diff --git a/reports/context_budget.json b/reports/context_budget.json index c6f5fd0..53f3f56 100644 --- a/reports/context_budget.json +++ b/reports/context_budget.json @@ -6,9 +6,9 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1035916, + "other_text_tokens": 1035917, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1036713, + "estimated_total_text_tokens": 1036714, "deferred_resource_tokens": 478069, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index f9036c0..b636014 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -189,12 +189,12 @@ "status": "pass", "expected": { "status": "pass", - "detail": "initial load 990/1000; deferred 477629/120000; top deferred scripts 422712; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 478069/120000; top deferred scripts 423106; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json" }, "actual": { "status": "pass", - "detail": "initial load 990/1000; deferred 477629/120000; top deferred scripts 422712; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 478069/120000; top deferred scripts 423106; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json" }, "paths": [ @@ -248,8 +248,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "15c743370e53311292e7045b2ec93f3046838055", - "actual": "15c743370e53311292e7045b2ec93f3046838055", + "expected": "c325269f10a7c691646aefc5f48ca73e0a94542f", + "actual": "c325269f10a7c691646aefc5f48ca73e0a94542f", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -264,8 +264,8 @@ "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa", - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "source_contract_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, @@ -277,8 +277,8 @@ "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa", - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "source_contract_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, @@ -394,8 +394,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "15c743370e53311292e7045b2ec93f3046838055", - "actual": "15c743370e53311292e7045b2ec93f3046838055", + "expected": "c325269f10a7c691646aefc5f48ca73e0a94542f", + "actual": "c325269f10a7c691646aefc5f48ca73e0a94542f", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -410,8 +410,8 @@ "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa", - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "source_contract_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, @@ -423,8 +423,8 @@ "release_lock_ready": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa", - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "source_contract_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, "world_class_source_pass_count": 6, @@ -598,7 +598,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 360 个词/字,references 约 16740 个词/字。", + "入口约 360 个词/字,references 约 16770 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。" ] @@ -662,7 +662,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 360 个词/字,references 约 16740 个词/字。", + "入口约 360 个词/字,references 约 16770 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。" ] @@ -894,7 +894,7 @@ "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 360 个词/字,references 约 16740 个词/字。" + "上下文成本需要补强:入口约 360 个词/字,references 约 16770 个词/字。" ], "recommendations": [ "先改触发边界,再扩展工作流。", @@ -942,7 +942,7 @@ "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 360 个词/字,references 约 16740 个词/字。" + "上下文成本需要补强:入口约 360 个词/字,references 约 16770 个词/字。" ], "recommendations": [ "先改触发边界,再扩展工作流。", diff --git a/reports/review-studio.html b/reports/review-studio.html index 235742d..e161902 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -648,6 +648,15 @@ font-size: 12px; color: var(--muted); } + .source-ref-list blockquote { + margin: 2px 0 0; + padding: 7px 9px; + border-left: 3px solid var(--line); + background: var(--soft); + color: var(--muted); + font-size: 12px; + overflow-wrap: anywhere; + } code { font-family: ui-monospace, SFMono-Regular, Menlo, Consolas, monospace; font-size: 13px; @@ -681,7 +690,7 @@

审查闸门

-
通过

意图画布

intent confidence 100/100; Intent is clear enough to package the first routeable version.

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 990/1000; deferred 477629/120000; top deferred scripts 422712; resource governance governed; quality density 131.3

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 121 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 193 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

190 Python files; 0 hotspots; 9 watchlist files; 0 blockers; largest 899 lines; 68 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

3/3 permissions approved; gaps 0; required file_write, network, subprocess

reports/security_trust_report.json + security/permission_policy.json 证据
通过

权限探针

4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4

reports/runtime_permission_probes.json 证据
通过

组合治理

12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true

reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

reports/registry_audit.json + reports/install_simulation.json 证据
通过

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md 证据
+
通过

意图画布

intent confidence 100/100; Intent is clear enough to package the first routeable version.

