding: 10px 0;
border-bottom: 1px solid var(--line-soft);
}
.metric-summary-list li:last-child { border-bottom: 0; }
.metric-summary-list b {
color: var(--ink);
font-weight: 500;
}
.metric-summary-list em {
color: var(--brand);
font-family: var(--mono);
font-style: normal;
font-variant-numeric: tabular-nums;
}
.metric-summary-list small {
grid-column: 2 / 4;
color: var(--muted);
line-height: 1.5;
}
.metric-status {
display: inline-flex;
align-items: center;
min-height: 24px;
padding: 2px 7px;
border-radius: 6px;
background: var(--brand-soft);
color: var(--brand);
font-size: 12px;
}
.metric-grid {
grid-template-columns: repeat(2, minmax(0, 1fr));
margin-top: 2px;
}
.list, .compact-list, .step-list {
margin: 0;
padding-left: 1.15em;
display: grid;
gap: 8px;
}
.list li::marker, .compact-list li::marker, .step-list li::marker { color: var(--brand); }
.compact-list {
gap: 6px;
font-size: 13px;
color: var(--muted);
}
.panel, .metric-card, .roadmap-item {
background: #ffffff;
border: 1px solid var(--line-soft);
border-radius: 8px;
padding: 22px;
box-shadow: 0 1px 2px rgba(27, 54, 93, 0.04);
}
.metric-card {
display: grid;
grid-template-columns: 92px minmax(0, 1fr);
gap: 18px;
align-content: start;
min-height: 0;
}
.metric-card-head {
display: grid;
align-content: start;
}
.metric-card strong {
display: block;
margin: 8px 0 10px;
color: var(--brand);
font-family: var(--mono);
font-size: 2rem;
font-weight: 500;
line-height: 1;
font-variant-numeric: tabular-nums;
}
.metric-label {
color: var(--muted);
font-size: 13px;
}
.metric-card-body {
min-width: 0;
}
.chart-figure {
margin: 0;
padding: 18px;
border: 1px solid var(--line-soft);
border-radius: 8px;
background: #ffffff;
box-shadow: 0 1px 2px rgba(27, 54, 93, 0.04);
}
.chart-figure svg {
width: 100%;
height: auto;
display: block;
overflow: visible;
}
.chart-figure text {
fill: var(--ink);
font-family: var(--serif);
font-size: 13px;
}
.chart-title {
fill: var(--brand);
font-size: 16px;
font-weight: 500;
}
.chart-line {
fill: none;
stroke: var(--brand);
stroke-width: 2;
}
figcaption {
margin-top: 12px;
padding-top: 10px;
border-top: 1px solid var(--line-soft);
color: var(--muted);
font-size: 13px;
line-height: 1.5;
text-wrap: pretty;
}
table {
width: 100%;
border-collapse: collapse;
font-size: 14px;
}
th, td {
padding: 12px 10px;
text-align: left;
border-bottom: 1px solid var(--line-soft);
vertical-align: top;
}
th {
color: var(--brand);
font-weight: 500;
font-size: 12px;
}
td:first-child, th:first-child { width: 96px; }
.roadmap {
display: grid;
grid-template-columns: repeat(3, minmax(0, 1fr));
gap: 16px;
}
.step {
display: inline-flex;
margin-bottom: 12px;
min-height: 28px;
align-items: center;
padding: 3px 8px;
border-radius: 6px;
background: var(--brand-soft);
color: var(--brand);
font-size: 12px;
}
.unlock {
margin-top: 14px;
color: var(--muted);
font-size: 13px;
}
@media (max-width: 980px) {
.topbar-inner {
grid-template-columns: minmax(0, 1fr) auto;
padding: 8px 16px;
}
.nav-shell { grid-template-columns: 1fr; gap: 6px; }
.report-mark { display: none; }
.report-nav a { min-width: 72px; }
.hero-grid, .section-head { grid-template-columns: 1fr; }
.hero-grid { gap: 24px; }
.score-strip { grid-template-columns: repeat(2, minmax(0, 1fr)); }
.metrics-lead, .two-col, .metric-grid, .chart-grid, .roadmap { grid-template-columns: 1fr; }
.metric-card { grid-template-columns: 86px minmax(0, 1fr); }
h1 { font-size: 2.75rem; }
}
@media (max-width: 540px) {
.wrap { padding: 34px 16px 72px; }
.topbar-inner { gap: 10px; }
.report-nav {
display: flex;
gap: 2px;
}
.report-nav a {
min-width: 66px;
min-height: 38px;
padding: 0 8px;
font-size: 12px;
}
.language-switch button { min-width: 38px; min-height: 32px; padding: 0 8px; }
.hero { padding-top: 8px; }
h1 { max-width: 8em; font-size: 2.35rem; }
.lead { font-size: 1rem; }
.hero-meta span, .badges span { font-size: 12px; }
.score-strip { grid-template-columns: 1fr; }
section { margin-top: 34px; padding-top: 34px; }
