diff --git a/registry/index.json b/registry/index.json index a26f4c60..0f4bab5f 100644 --- a/registry/index.json +++ b/registry/index.json @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "8b89cae0e2eaf8456b9e97940706576db7ecaf0f46e5de8153c45486f3ab1677" + "package_sha256": "0de594f90374f72387eea382b32ad0dd220d0f1d6f809b8fdd39859a1f35d5b7" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index e5b446c0..2f4669b2 100644 --- a/registry/packages/yao-meta-skill.json +++ b/registry/packages/yao-meta-skill.json @@ -16,8 +16,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "8b89cae0e2eaf8456b9e97940706576db7ecaf0f46e5de8153c45486f3ab1677", - "archive_sha256": "1bb01abccae0984f63251cb73a7782163bcf4b0afb260c73230dcb35da68d0dc" + "package_sha256": "0de594f90374f72387eea382b32ad0dd220d0f1d6f809b8fdd39859a1f35d5b7", + "archive_sha256": "9761608424bbab003651eb643921a13f86b51220de705a3255d7c201e267dc68" }, "compatibility": { "openai": "pass", @@ -48,7 +48,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "1bb01abccae0984f63251cb73a7782163bcf4b0afb260c73230dcb35da68d0dc", + "archive_sha256": "9761608424bbab003651eb643921a13f86b51220de705a3255d7c201e267dc68", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" diff --git a/reports/architecture_maintainability.json b/reports/architecture_maintainability.json index 38c26d1f..ed931160 100644 --- a/reports/architecture_maintainability.json +++ b/reports/architecture_maintainability.json @@ -83,7 +83,7 @@ }, { "path": "tests/verify_review_studio.py", - "lines": 674, + "lines": 677, "kind": "test", "severity": "pass", "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." diff --git a/reports/architecture_maintainability.md b/reports/architecture_maintainability.md index ac57a9e8..8d966937 100644 --- a/reports/architecture_maintainability.md +++ b/reports/architecture_maintainability.md @@ -34,7 +34,7 @@ No file-size hotspots found. | `scripts/optimize_description.py` | `723` | `cli-script` | `pass` | | `scripts/trust_check.py` | `714` | `internal-module` | `pass` | | `scripts/render_review_viewer.py` | `685` | `cli-script` | `pass` | -| `tests/verify_review_studio.py` | `674` | `test` | `pass` | +| `tests/verify_review_studio.py` | `677` | `test` | `pass` | | `scripts/skill_report_layout.py` | `653` | `internal-module` | `pass` | | `scripts/render_reference_synthesis.py` | `644` | `cli-script` | `pass` | diff --git a/reports/compiled_targets.json b/reports/compiled_targets.json index 32a31912..8951f4a6 100644 --- a/reports/compiled_targets.json +++ b/reports/compiled_targets.json @@ -92,6 +92,7 @@ "`Scaffold`: exploratory or personal.", "`Production`: team reuse.", "`Library`: shared infrastructure.", + "`Governed`: high-trust, policy-sensitive, or release-critical.", "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.", "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.", "Do not silently broaden the skill into adjacent jobs just because the examples are nearby." @@ -214,6 +215,7 @@ "scripts/review_studio_gates.py", "scripts/review_studio_layout.py", "scripts/review_studio_output_review.py", + "scripts/review_studio_waivers.py", "scripts/review_studio_world_class.py", "scripts/review_viewer_data.py", "scripts/run_conformance_suite.py", @@ -223,8 +225,7 @@ "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_layout.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -941,6 +942,7 @@ "`Scaffold`: exploratory or personal.", "`Production`: team reuse.", "`Library`: shared infrastructure.", + "`Governed`: high-trust, policy-sensitive, or release-critical.", "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.", "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.", "Do not silently broaden the skill into adjacent jobs just because the examples are nearby." @@ -1063,6 +1065,7 @@ "scripts/review_studio_gates.py", "scripts/review_studio_layout.py", "scripts/review_studio_output_review.py", + "scripts/review_studio_waivers.py", "scripts/review_studio_world_class.py", "scripts/review_viewer_data.py", "scripts/run_conformance_suite.py", @@ -1072,8 +1075,7 @@ "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_layout.