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 990/1000; deferred 478069/120000; top deferred scripts 423106; resource governance governed; quality density 131.3

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 121 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 193 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

190 Python files; 0 hotspots; 9 watchlist files; 0 blockers; largest 899 lines; 68 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

3/3 permissions approved; gaps 0; required file_write, network, subprocess

reports/security_trust_report.json + security/permission_policy.json 证据
通过

权限探针

4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4

reports/runtime_permission_probes.json 证据
通过

组合治理

12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true

reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

reports/registry_audit.json + reports/install_simulation.json 证据
通过

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

@@ -691,7 +700,7 @@

修复动作

-
关注

输出实验

补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。

没有输出质量和人工盲评证据时,Skill 只能证明会触发,不能证明输出真的更好且经得起审查。
修复位置
evals/output/cases.jsonl + reports/output_quality_scorecard.md + reports/output_review_kit.html + reports/output_review_adjudication.md
验证命令
python3 scripts/adjudicate_output_review.py --write-template && python3 scripts/yao.py output-review
关注

人工批准

对保留的 warning 写入 reviewer、理由、范围和到期时间,或修掉 warning。

warning 可以被接受,但必须可审计、会过期,并且不能掩盖 blocker。
修复位置
reports/review_waivers.md
验证命令
python3 scripts/render_review_waivers.py .
关注

世界证据

补齐 provider、真人盲评、原生权限执行和真实客户端遥测证据,或明确本次发布不声明 world-class 完成。

世界级结论必须来自已接受的外部/人工证据;计划、metadata fallback、待评审和本地命令都不能替代完成证据。
修复位置
reports/world_class_operator_runbook.html + reports/world_class_evidence_ledger.md + reports/world_class_evidence_intake.md + reports/world_class_submission_review.md
验证命令
python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py review-studio .

证据采集

以下条目仍需真实外部或人工证据;提交文件、校验命令和阻断检查必须同时闭环。

pending · external

Provider Holdout

model-executed 0; token-observed 0

提交
evidence/world_class/submissions/provider-holdout.json
模板
evidence/world_class/templates/provider-holdout.intake.json
阻断
2 blocked / 1 pass
下一步
Run provider-backed holdout cases with real credentials and commit only aggregate evidence.
阻断检查
  • Provider model runmodel_executed_count: 0 / >0Run provider-backed output-exec with real credentials.
  • Token usage observedtoken_observed_count: 0 / >0Provider execution should return non-estimated token usage.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60
  2. python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  3. Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.
pending · human

Human Adjudication

0/5 decisions; pending 5

提交
evidence/world_class/submissions/human-adjudication.json
模板
evidence/world_class/templates/human-adjudication.intake.json
阻断
2 blocked / 2 pass
下一步
Record real A/B choices in the decision template, then regenerate adjudication.
阻断检查
  • No pending decisionspending_count: 5 / ==0Record a reviewer choice for every pair.
  • Judgments completejudgment_count: 0 / ==pair_countEvery pair needs one valid human judgment.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. python3 scripts/yao.py output-review-kit --write-template
  2. Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.
  3. python3 scripts/adjudicate_output_review.py --write-template
pending · external

Native Permission Enforcement

native-enforced targets 0; installer-enforced targets 4

提交
evidence/world_class/submissions/native-permission-enforcement.json
模板
evidence/world_class/templates/native-permission-enforcement.intake.json
阻断
1 blocked / 2 pass
下一步
Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.
阻断检查
  • Native enforcementnative_enforcement_count: 0 / >0Collect real target-client or external runtime guard proof.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.
  2. Update the generated target adapter only when the guard is actually enforced by that target.
  3. python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip
pending · external

Native Client Telemetry

external source events 0; adoption samples 0

提交
evidence/world_class/submissions/native-client-telemetry.json
模板
evidence/world_class/templates/native-client-telemetry.intake.json
阻断
2 blocked / 1 pass
下一步
Install a real client against the native host and import production metadata-only events.
阻断检查
  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
  • Adoption sampleadoption_sample_count: 0 / >0Telemetry must include adoption outcome evidence.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/
  2. Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.
  3. python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl
+
关注

输出实验

补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。

没有输出质量和人工盲评证据时,Skill 只能证明会触发,不能证明输出真的更好且经得起审查。
修复位置
evals/output/cases.jsonl + reports/output_quality_scorecard.md + reports/output_review_kit.html + reports/output_review_adjudication.md
验证命令
python3 scripts/adjudicate_output_review.py --write-template && python3 scripts/yao.py output-review
关注