.panel, .metric-card, .roadmap-item, .chart-figure, .hero-card { padding: 18px; }
.metric-card { grid-template-columns: 1fr; gap: 10px; }
.metric-card strong { margin-bottom: 2px; }
.metric-summary-list li { grid-template-columns: auto minmax(0, 1fr) auto; }
table { font-size: 13px; }
th, td { padding: 10px 7px; }
}
@media (prefers-reduced-motion: reduce) {
html { scroll-behavior: auto; }
*, *::before, *::after { transition-duration: 0.01ms !important; }
}
""".strip()
def skill_overview_script() -> str:
return """
(function () {
var buttons = Array.prototype.slice.call(document.querySelectorAll("[data-set-lang]"));
var navLinks = Array.prototype.slice.call(document.querySelectorAll(".report-nav a"));
var sections = navLinks
.map(function (link) { return document.querySelector(link.getAttribute("href")); })
.filter(Boolean);
var progressBar = document.querySelector(".progress-bar");
function setLanguage(lang) {
document.body.setAttribute("data-report-lang", lang);
document.documentElement.setAttribute("lang", lang);
buttons.forEach(function (button) {
button.setAttribute("aria-pressed", button.getAttribute("data-set-lang") === lang ? "true" : "false");
});
}
function updateProgress() {
var scrollTop = window.scrollY || document.documentElement.scrollTop;
var height = Math.max(1, document.documentElement.scrollHeight - window.innerHeight);
var pct = Math.min(100, Math.max(0, (scrollTop / height) * 100));
if (progressBar) progressBar.style.transform = "scaleX(" + pct / 100 + ")";
var active = sections[0];
sections.forEach(function (section) {
if (section.getBoundingClientRect().top <= 110) active = section;
});
navLinks.forEach(function (link) {
link.setAttribute("aria-current", link.getAttribute("href") === "#" + active.id ? "true" : "false");
});
}
buttons.forEach(function (button) {
button.addEventListener("click", function () {
setLanguage(button.getAttribute("data-set-lang"));
});
});
window.addEventListener("scroll", updateProgress, { passive: true });
window.addEventListener("resize", updateProgress);
setLanguage("zh-CN");
updateProgress();
})();
""".strip()
scripts/yao.py
+14 -225
View File
@@ -7,65 +7,29 @@ from pathlib import Path
from github_benchmark_scan import build_query
from render_intent_confidence import assess_intent_confidence
from yao_cli_config import (
ARCHETYPE_MODE,
archetype_guidance,
baseline_compare_args,
diagnose_skill_candidates,
diagnosis_note,
discovery_summary,
infer_archetype,
local_output_runner_command,
recommendation_from_synthesis,
reference_visibility,
resolve_promotion_target,
resolve_target,
)
ROOT = Path(__file__).resolve().parent.parent
SCRIPTS = ROOT / "scripts"
TARGETS = {
"root": {
"description_file": ROOT / "SKILL.md",
"baseline_description_file": ROOT / "evals" / "baseline_description.txt",
"semantic_config": ROOT / "evals" / "semantic_config.json",
"dev_cases": ROOT / "evals" / "dev" / "trigger_cases.json",
"holdout_cases": ROOT / "evals" / "holdout" / "trigger_cases.json",
"blind_holdout_cases": ROOT / "evals" / "blind_holdout" / "trigger_cases.json",
"adversarial_cases": ROOT / "evals" / "adversarial" / "trigger_cases.json",
"output_json": ROOT / "reports" / "description_optimization.json",
"output_md": ROOT / "reports" / "description_optimization.md",
"title": "Root Description Optimization",
},
"team-frontend-review": {
"description_file": ROOT / "examples" / "team-frontend-review" / "generated-skill" / "SKILL.md",
"baseline_description_file": ROOT / "examples" / "team-frontend-review" / "optimization" / "baseline_description.txt",
"semantic_config": ROOT / "examples" / "team-frontend-review" / "optimization" / "semantic_config.json",
"dev_cases": ROOT / "examples" / "team-frontend-review" / "optimization" / "dev" / "trigger_cases.json",
"holdout_cases": ROOT / "examples" / "team-frontend-review" / "optimization" / "holdout" / "trigger_cases.json",
"blind_holdout_cases": ROOT / "examples" / "team-frontend-review" / "optimization" / "blind_holdout" / "trigger_cases.json",