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -1790,6 +1792,7 @@ "`Scaffold`: exploratory or personal.", "`Production`: team reuse.", "`Library`: shared infrastructure.", + "`Governed`: high-trust, policy-sensitive, or release-critical.", "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.", "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.", "Do not silently broaden the skill into adjacent jobs just because the examples are nearby." @@ -1912,6 +1915,7 @@ "scripts/review_studio_gates.py", "scripts/review_studio_layout.py", "scripts/review_studio_output_review.py", + "scripts/review_studio_waivers.py", "scripts/review_studio_world_class.py", "scripts/review_viewer_data.py", "scripts/run_conformance_suite.py", @@ -1921,8 +1925,7 @@ "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_layout.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -2623,6 +2626,7 @@ "`Scaffold`: exploratory or personal.", "`Production`: team reuse.", "`Library`: shared infrastructure.", + "`Governed`: high-trust, policy-sensitive, or release-critical.", "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.", "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.", "Do not silently broaden the skill into adjacent jobs just because the examples are nearby." @@ -2745,6 +2749,7 @@ "scripts/review_studio_gates.py", "scripts/review_studio_layout.py", "scripts/review_studio_output_review.py", + "scripts/review_studio_waivers.py", "scripts/review_studio_world_class.py", "scripts/review_viewer_data.py", "scripts/run_conformance_suite.py", @@ -2754,8 +2759,7 @@ "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_layout.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -3456,6 +3460,7 @@ "`Scaffold`: exploratory or personal.", "`Production`: team reuse.", "`Library`: shared infrastructure.", + "`Governed`: high-trust, policy-sensitive, or release-critical.", "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.", "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.", "Do not silently broaden the skill into adjacent jobs just because the examples are nearby." @@ -3578,6 +3583,7 @@ "scripts/review_studio_gates.py", "scripts/review_studio_layout.py", "scripts/review_studio_output_review.py", + "scripts/review_studio_waivers.py", "scripts/review_studio_world_class.py", "scripts/review_viewer_data.py", "scripts/run_conformance_suite.py", @@ -3587,8 +3593,7 @@ "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_layout.py" ], "assets": [ "templates/basic_skill.md.j2", diff --git a/reports/context_budget.json b/reports/context_budget.json index 7f2f2f67..37aef7de 100644 --- a/reports/context_budget.json +++ b/reports/context_budget.json @@ -5,11 +5,11 @@ "stats": { "context_budget_tier": "production", "context_budget_limit": 1000, - "skill_body_tokens": 751, - "other_text_tokens": 1202458, - "estimated_initial_load_tokens": 944, - "estimated_total_text_tokens": 1203209, - "deferred_resource_tokens": 387788, + "skill_body_tokens": 767, + "other_text_tokens": 1203081, + "estimated_initial_load_tokens": 960, + "estimated_total_text_tokens": 1203848, + "deferred_resource_tokens": 388041, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { @@ -19,7 +19,7 @@ }, { "path": "references", - "estimated_tokens": 25648, + "estimated_tokens": 25901, "file_count": 32 }, { @@ -64,6 +64,6 @@ "relevant_file_count": 508, "unused_resource_dirs": [], "quality_signal_points": 130, - "quality_density": 137.7 + "quality_density": 135.4 } } diff --git a/reports/context_budget.md b/reports/context_budget.md index 4cdf3aae..ba36db87 100644 --- a/reports/context_budget.md +++ b/reports/context_budget.md @@ -2,7 +2,7 @@ | Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status | | --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- | -| root | `.