人工批准

对保留的 warning 写入 reviewer、理由、范围和到期时间,或修掉 warning。

warning 可以被接受,但必须可审计、会过期,并且不能掩盖 blocker。
修复位置
reports/review_waivers.md
验证命令
python3 scripts/render_review_waivers.py .
关注

世界证据

补齐 provider、真人盲评、原生权限执行和真实客户端遥测证据,或明确本次发布不声明 world-class 完成。

世界级结论必须来自已接受的外部/人工证据;计划、metadata fallback、待评审和本地命令都不能替代完成证据。
修复位置
reports/world_class_operator_runbook.html + reports/world_class_evidence_ledger.md + reports/world_class_evidence_intake.md + reports/world_class_submission_review.md
验证命令
python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py review-studio .

证据采集

以下条目仍需真实外部或人工证据;提交文件、校验命令和阻断检查必须同时闭环。

pending · external

Provider Holdout

model-executed 0; token-observed 0

提交
evidence/world_class/submissions/provider-holdout.json
模板
evidence/world_class/templates/provider-holdout.intake.json
阻断
2 blocked / 1 pass
下一步
Run provider-backed holdout cases with real credentials and commit only aggregate evidence.
阻断检查
  • Provider model runmodel_executed_count: 0 / >0Run provider-backed output-exec with real credentials.
  • Token usage observedtoken_observed_count: 0 / >0Provider execution should return non-estimated token usage.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60
  2. python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  3. Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.
pending · human

Human Adjudication

0/5 decisions; pending 5

提交
evidence/world_class/submissions/human-adjudication.json
模板
evidence/world_class/templates/human-adjudication.intake.json
阻断
2 blocked / 2 pass
下一步
Record real A/B choices in the decision template, then regenerate adjudication.
阻断检查
  • No pending decisionspending_count: 5 / ==0Record a reviewer choice for every pair.
  • Judgments completejudgment_count: 0 / ==pair_countEvery pair needs one valid human judgment.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. python3 scripts/yao.py output-review-kit --write-template
  2. Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.
  3. python3 scripts/adjudicate_output_review.py --write-template
pending · external

Native Permission Enforcement

native-enforced targets 0; installer-enforced targets 4

提交
evidence/world_class/submissions/native-permission-enforcement.json
模板
evidence/world_class/templates/native-permission-enforcement.intake.json
阻断
1 blocked / 2 pass
下一步
Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.
阻断检查
  • Native enforcementnative_enforcement_count: 0 / >0Collect real target-client or external runtime guard proof.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.
  2. Update the generated target adapter only when the guard is actually enforced by that target.
  3. python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip
pending · external

Native Client Telemetry

external source events 0; adoption samples 0

提交
evidence/world_class/submissions/native-client-telemetry.json
模板
evidence/world_class/templates/native-client-telemetry.intake.json
阻断
2 blocked / 1 pass
下一步
Install a real client against the native host and import production metadata-only events.
阻断检查
  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
  • Adoption sampleadoption_sample_count: 0 / >0Telemetry must include adoption outcome evidence.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/
  2. Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.
  3. python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl
@@ -743,12 +752,12 @@
-

上下文

initial load 990/1000; deferred 477629/120000; top deferred scripts 422712; resource governance governed; quality density 131.3

+

上下文

initial load 990/1000; deferred 478069/120000; top deferred scripts 423106; resource governance governed; quality density 131.3

编译证据

Review reports/compiled_targets.md before packaging to inspect target adapter modes, generated files, preserved semantics, warnings, and unsupported features.

-

信任报告

Secret
0
脚本数
121
网络脚本
3
Help 失败
0
包体哈希
8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa
+

信任报告

Secret
0
脚本数
121
网络脚本
3
Help 失败
0
包体哈希
f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc

安全边界

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。

@@ -834,12 +843,12 @@

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

-

包体元数据

名称
yao-meta-skill
版本
1.1.0
Maturity
governed
Owner
Yao Team
License
MIT
信任级别
local
目标平台
openai, claude, generic, agent-skills-compatible, vscode
兼容通过
6/6
归档哈希
167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407
+

包体元数据

名称
yao-meta-skill
版本
1.1.0
Maturity
governed
Owner
Yao Team
License
MIT
信任级别
local
目标平台
openai, claude, generic, agent-skills-compatible, vscode
兼容通过
6/6
归档哈希
c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