"adversarial_cases": ROOT / "examples" / "team-frontend-review" / "optimization" / "adversarial" / "trigger_cases.json",
"output_json": ROOT / "examples" / "team-frontend-review" / "optimization" / "reports" / "description_optimization.json",
"output_md": ROOT / "examples" / "team-frontend-review" / "optimization" / "reports" / "description_optimization.md",
"title": "Frontend Review Description Optimization",
},
"governed-incident-command": {
"description_file": ROOT / "examples" / "governed-incident-command" / "generated-skill" / "SKILL.md",
"baseline_description_file": ROOT / "examples" / "governed-incident-command" / "optimization" / "baseline_description.txt",
"semantic_config": ROOT / "examples" / "governed-incident-command" / "optimization" / "semantic_config.json",
"dev_cases": ROOT / "examples" / "governed-incident-command" / "optimization" / "dev" / "trigger_cases.json",
"holdout_cases": ROOT / "examples" / "governed-incident-command" / "optimization" / "holdout" / "trigger_cases.json",
"blind_holdout_cases": ROOT / "examples" / "governed-incident-command" / "optimization" / "blind_holdout" / "trigger_cases.json",
"adversarial_cases": ROOT / "examples" / "governed-incident-command" / "optimization" / "adversarial" / "trigger_cases.json",
"output_json": ROOT / "examples" / "governed-incident-command" / "optimization" / "reports" / "description_optimization.json",
"output_md": ROOT / "examples" / "governed-incident-command" / "optimization" / "reports" / "description_optimization.md",
"title": "Governed Incident Description Optimization",
},
}
PROMOTION_TARGETS = {
"root": "yao-meta-skill",
"team-frontend-review": "team-frontend-review",
"governed-incident-command": "governed-incident-command",
}
def script_path(name: str) -> str:
return str(SCRIPTS / name)
def local_output_runner_command() -> str:
return json.dumps(["python3", "scripts/local_output_eval_runner.py"])
def load_json_maybe(text: str) -> dict | None:
text = text.strip()
if not text:
@@ -94,33 +58,6 @@ def run_script(name: str, args: list[str], cwd: Path | None = None) -> dict:
}
def resolve_target(name: str) -> dict:
if name not in TARGETS:
raise KeyError(f"Unknown target: {name}")
return TARGETS[name]
def resolve_promotion_target(name: str) -> str:
if name not in PROMOTION_TARGETS:
raise KeyError(f"Unknown promotion target: {name}")
return PROMOTION_TARGETS[name]
def baseline_compare_args() -> list[str]:
args = []
for label, target in TARGETS.items():
args.extend(["--entry", f"{label}::{target['output_json']}"])
args.extend(
[
"--output-json",
str(ROOT / "reports" / "baseline-compare.json"),
"--output-md",
str(ROOT / "reports" / "baseline-compare.md"),
]
)
return args
def prompt_with_default(label: str, default: str) -> str:
sys.stderr.write(f"{label} [{default}]: ")
sys.stderr.flush()
@@ -165,154 +102,6 @@ def intent_confidence_note(summary: dict) -> str:
return "\n".join(lines) + "\n"
ARCHETYPE_MODE = {
"scaffold": "scaffold",
"production": "production",
"library": "library",
"governed": "governed",
}
def infer_archetype(job: str, description: str) -> tuple[str, str]:
text = f"{job} {description}".lower()
if any(token in text for token in ("incident", "compliance", "security", "release", "govern", "audit", "policy")):
return "governed", "The request looks operationally sensitive, so governed is the safest default."
if any(token in text for token in ("shared", "cross-team", "library", "portable", "platform", "reusable across")):
return "library", "The request signals multi-team reuse or portability, so library is the better fit."
if any(token in text for token in ("review", "checklist", "team", "workflow", "process", "standardize")):
return "production", "The request looks team-reused and repeatable, so production fits better than scaffold."
return "scaffold", "The request still looks exploratory or lightweight, so scaffold keeps the first package lean."