` | `production` | 1000 | 944 | 751 | 387788 | `governed` | scripts:340305 | 137.7 | - | ok | +| root | `.` | `production` | 1000 | 960 | 767 | 388041 | `governed` | scripts:340305 | 135.4 | - | ok | | complex-release-orchestrator | `examples/complex-release-orchestrator/generated-skill` | `production` | 1000 | 790 | 718 | 1657 | `not-required` | - | 164.6 | - | ok | | governed-incident-command | `examples/governed-incident-command/generated-skill` | `production` | 1000 | 760 | 658 | 1030 | `not-required` | - | 171.1 | - | ok | diff --git a/reports/context_budget_summary.json b/reports/context_budget_summary.json index 77a11e9e..370e81bd 100644 --- a/reports/context_budget_summary.json +++ b/reports/context_budget_summary.json @@ -6,9 +6,9 @@ "path": ".", "budget_tier": "production", "budget_limit": 1000, - "initial_tokens": 944, - "skill_body_tokens": 751, - "deferred_resource_tokens": 387788, + "initial_tokens": 960, + "skill_body_tokens": 767, + "deferred_resource_tokens": 388041, "large_deferred_resource_dirs": [ { "path": "scripts", @@ -42,7 +42,7 @@ ], "summary": "Large deferred resources are indexed and backed by evidence." }, - "quality_density": 137.7, + "quality_density": 135.4, "unused_resource_dirs": [], "ok": true, "warnings": [] diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index 04d82c8d..0db4f107 100644 --- a/reports/output_execution_runs.json +++ b/reports/output_execution_runs.json @@ -34,7 +34,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.68, + "duration_ms": 33.35, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.53, + "duration_ms": 32.64, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.59, + "duration_ms": 33.25, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.84, + "duration_ms": 33.84, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.95, + "duration_ms": 33.23, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.6, + "duration_ms": 33.36, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.76, + "duration_ms": 38.65, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.87, + "duration_ms": 34.63, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.9, + "duration_ms": 32.6, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 27.3, + "duration_ms": 32.85, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index 083d91b8..e018d2be 100644 --- a/reports/output_execution_runs.md +++ b/reports/output_execution_runs.md @@ -23,16 +23,16 @@ Command runner evidence is present. This proves the eval harness executed an ext | Case | Variant | Mode | Model | Duration ms | Tokens | Score | Status | | --- | --- | --- | --- | ---: | ---: | ---: | --- | -| skill-package-contract | baseline | command | local-output-eval-runner | 30.68 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 28.53 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 29.59 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 31.84 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 30.95 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 27.6 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.76 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.87 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 26.9 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 27.3 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 33.35 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 