-

包体验证

目标数
4
Adapter
4
归档存在
Zip 条目
645
失败数
0
警告数
0
归档哈希
167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407
+

包体验证

目标数
4
Adapter
4
归档存在
Zip 条目
645
失败数
0
警告数
0
归档哈希
c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6
diff --git a/reports/review-studio.json b/reports/review-studio.json index b045236..4294f43 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -43,7 +43,7 @@ "key": "context-budget", "label": "上下文", "status": "pass", - "detail": "initial load 990/1000; deferred 477629/120000; top deferred scripts 422712; resource governance governed; quality density 131.3", + "detail": "initial load 990/1000; deferred 478069/120000; top deferred scripts 423106; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json", "link": "context_budget.md" }, @@ -186,6 +186,8 @@ "label": "output eval cases", "kind": "eval", "line": 1, + "matched_pattern": "", + "excerpt": "{\"id\":\"skill-package-contract\",\"prompt\":\"Turn this repeated workflow into a reusable team skill package.\",\"baseline_output\":\"I can write a prompt for that workflow and include a s…", "exists": true, "link": "../evals/output/cases.jsonl" }, @@ -194,6 +196,8 @@ "label": "output scorecard", "kind": "report", "line": 1, + "matched_pattern": "# Output", + "excerpt": "# Output Quality Scorecard", "exists": true, "link": "output_quality_scorecard.md" }, @@ -202,6 +206,8 @@ "label": "output execution runs", "kind": "report", "line": 1, + "matched_pattern": "# Output Execution", + "excerpt": "# Output Execution Runs", "exists": true, "link": "output_execution_runs.md" }, @@ -210,6 +216,8 @@ "label": "blind A/B review pack", "kind": "report", "line": 1, + "matched_pattern": "# Output Blind", + "excerpt": "# Output Blind A/B Review Pack", "exists": true, "link": "output_blind_review_pack.md" }, @@ -218,6 +226,8 @@ "label": "reviewer cockpit", "kind": "report", "line": 6, + "matched_pattern": "Output Review Kit", + "excerpt": "Output Review Kit", "exists": true, "link": "output_review_kit.html" }, @@ -226,6 +236,8 @@ "label": "review adjudication", "kind": "report", "line": 1, + "matched_pattern": "# Output Review", + "excerpt": "# Output Review Adjudication", "exists": true, "link": "output_review_adjudication.md" } @@ -249,6 +261,8 @@ "label": "waiver ledger", "kind": "report", "line": 1, + "matched_pattern": "# Review", + "excerpt": "# Review Waivers", "exists": true, "link": "review_waivers.md" }, @@ -257,6 +271,8 @@ "label": "waiver method", "kind": "method", "line": 1, + "matched_pattern": "# Review", + "excerpt": "# Review Waiver Method", "exists": true, "link": "../references/review-waiver-method.md" } @@ -280,6 +296,8 @@ "label": "world-class evidence ledger", "kind": "report", "line": 1, + "matched_pattern": "# World-Class Evidence Ledger", + "excerpt": "# World-Class Evidence Ledger", "exists": true, "link": "world_class_evidence_ledger.md" }, @@ -288,6 +306,8 @@ "label": "world-class evidence plan", "kind": "report", "line": 1, + "matched_pattern": "# World-Class Evidence Plan", + "excerpt": "# World-Class Evidence Plan", "exists": true, "link": "world_class_evidence_plan.md" }, @@ -296,6 +316,8 @@ "label": "world-class evidence intake", "kind": "report", "line": 1, + "matched_pattern": "# World-Class Evidence Intake", + "excerpt": "# World-Class Evidence Intake", "exists": true, "link": "world_class_evidence_intake.md" }, @@ -304,6 +326,8 @@ "label": "world-class submission review", "kind": "report", "line": 1, + "matched_pattern": "# World-Class Submission Review", + "excerpt": "# World-Class Submission Review", "exists": true, "link": "world_class_submission_review.md" }, @@ -312,6 +336,8 @@ "label": "world-class claim guard", "kind": "report", "line": 1, + "matched_pattern": "# World-Class Claim Guard", + "excerpt": "# World-Class Claim Guard", "exists": true, "link": "world_class_claim_guard.md" }, @@ -320,6 +346,8 @@ "label": "evidence intake schema", "kind": "schema", "line": 4, + "matched_pattern": "Yao World-Class Evidence Intake", + "excerpt": "\"title\": \"Yao World-Class Evidence Intake\",", "exists": true, "link": "../evidence/world_class/intake.schema.json" }, @@ -328,6 +356,8 @@ "label": "provider intake template", "kind": "template", "line": 