def archetype_guidance(archetype: str) -> dict:
mapping = {
"scaffold": {
"first_gate": "trigger and exclusions",
"focus": "keep the first package small and avoid governance overhead",
},
"production": {
"first_gate": "trigger plus one execution or eval asset",
"focus": "make the package reliable for team reuse",
},
"library": {
"first_gate": "trigger, portability, and packaging semantics",
"focus": "treat the package as a shared capability with visible evidence",
},
"governed": {
"first_gate": "trigger, governance, and review cadence",
"focus": "treat the package as a high-trust asset from the start",
},
}
return mapping.get(archetype, mapping["scaffold"])
def discovery_summary(job: str, primary_output: str, archetype: str, guidance: dict) -> str:
return (
"\nHere's the shape I'm hearing so far:\n"
f"- Repeated job: {job}\n"
f"- Desired hand-back: {primary_output}\n"
f"- Best starting archetype: {archetype}\n"
f"- First gate: {guidance['first_gate']}\n"
f"- Current focus: {guidance['focus']}\n"
)
def explicit_skill_request(job: str, description: str) -> bool:
text = f"{job} {description}".lower()
return any(token in text for token in ("skill", "workflow", "checklist", "package", "automate", "standardize"))
def diagnose_skill_candidates(job: str, primary_output: str, archetype: str, confidence: dict) -> dict:
fuzzy = not explicit_skill_request(job, primary_output) or confidence.get("score", 0) < 75
candidates = [
{
"shape": archetype,
"recommendation": "recommended",
"why_it_fits": "This is the lightest shape that matches the current recurring job signal.",
"limitation": "It should not deepen until the concrete output and exclusion boundary are clear.",
"first_pass": "Create one routeable skill with honest boundaries, one review report, and one next-step direction.",
}
]
if archetype != "scaffold":
candidates.append(
{
"shape": "scaffold",
"recommendation": "fallback",
"why_it_fits": "Use this if the idea is still exploratory or personal.",
"limitation": "It may under-serve team reuse, portability, or governance needs.",
"first_pass": "Ship only SKILL.md, interface metadata, intent confidence, and review viewer.",
}
)
if archetype not in {"production", "governed"}:
candidates.append(
{
"shape": "production",
"recommendation": "upgrade path",
"why_it_fits": "Use this when the workflow will be repeated by a team or needs consistent outputs.",
"limitation": "It adds validation and review cost that a personal scaffold may not need.",
"first_pass": "Add one practical eval or execution check after the trigger boundary is stable.",
}
)
if archetype != "governed" and any(token in f"{job} {primary_output}".lower() for token in ("risk", "audit", "release", "policy", "security", "compliance")):
candidates.append(
{
"shape": "governed",
"recommendation": "risk path",
"why_it_fits": "Use this if the skill affects operational, compliance, security, or release decisions.",
"limitation": "It is too heavy unless ownership and review cadence are real.",
"first_pass": "Add owner, review cadence, lifecycle metadata, and reviewer-visible evidence.",
}
)
return {
"mode": "fuzzy-problem-diagnosis" if fuzzy else "direct-skill-shaping",
"fuzzy": fuzzy,
"candidates": candidates[:3],
}
def diagnosis_note(diagnosis: dict) -> str:
lines = ["\nProblem-to-skill diagnosis:"]
for candidate in diagnosis["candidates"]:
lines.append(
f"- {candidate['shape']} ({candidate['recommendation']}): {candidate['why_it_fits']} "
f"First pass: {candidate['first_pass']}"
)
return "\n".join(lines) + "\n"
def reference_visibility(reference_synthesis: dict) -> dict:
synthesis = reference_synthesis.get("synthesis", {}) if isinstance(reference_synthesis, dict) else {}
visibility = synthesis.get("visibility", {}) if isinstance(synthesis, dict) else {}
reasons = list(visibility.get("reasons", []))
mode = visibility.get("mode", "explicit" if reasons else "silent")
return {
"mode": mode,
"user_decision_required": mode == "explicit",
"reasons": reasons,
"conflicts": synthesis.get("conflicts", []),
}
def recommendation_from_synthesis(reference_synthesis: dict, visibility: dict) -> dict:
synthesis = reference_synthesis.get("synthesis", {}) if isinstance(reference_synthesis, dict) else {}
recommendation = synthesis.get("recommendation", {}) if isinstance(synthesis, dict) else {}
borrow_now = recommendation.get("borrow_now") or synthesis.get("borrow_now", [])
avoid_now = recommendation.get("avoid_for_now") or synthesis.get("avoid_now", [])
summary = recommendation.get("summary") or (
f"Start with {borrow_now[0]} Avoid {avoid_now[0]} for the first pass."
if borrow_now and avoid_now
else "Start with the smallest high-confidence pattern and keep the first pass light."
)
why = recommendation.get("why") or "This recommendation comes from the benchmark synthesis and current intent confidence."
return {
"summary": summary,
"borrow_now": borrow_now[:2],
"avoid_for_now": avoid_now[:2],
"why": why,
"user_decision_required": visibility["user_decision_required"],
}
def maybe_emit_update_notice(args: argparse.Namespace) -> None:
if getattr(args, "no_update_check", False):
return
scripts/yao_cli_config.py
+235
View File
@@ -0,0 +1,235 @@
#!/usr/bin/env python3
"""Pure configuration and shaping helpers for the Yao CLI."""
import json
from pathlib import Path
SCRIPT_INTERFACE = "internal-module"
SCRIPT_INTERFACE_REASON = "Imported by yao.py for CLI target maps and side-effect-free shaping helpers."