32.64 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 33.25 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 33.84 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 33.23 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 33.36 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 38.65 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 34.63 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 32.6 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 32.85 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/package_verification.json b/reports/package_verification.json index 8d0e4583..5a3514b6 100644 --- a/reports/package_verification.json +++ b/reports/package_verification.json @@ -8,7 +8,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "1bb01abccae0984f63251cb73a7782163bcf4b0afb260c73230dcb35da68d0dc", + "archive_sha256": "9761608424bbab003651eb643921a13f86b51220de705a3255d7c201e267dc68", "archive_entry_count": 576, "failure_count": 0, "warning_count": 0 diff --git a/reports/package_verification.md b/reports/package_verification.md index 46f0f751..e2bebbb9 100644 --- a/reports/package_verification.md +++ b/reports/package_verification.md @@ -4,7 +4,7 @@ - Package directory: `dist` - Targets: `4 / 4` adapters present - Archive present: `True` -- Archive SHA256: `1bb01abccae0984f63251cb73a7782163bcf4b0afb260c73230dcb35da68d0dc` +- Archive SHA256: `9761608424bbab003651eb643921a13f86b51220de705a3255d7c201e267dc68` - Failures: `0` - Warnings: `0` diff --git a/reports/registry_audit.json b/reports/registry_audit.json index 1006be4f..d4881778 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,8 +21,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "8b89cae0e2eaf8456b9e97940706576db7ecaf0f46e5de8153c45486f3ab1677", - "archive_sha256": "1bb01abccae0984f63251cb73a7782163bcf4b0afb260c73230dcb35da68d0dc" + "package_sha256": "0de594f90374f72387eea382b32ad0dd220d0f1d6f809b8fdd39859a1f35d5b7", + "archive_sha256": "9761608424bbab003651eb643921a13f86b51220de705a3255d7c201e267dc68" }, "compatibility": { "openai": "pass", @@ -53,7 +53,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "1bb01abccae0984f63251cb73a7782163bcf4b0afb260c73230dcb35da68d0dc", + "archive_sha256": "9761608424bbab003651eb643921a13f86b51220de705a3255d7c201e267dc68", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "8b89cae0e2eaf8456b9e97940706576db7ecaf0f46e5de8153c45486f3ab1677" + "package_sha256": "0de594f90374f72387eea382b32ad0dd220d0f1d6f809b8fdd39859a1f35d5b7" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index dd2bd62a..00855e97 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,8 +6,8 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `8b89cae0e2eaf8456b9e97940706576db7ecaf0f46e5de8153c45486f3ab1677` -- Archive SHA256: `1bb01abccae0984f63251cb73a7782163bcf4b0afb260c73230dcb35da68d0dc` +- Package SHA256: `0de594f90374f72387eea382b32ad0dd220d0f1d6f809b8fdd39859a1f35d5b7` +- Archive SHA256: `9761608424bbab003651eb643921a13f86b51220de705a3255d7c201e267dc68` - Install simulated: `True` ## Compatibility diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json index f7826dd1..cc197be8 100644 --- a/reports/security_trust_report.json +++ b/reports/security_trust_report.json @@ -23,7 +23,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 181, - "package_sha256": "8b89cae0e2eaf8456b9e97940706576db7ecaf0f46e5de8153c45486f3ab1677" + "package_sha256": "0de594f90374f72387eea382b32ad0dd220d0f1d6f809b8fdd39859a1f35d5b7" }, "failures": [], "warnings": [], diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index cd8a9926..aa805929 100644 --- a/reports/security_trust_report.md +++ b/reports/security_trust_report.md @@ -16,7 +16,7 @@ - Interactive scripts: `0` - Package hash scope: `source-contract-without-generated-reports` - Package hash files: `181` -- Package SHA256: `8b89cae0e2eaf8456b9e97940706576db7ecaf0f46e5de8153c45486f3ab1677` +- Package SHA256: `0de594f90374f72387eea382b32ad0dd220d0f1d6f809b8fdd39859a1f35d5b7` ## Failures diff --git a/reports/skill-overview.html b/reports/skill-overview.html index a8a3ca20..d2ed34d1 100644 --- a/reports/skill-overview.html +++ b/reports/skill-overview.html @@ -609,7 +609,7 @@ -