ROOT = Path(__file__).resolve().parent.parent
TARGETS = {
"root": {
"description_file": ROOT / "SKILL.md",
"baseline_description_file": ROOT / "evals" / "baseline_description.txt",
"semantic_config": ROOT / "evals" / "semantic_config.json",
"dev_cases": ROOT / "evals" / "dev" / "trigger_cases.json",
"holdout_cases": ROOT / "evals" / "holdout" / "trigger_cases.json",
"blind_holdout_cases": ROOT / "evals" / "blind_holdout" / "trigger_cases.json",
"adversarial_cases": ROOT / "evals" / "adversarial" / "trigger_cases.json",
"output_json": ROOT / "reports" / "description_optimization.json",
"output_md": ROOT / "reports" / "description_optimization.md",
"title": "Root Description Optimization",
},
"team-frontend-review": {
"description_file": ROOT / "examples" / "team-frontend-review" / "generated-skill" / "SKILL.md",
"baseline_description_file": ROOT / "examples" / "team-frontend-review" / "optimization" / "baseline_description.txt",
"semantic_config": ROOT / "examples" / "team-frontend-review" / "optimization" / "semantic_config.json",
"dev_cases": ROOT / "examples" / "team-frontend-review" / "optimization" / "dev" / "trigger_cases.json",
"holdout_cases": ROOT / "examples" / "team-frontend-review" / "optimization" / "holdout" / "trigger_cases.json",
"blind_holdout_cases": ROOT / "examples" / "team-frontend-review" / "optimization" / "blind_holdout" / "trigger_cases.json",
"adversarial_cases": ROOT / "examples" / "team-frontend-review" / "optimization" / "adversarial" / "trigger_cases.json",
"output_json": ROOT / "examples" / "team-frontend-review" / "optimization" / "reports" / "description_optimization.json",
"output_md": ROOT / "examples" / "team-frontend-review" / "optimization" / "reports" / "description_optimization.md",
"title": "Frontend Review Description Optimization",
},
"governed-incident-command": {
"description_file": ROOT / "examples" / "governed-incident-command" / "generated-skill" / "SKILL.md",
"baseline_description_file": ROOT / "examples" / "governed-incident-command" / "optimization" / "baseline_description.txt",
"semantic_config": ROOT / "examples" / "governed-incident-command" / "optimization" / "semantic_config.json",
"dev_cases": ROOT / "examples" / "governed-incident-command" / "optimization" / "dev" / "trigger_cases.json",
"holdout_cases": ROOT / "examples" / "governed-incident-command" / "optimization" / "holdout" / "trigger_cases.json",
"blind_holdout_cases": ROOT / "examples" / "governed-incident-command" / "optimization" / "blind_holdout" / "trigger_cases.json",
"adversarial_cases": ROOT / "examples" / "governed-incident-command" / "optimization" / "adversarial" / "trigger_cases.json",
"output_json": ROOT / "examples" / "governed-incident-command" / "optimization" / "reports" / "description_optimization.json",
"output_md": ROOT / "examples" / "governed-incident-command" / "optimization" / "reports" / "description_optimization.md",
"title": "Governed Incident Description Optimization",
},
}
PROMOTION_TARGETS = {
"root": "yao-meta-skill",
"team-frontend-review": "team-frontend-review",
"governed-incident-command": "governed-incident-command",
}
ARCHETYPE_MODE = {
"scaffold": "scaffold",
"production": "production",
"library": "library",
"governed": "governed",
}
def local_output_runner_command() -> str:
return json.dumps(["python3", "scripts/local_output_eval_runner.py"])
def resolve_target(name: str) -> dict:
if name not in TARGETS:
raise KeyError(f"Unknown target: {name}")
return TARGETS[name]
def resolve_promotion_target(name: str) -> str:
if name not in PROMOTION_TARGETS:
raise KeyError(f"Unknown promotion target: {name}")
return PROMOTION_TARGETS[name]
def baseline_compare_args() -> list[str]:
args = []
for label, target in TARGETS.items():
args.extend(["--entry", f"{label}::{target['output_json']}"])
args.extend(
[
"--output-json",
str(ROOT / "reports" / "baseline-compare.json"),
"--output-md",
str(ROOT / "reports" / "baseline-compare.md"),
]
)
return args
def infer_archetype(job: str, description: str) -> tuple[str, str]:
text = f"{job} {description}".lower()
if any(token in text for token in ("incident", "compliance", "security", "release", "govern", "audit", "policy")):
return "governed", "The request looks operationally sensitive, so governed is the safest default."