完整度100SKILL.md 已存在，是 Skill 的入口。SKILL.md 已存在，是 Skill 的入口。
触发清晰100frontmatter description 已存在，具备基础路由面。frontmatter description 已存在，具备基础路由面。
证据充分100已生成 20 / 20 类报告证据。已生成 20 / 20 类报告证据。
上下文成本42入口约 350 个词/字，references 约 15431 个词/字。入口约 350 个词/字，references 约 15431 个词/字。
+
完整度100SKILL.md 已存在，是 Skill 的入口。SKILL.md 已存在，是 Skill 的入口。
触发清晰100frontmatter description 已存在，具备基础路由面。frontmatter description 已存在，具备基础路由面。
证据充分100已生成 20 / 20 类报告证据。已生成 20 / 20 类报告证据。
上下文成本42入口约 356 个词/字，references 约 15566 个词/字。入口约 356 个词/字，references 约 15566 个词/字。
@@ -641,10 +641,10 @@

指标判读Reading

先看雷达图判断能力短板，再看下方每项分数的证据原因。分数不是装饰数字，必须和本地文件、reports 证据或证据不足提示对应。Read the radar first for weak spots, then inspect each score with its evidence. Scores must map to local files, reports, or explicit evidence gaps.

-
  1. 稳定Stable完整度100SKILL.md 已存在，是 Skill 的入口。SKILL.md 已存在，是 Skill 的入口。
  2. 稳定Stable触发清晰100frontmatter description 已存在，具备基础路由面。frontmatter description 已存在，具备基础路由面。
  3. 稳定Stable证据充分100已生成 20 / 20 类报告证据。已生成 20 / 20 类报告证据。
  4. 稳定Stable可维护性100SKILL.md 约 350 个词/字。SKILL.md 约 350 个词/字。
  5. 稳定Stable可迁移性100agents/interface.yaml 已存在。agents/interface.yaml 已存在。
  6. 关注Watch上下文成本42入口约 350 个词/字，references 约 15431 个词/字。入口约 350 个词/字，references 约 15431 个词/字。
+
  1. 稳定Stable完整度100SKILL.md 已存在，是 Skill 的入口。SKILL.md 已存在，是 Skill 的入口。
  2. 稳定Stable触发清晰100frontmatter description 已存在，具备基础路由面。frontmatter description 已存在，具备基础路由面。
  3. 稳定Stable证据充分100已生成 20 / 20 类报告证据。已生成 20 / 20 类报告证据。
  4. 稳定Stable可维护性100SKILL.md 约 356 个词/字。SKILL.md 约 356 个词/字。
  5. 稳定Stable可迁移性100agents/interface.yaml 已存在。agents/interface.yaml 已存在。
  6. 关注Watch上下文成本42入口约 356 个词/字，references 约 15566 个词/字。入口约 356 个词/字，references 约 15566 个词/字。
-
完整度100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md 已存在，是 Skill 的入口。
  • README.md 已存在，便于人工阅读。README.md 已存在，便于人工阅读。
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml 已存在，便于跨平台适配。
触发清晰100
  • frontmatter description 已存在，具备基础路由面。frontmatter description 已存在，具备基础路由面。
  • description 有足够长度说明任务边界。description 有足够长度说明任务边界。
  • description 已包含使用场景或排除边界信号。description 已包含使用场景或排除边界信号。
证据充分100
  • 已生成 20 / 20 类报告证据。已生成 20 / 20 类报告证据。
  • skill-ir.json 已存在。skill-ir.json 已存在。
  • compiled_targets.json 已存在。compiled_targets.json 已存在。
可维护性100
  • SKILL.md 约 350 个词/字。SKILL.md 约 350 个词/字。
  • 入口文件保持克制，可维护性较好。入口文件保持克制，可维护性较好。
  • references/ 已承载扩展指导。references/ 已承载扩展指导。
可迁移性100
  • agents/interface.yaml 已存在。agents/interface.yaml 已存在。
  • manifest.json 已存在。manifest.json 已存在。
  • 目标平台或 adapter target 已声明。目标平台或 adapter target 已声明。
上下文成本42
  • 入口约 350 个词/字，references 约 15431 个词/字。入口约 350 个词/字，references 约 15431 个词/字。
  • 分数越高代表上下文成本越低。分数越高代表上下文成本越低。
  • 上下文成本偏高，建议压缩入口或拆分 references。上下文成本偏高，建议压缩入口或拆分 references。
+
完整度100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md 已存在，是 Skill 的入口。
  • README.md 已存在，便于人工阅读。README.md 已存在，便于人工阅读。
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml 已存在，便于跨平台适配。
触发清晰100
  • frontmatter description 已存在，具备基础路由面。frontmatter description 已存在，具备基础路由面。
  • description 有足够长度说明任务边界。description 有足够长度说明任务边界。
  • description 已包含使用场景或排除边界信号。description 已包含使用场景或排除边界信号。
证据充分100
  • 已生成 20 / 20 类报告证据。已生成 20 / 20 类报告证据。
  • skill-ir.json 已存在。skill-ir.json 已存在。
  • compiled_targets.json 已存在。compiled_targets.json 已存在。
可维护性100
  • SKILL.md 约 356 个词/字。SKILL.md 约 356 个词/字。
  • 入口文件保持克制，可维护性较好。入口文件保持克制，可维护性较好。