if any(token in text for token in ("shared", "cross-team", "library", "portable", "platform", "reusable across")):
return "library", "The request signals multi-team reuse or portability, so library is the better fit."
if any(token in text for token in ("review", "checklist", "team", "workflow", "process", "standardize")):
return "production", "The request looks team-reused and repeatable, so production fits better than scaffold."
return "scaffold", "The request still looks exploratory or lightweight, so scaffold keeps the first package lean."
def archetype_guidance(archetype: str) -> dict:
mapping = {
"scaffold": {
"first_gate": "trigger and exclusions",
"focus": "keep the first package small and avoid governance overhead",
},
"production": {
"first_gate": "trigger plus one execution or eval asset",
"focus": "make the package reliable for team reuse",
},
"library": {
"first_gate": "trigger, portability, and packaging semantics",
"focus": "treat the package as a shared capability with visible evidence",
},
"governed": {
"first_gate": "trigger, governance, and review cadence",
"focus": "treat the package as a high-trust asset from the start",
},
}
return mapping.get(archetype, mapping["scaffold"])
def discovery_summary(job: str, primary_output: str, archetype: str, guidance: dict) -> str:
return (
"\nHere's the shape I'm hearing so far:\n"
f"- Repeated job: {job}\n"
f"- Desired hand-back: {primary_output}\n"
f"- Best starting archetype: {archetype}\n"
f"- First gate: {guidance['first_gate']}\n"
f"- Current focus: {guidance['focus']}\n"
)
def explicit_skill_request(job: str, description: str) -> bool:
text = f"{job} {description}".lower()
return any(token in text for token in ("skill", "workflow", "checklist", "package", "automate", "standardize"))
def diagnose_skill_candidates(job: str, primary_output: str, archetype: str, confidence: dict) -> dict:
fuzzy = not explicit_skill_request(job, primary_output) or confidence.get("score", 0) < 75
candidates = [
{
"shape": archetype,
"recommendation": "recommended",
"why_it_fits": "This is the lightest shape that matches the current recurring job signal.",
"limitation": "It should not deepen until the concrete output and exclusion boundary are clear.",
"first_pass": "Create one routeable skill with honest boundaries, one review report, and one next-step direction.",
}
]
if archetype != "scaffold":
candidates.append(
{
"shape": "scaffold",
"recommendation": "fallback",
"why_it_fits": "Use this if the idea is still exploratory or personal.",
"limitation": "It may under-serve team reuse, portability, or governance needs.",
"first_pass": "Ship only SKILL.md, interface metadata, intent confidence, and review viewer.",
}
)
if archetype not in {"production", "governed"}:
candidates.append(
{
"shape": "production",
"recommendation": "upgrade path",
"why_it_fits": "Use this when the workflow will be repeated by a team or needs consistent outputs.",
"limitation": "It adds validation and review cost that a personal scaffold may not need.",
"first_pass": "Add one practical eval or execution check after the trigger boundary is stable.",
}
)
if archetype != "governed" and any(token in f"{job} {primary_output}".lower() for token in ("risk", "audit", "release", "policy", "security", "compliance")):
candidates.append(
{
"shape": "governed",
"recommendation": "risk path",
"why_it_fits": "Use this if the skill affects operational, compliance, security, or release decisions.",
"limitation": "It is too heavy unless ownership and review cadence are real.",
"first_pass": "Add owner, review cadence, lifecycle metadata, and reviewer-visible evidence.",
}
)
return {
"mode": "fuzzy-problem-diagnosis" if fuzzy else "direct-skill-shaping",
"fuzzy": fuzzy,
"candidates": candidates[:3],
}
def diagnosis_note(diagnosis: dict) -> str:
lines = ["\nProblem-to-skill diagnosis:"]
for candidate in diagnosis["candidates"]:
lines.append(
f"- {candidate['shape']} ({candidate['recommendation']}): {candidate['why_it_fits']} "
f"First pass: {candidate['first_pass']}"
)
return "\n".join(lines) + "\n"
def reference_visibility(reference_synthesis: dict) -> dict:
synthesis = reference_synthesis.get("synthesis", {}) if isinstance(reference_synthesis, dict) else {}
visibility = synthesis.get("visibility", {}) if isinstance(synthesis, dict) else {}
reasons = list(visibility.get("reasons", []))
mode = visibility.get("mode", "explicit" if reasons else "silent")
return {
"mode": mode,
"user_decision_required": mode == "explicit",
"reasons": reasons,
"conflicts": synthesis.get("conflicts", []),
}
def recommendation_from_synthesis(reference_synthesis: dict, visibility: dict) -> dict:
synthesis = reference_synthesis.get("synthesis", {}) if isinstance(reference_synthesis, dict) else {}
recommendation = synthesis.get("recommendation", {}) if isinstance(synthesis, dict) else {}
borrow_now = recommendation.get("borrow_now") or synthesis.get("borrow_now", [])
avoid_now = recommendation.get("avoid_for_now") or synthesis.get("avoid_now", [])
summary = recommendation.get("summary") or (
f"Start with {borrow_now[0]} Avoid {avoid_now[0]} for the first pass."
if borrow_now and avoid_now
else "Start with the smallest high-confidence pattern and keep the first pass light."