  • references/ 已承载扩展指导。references/ 已承载扩展指导。
可迁移性100
  • agents/interface.yaml 已存在。agents/interface.yaml 已存在。
  • manifest.json 已存在。manifest.json 已存在。
  • 目标平台或 adapter target 已声明。目标平台或 adapter target 已声明。
上下文成本42
  • 入口约 356 个词/字，references 约 15566 个词/字。入口约 356 个词/字，references 约 15566 个词/字。
  • 分数越高代表上下文成本越低。分数越高代表上下文成本越低。
  • 上下文成本偏高，建议压缩入口或拆分 references。上下文成本偏高，建议压缩入口或拆分 references。
@@ -720,7 +720,7 @@
- +
类型Type证据Evidence建议Action
强项Strength触发面保持精简，并锚定在 frontmatter description。The trigger surface stays lean and anchored in the frontmatter description.保留并复用Keep
强项Strength已生成 Skill IR，核心语义可先于平台打包被审查和迁移。已生成 Skill IR，核心语义可先于平台打包被审查和迁移。保留并复用Keep
强项Strength已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。保留并复用Keep
缺口Gap上下文成本需要补强：入口约 350 个词/字，references 约 15431 个词/字。上下文成本需要补强：入口约 350 个词/字，references 约 15431 个词/字。纳入下一轮修复Fix next
强项Strength触发面保持精简，并锚定在 frontmatter description。The trigger surface stays lean and anchored in the frontmatter description.保留并复用Keep
强项Strength已生成 Skill IR，核心语义可先于平台打包被审查和迁移。已生成 Skill IR，核心语义可先于平台打包被审查和迁移。保留并复用Keep
强项Strength已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。保留并复用Keep
缺口Gap上下文成本需要补强：入口约 356 个词/字，references 约 15566 个词/字。上下文成本需要补强：入口约 356 个词/字，references 约 15566 个词/字。纳入下一轮修复Fix next
@@ -757,7 +757,7 @@
- +
风险Risk信号Signal应对Response
误触发风险误触发风险frontmatter description 已存在，具备基础路由面。frontmatter description 已存在，具备基础路由面。先补证据和边界，再增加包体复杂度。先补证据和边界，再增加包体复杂度。
输出漂移风险输出漂移风险已生成 20 / 20 类报告证据。已生成 20 / 20 类报告证据。先补证据和边界，再增加包体复杂度。先补证据和边界，再增加包体复杂度。
证据不足风险证据不足风险已生成 20 / 20 类报告证据。已生成 20 / 20 类报告证据。先补证据和边界，再增加包体复杂度。先补证据和边界，再增加包体复杂度。
包体膨胀风险包体膨胀风险SKILL.md 约 350 个词/字。SKILL.md 约 350 个词/字。先补证据和边界，再增加包体复杂度。先补证据和边界，再增加包体复杂度。
跨平台迁移风险跨平台迁移风险agents/interface.yaml 已存在。agents/interface.yaml 已存在。先补证据和边界，再增加包体复杂度。先补证据和边界，再增加包体复杂度。
误触发风险误触发风险frontmatter description 已存在，具备基础路由面。frontmatter description 已存在，具备基础路由面。先补证据和边界，再增加包体复杂度。先补证据和边界，再增加包体复杂度。
输出漂移风险输出漂移风险已生成 20 / 20 类报告证据。已生成 20 / 20 类报告证据。先补证据和边界，再增加包体复杂度。先补证据和边界，再增加包体复杂度。
证据不足风险证据不足风险已生成 20 / 20 类报告证据。已生成 20 / 20 类报告证据。先补证据和边界，再增加包体复杂度。先补证据和边界，再增加包体复杂度。
包体膨胀风险包体膨胀风险SKILL.md 约 356 个词/字。SKILL.md 约 356 个词/字。先补证据和边界，再增加包体复杂度。先补证据和边界，再增加包体复杂度。
跨平台迁移风险跨平台迁移风险agents/interface.yaml 已存在。agents/interface.yaml 已存在。先补证据和边界，再增加包体复杂度。先补证据和边界，再增加包体复杂度。
diff --git a/reports/skill-overview.json b/reports/skill-overview.json index c5b4388a..450a3495 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -79,7 +79,7 @@ "label": "可维护性", "score": 100, "reasons": [ - "SKILL.md 约 350 个词/字。", + "SKILL.md 约 356 个词/字。", "入口文件保持克制，可维护性较好。", "references/ 已承载扩展指导。", "scripts/ 已承载确定性逻辑。", @@ -100,7 +100,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 350 个词/字，references 约 15431 个词/字。", + "入口约 356 个词/字，references 约 15566 个词/字。", "分数越高代表上下文成本越低。", "上下文成本偏高，建议压缩入口或拆分 references。" ] @@ -204,7 +204,7 @@ "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。" ], "gaps": [ - "上下文成本需要补强：入口约 350 个词/字，references 约 15431 个词/字。" + "上下文成本需要补强：入口约 356 个词/字，references 约 15566 个词/字。" ], "recommendations": [ "先改触发边界，再扩展工作流。", @@ -269,7 +269,7 @@ "name": "包体膨胀风险", "impact": 2, "probability": 1, - "signal": "SKILL.md 约 350 个词/字。", + "signal": "SKILL.md 约 356 个词/字。", "response": "先补证据和边界，再增加包体复杂度。" }, { @@ -918,13 +918,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "d1e46322a670ebd2d3977fd716c13b3d00bc37816e83343fc21978eba96d40bb", - "source_contract_sha256": "e38d34ebe54c377f47f6010c06716f8f972406cf1019a27e6ebc057371dd260f", - "archive_sha256": "0e4ba92cd88c099965383daf5c3d6319b917d7c83d5ef29917f1cd932c1bd6f8", + "evidence_bundle_sha256": "f54d5131bea27a3c055b8a2d7fd6d647f69148b293518eff57592eb35d5f6983", + "source_contract_sha256": "0de594f90374f72387eea382b32ad0dd220d0f1d6f809b8fdd39859a1f35d5b7", + "archive_sha256": "1bb01abccae0984f63251cb73a7782163bcf4b0afb260c73230dcb35da68d0dc", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 