)
why = recommendation.get("why") or "This recommendation comes from the benchmark synthesis and current intent confidence."
return {
"summary": summary,
"borrow_now": borrow_now[:2],
"avoid_for_now": avoid_now[:2],
"why": why,
"user_decision_required": visibility["user_decision_required"],
}
skill-ir/examples/yao-meta-skill.json
+5 -1
View File
@@ -154,6 +154,8 @@
"scripts/render_social_preview.py",
"scripts/render_system_model.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_layout.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -161,6 +163,7 @@
"scripts/run_output_execution.py",
"scripts/simulate_install.py",
"scripts/skill_report_charts.py",
"scripts/skill_report_layout.py",
"scripts/skill_report_metrics.py",
"scripts/skill_report_model.py",
"scripts/sync_local_install.py",
@@ -169,7 +172,8 @@
"scripts/upgrade_check.py",
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py"
"scripts/yao.py",
"scripts/yao_cli_config.py"
],
"assets": [
"templates/basic_skill.md.j2",
skill_atlas/catalog.json
+4
View File
@@ -65,6 +65,8 @@
"scripts/render_social_preview.py",
"scripts/render_system_model.py",
"scripts/resource_boundary_check.py",
"scripts/review_studio_formatting.py",
"scripts/review_studio_layout.py",
"scripts/run_conformance_suite.py",
"scripts/run_description_optimization_suite.py",
"scripts/run_eval_suite.py",
@@ -72,6 +74,7 @@
"scripts/run_output_execution.py",
"scripts/simulate_install.py",
"scripts/skill_report_charts.py",
"scripts/skill_report_layout.py",
"scripts/skill_report_metrics.py",
"scripts/skill_report_model.py",
"scripts/sync_local_install.py",
@@ -81,6 +84,7 @@
"scripts/validate_skill.py",
"scripts/verify_package.py",
"scripts/yao.py",
"scripts/yao_cli_config.py",
"references/artifact-design-doctrine.md",
"references/authoring-discipline.md",
"references/distribution-registry-method.md",
tests/verify_review_studio.py
+23
View File
@@ -10,6 +10,8 @@ ROOT = Path(__file__).resolve().parent.parent
SCRIPT = ROOT / "scripts" / "render_review_studio.py"
sys.path.insert(0, str(ROOT / "scripts"))
import render_review_studio as review_studio # noqa: E402
import review_studio_formatting as review_formatting # noqa: E402
import review_studio_layout as review_layout # noqa: E402
def main() -> None:
@@ -353,9 +355,30 @@ def main() -> None:
assert "人工批准" in html, html[:8200]
assert "权限批准" in html, html[:9000]
assert "权限探针" in html, html[:9500]
assert "kv-grid" in html, html
assert "案例数" in html, html
assert "命令执行" in html, html
assert "包体哈希" in html, html
assert "{&#x27;" not in html, html
assert "&#x27;case_count&#x27;" not in html, html
assert "&#x27;name&#x27;" not in html, html
assert "reports/review_waivers.md" in output_json.read_text(encoding="utf-8"), output_json
assert "upgrade minor declared / minor recommended" in html, html[:8000]
assert str(ROOT) not in output_json.read_text(encoding="utf-8"), output_json
formatted = review_formatting.render_kv_grid(
{"case_count": 5, "package_sha256": "abc123"},
["case_count", "package_sha256"],
"missing",
)
assert "kv-grid" in formatted, formatted
assert "案例数" in formatted, formatted
assert "<code>abc123</code>" in formatted, formatted
assert review_formatting.value_text({"case_count": 5}) == "案例数: 5"
assert len(review_layout.REVIEW_STUDIO_NAV) == 15, review_layout.REVIEW_STUDIO_NAV
assert "position: sticky" in review_layout.review_studio_css(), review_layout.review_studio_css()[:400]
assert "#overview" in review_layout.render_review_nav(), review_layout.render_review_nav()
assert "审查总览" in review_layout.render_review_nav(), review_layout.render_review_nav()
assert review_layout.render_review_nav([]) == ""
print(json.dumps({"ok": True}, ensure_ascii=False, indent=2))
tests/verify_skill_overview.py
+28
View File
@@ -7,6 +7,10 @@ from pathlib import Path
ROOT = Path(__file__).resolve().parent.parent
CLI = ROOT / "scripts" / "yao.py"
sys.path.insert(0, str(ROOT / "scripts"))
from skill_report_layout import render_language_switch, render_report_nav, skill_overview_css, skill_overview_script
from skill_report_model import REPORT_NAV_V2
def run(*args: str) -> dict:
@@ -26,6 +30,30 @@ def run(*args: str) -> dict:
def main() -> None:
nav_contract = render_report_nav(REPORT_NAV_V2)
assert nav_contract.count("<a ") == 9, nav_contract
assert '#overview' in nav_contract, nav_contract
assert ">技能概述</span>" in nav_contract, nav_contract
assert ">Overview</span>" in nav_contract, nav_contract
assert render_report_nav([]) == ""
language_switch_contract = render_language_switch()
assert 'data-set-lang="zh-CN"' in language_switch_contract, language_switch_contract
assert 'data-set-lang="en"' in language_switch_contract, language_switch_contract
assert 'aria-pressed="true"' in language_switch_contract, language_switch_contract
css_contract = skill_overview_css()
assert "position: sticky" in css_contract, css_contract[:1200]
assert ".report-nav {" in css_contract, css_contract[:3200]
assert "background: #ffffff" in css_contract, css_contract[:1600]
assert ".metrics-lead" in css_contract, css_contract[:7000]
assert "@media (max-width: 980px)" in css_contract, css_contract[-2200:]
script_contract = skill_overview_script()
assert 'setLanguage("zh-CN")' in script_contract, script_contract[-1000:]
assert "scaleX(" in script_contract, script_contract
assert "aria-current" in script_contract, script_contract
tmp_root = ROOT / "tests" / "tmp_skill_overview"
if tmp_root.exists():
subprocess.run(["rm", "-rf", str(tmp_root)], check=True)
tests/verify_trust_check.py
+8
View File
@@ -87,16 +87,24 @@ def main() -> None:
assert "scripts/github_benchmark_scan.py" in payload["network_policy"]["covered_scripts"], payload["network_policy"]
script_map = {item["path"]: item for item in payload["scripts"]}
for internal_module in [
"scripts/review_studio_formatting.py",
"scripts/review_studio_layout.py",
"scripts/skill_report_charts.py",
"scripts/skill_report_layout.py",
"scripts/skill_report_metrics.py",
"scripts/skill_report_model.py",
"scripts/yao_cli_config.py",
]:
assert script_map[internal_module]["interface"] == "internal-module", script_map[internal_module]
assert script_map[internal_module]["interface_declared"], script_map[internal_module]
warning_text = "\n".join(payload["warnings"])
assert "review_studio_formatting.py" not in warning_text, payload["warnings"]
assert "review_studio_layout.py" not in warning_text, payload["warnings"]
assert "skill_report_charts.py" not in warning_text, payload["warnings"]
assert "skill_report_layout.py" not in warning_text, payload["warnings"]
assert "skill_report_metrics.py" not in warning_text, payload["warnings"]
assert "skill_report_model.py" not in warning_text, payload["warnings"]
assert "yao_cli_config.py" not in warning_text, payload["warnings"]
assert "render_context_reports.py" not in warning_text, payload["warnings"]
assert "render_social_preview.py" not in warning_text, payload["warnings"]
assert "Network-capable scripts require bounded host policy" not in warning_text, payload["warnings"]
tests/verify_yao_cli.py
+7
View File
@@ -9,6 +9,8 @@ from pathlib import Path
ROOT = Path(__file__).resolve().parent.parent
CLI = ROOT / "scripts" / "yao.py"
BENCHMARK_FIXTURE_DIR = ROOT / "tests" / "fixtures" / "github_benchmark_scan"
sys.path.insert(0, str(ROOT / "scripts"))
import yao_cli_config # noqa: E402
def run(*args: str, input_text: str | None = None) -> dict:
@@ -36,6 +38,11 @@ def main() -> None:
tmp_root.mkdir(parents=True, exist_ok=True)
remote_version = tmp_root / "remote-version.txt"
remote_version.write_text("9.9.9\n", encoding="utf-8")
assert yao_cli_config.resolve_target("root")["title"] == "Root Description Optimization"
assert yao_cli_config.resolve_promotion_target("root") == "yao-meta-skill"
assert yao_cli_config.infer_archetype("Standardize team review workflow.", "")[0] == "production"
assert yao_cli_config.infer_archetype("Govern release policy.", "")[0] == "governed"
assert "--entry" in yao_cli_config.baseline_compare_args()
init_result = run("init", "cli-demo-skill", "--description", "CLI demo skill.", "--output-dir", str(tmp_root))
assert init_result["ok"], init_result