21, @@ -939,11 +939,11 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "public_claim_ready": false, - "public_claim_blocker_count": 3, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 4, + "working_tree_dirty": true, + "changed_file_count": 33 }, - "commit": "78f94e47fd7ab999fdfc6d18ffb9917cf8848dba", + "commit": "c2d15206e25551022b02b86f36e7e6f0158888f2", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", @@ -1048,7 +1048,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 181, - "package_sha256": "8b89cae0e2eaf8456b9e97940706576db7ecaf0f46e5de8153c45486f3ab1677" + "package_sha256": "0de594f90374f72387eea382b32ad0dd220d0f1d6f809b8fdd39859a1f35d5b7" }, "skill_atlas": { "skill_count": 12, @@ -1086,8 +1086,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "8b89cae0e2eaf8456b9e97940706576db7ecaf0f46e5de8153c45486f3ab1677", - "archive_sha256": "1bb01abccae0984f63251cb73a7782163bcf4b0afb260c73230dcb35da68d0dc" + "package_sha256": "0de594f90374f72387eea382b32ad0dd220d0f1d6f809b8fdd39859a1f35d5b7", + "archive_sha256": "9761608424bbab003651eb643921a13f86b51220de705a3255d7c201e267dc68" }, "compatibility": { "openai": "pass", @@ -1118,7 +1118,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "1bb01abccae0984f63251cb73a7782163bcf4b0afb260c73230dcb35da68d0dc", + "archive_sha256": "9761608424bbab003651eb643921a13f86b51220de705a3255d7c201e267dc68", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1134,7 +1134,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "1bb01abccae0984f63251cb73a7782163bcf4b0afb260c73230dcb35da68d0dc", + "archive_sha256": "9761608424bbab003651eb643921a13f86b51220de705a3255d7c201e267dc68", "archive_entry_count": 576, "failure_count": 0, "warning_count": 0 @@ -1213,12 +1213,12 @@ { "field": "archive_sha256", "from": "", - "to": "1bb01abccae0984f63251cb73a7782163bcf4b0afb260c73230dcb35da68d0dc" + "to": "9761608424bbab003651eb643921a13f86b51220de705a3255d7c201e267dc68" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "8b89cae0e2eaf8456b9e97940706576db7ecaf0f46e5de8153c45486f3ab1677" + "to": "0de594f90374f72387eea382b32ad0dd220d0f1d6f809b8fdd39859a1f35d5b7" } ] }, diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index 81ceaa53..4a2c03d2 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -70,12 +70,12 @@ { "field": "archive_sha256", "from": "", - "to": "1bb01abccae0984f63251cb73a7782163bcf4b0afb260c73230dcb35da68d0dc" + "to": "9761608424bbab003651eb643921a13f86b51220de705a3255d7c201e267dc68" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "8b89cae0e2eaf8456b9e97940706576db7ecaf0f46e5de8153c45486f3ab1677" + "to": "0de594f90374f72387eea382b32ad0dd220d0f1d6f809b8fdd39859a1f35d5b7" } ] }, diff --git a/skill-ir/examples/yao-meta-skill.json b/skill-ir/examples/yao-meta-skill.json index 8ff9b43a..24a2583e 100644 --- a/skill-ir/examples/yao-meta-skill.json +++ b/skill-ir/examples/yao-meta-skill.json @@ -55,6 +55,7 @@ "`Scaffold`: exploratory or personal.", "`Production`: team reuse.", "`Library`: shared infrastructure.", + "`Governed`: high-trust, policy-sensitive, or release-critical.", "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.", "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.", "Do not silently broaden the skill into adjacent jobs just because the examples are nearby." @@ -177,6 +178,7 @@ "scripts/review_studio_gates.py", "scripts/review_studio_layout.py", "scripts/review_studio_output_review.py", + "scripts/review_studio_waivers.py", "scripts/review_studio_world_class.py", "scripts/review_viewer_data.py", "scripts/run_conformance_suite.py", @@ -186,8 +188,7 @@ "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_layout.py" ], "assets": [ "templates/basic_skill.md.j2",