3, + "matched_pattern": "provider-holdout", + "excerpt": "\"evidence_key\": \"provider-holdout\",", "exists": true, "link": "../evidence/world_class/templates/provider-holdout.intake.json" }, @@ -336,6 +366,8 @@ "label": "human intake template", "kind": "template", "line": 3, + "matched_pattern": "human-adjudication", + "excerpt": "\"evidence_key\": \"human-adjudication\",", "exists": true, "link": "../evidence/world_class/templates/human-adjudication.intake.json" }, @@ -344,6 +376,8 @@ "label": "permission intake template", "kind": "template", "line": 3, + "matched_pattern": "native-permission-enforcement", + "excerpt": "\"evidence_key\": \"native-permission-enforcement\",", "exists": true, "link": "../evidence/world_class/templates/native-permission-enforcement.intake.json" }, @@ -352,6 +386,8 @@ "label": "telemetry intake template", "kind": "template", "line": 3, + "matched_pattern": "native-client-telemetry", + "excerpt": "\"evidence_key\": \"native-client-telemetry\",", "exists": true, "link": "../evidence/world_class/templates/native-client-telemetry.intake.json" }, @@ -360,6 +396,8 @@ "label": "Skill OS 2.0 audit", "kind": "report", "line": 1, + "matched_pattern": "# Skill OS", + "excerpt": "# Skill OS 2.0 Audit", "exists": true, "link": "skill_os2_audit.md" }, @@ -368,6 +406,8 @@ "label": "human review decisions", "kind": "report", "line": 6, + "matched_pattern": "winner_variant", + "excerpt": "\"winner_variant\": \"Use A or B after reading the blind review pack. Leave blank when pending.\",", "exists": true, "link": "output_review_decisions.json" }, @@ -376,6 +416,8 @@ "label": "runtime permission probes", "kind": "report", "line": 1, + "matched_pattern": "# Runtime", + "excerpt": "# Runtime Permission Probes", "exists": true, "link": "runtime_permission_probes.md" }, @@ -384,6 +426,8 @@ "label": "adoption drift", "kind": "report", "line": 1, + "matched_pattern": "# Adoption", + "excerpt": "# Adoption And Drift Report", "exists": true, "link": "adoption_drift_report.md" } @@ -785,7 +829,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 360 个词/字,references 约 16740 个词/字。", + "入口约 360 个词/字,references 约 16770 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。" ] @@ -889,7 +933,7 @@ "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 360 个词/字,references 约 16740 个词/字。" + "上下文成本需要补强:入口约 360 个词/字,references 约 16770 个词/字。" ], "recommendations": [ "先改触发边界,再扩展工作流。", @@ -1684,9 +1728,9 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "164fa736727f9162f4c61860de8fb4c7b450c026c742c6f9233520578e25c860", - "source_contract_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa", - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "evidence_bundle_sha256": "95a01210eb2bacbef1d295e72bd60fdcce075db27930533679397b5aad82e4cf", + "source_contract_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1708,7 +1752,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "15c743370e53311292e7045b2ec93f3046838055", + "commit": "c325269f10a7c691646aefc5f48ca73e0a94542f", "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.", @@ -1813,7 +1857,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 211, - "package_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa" + "package_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc" }, "skill_atlas": { "skill_count": 12, @@ -1851,8 +1895,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa", - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407" + "package_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6" }, "compatibility": { "openai": "pass", @@ -1883,7 +1927,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1899,7 +1943,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "archive_entry_count": 645, "failure_count": 0, "warning_count": 0 @@ -1978,12 +2022,12 @@ { "field": "archive_sha256", "from": "", - "to": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407" + "to": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa" + "to": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc" } ] }, @@ -5314,7 +5358,7 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "15c743370e53311292e7045b2ec93f3046838055", + "commit": "c325269f10a7c691646aefc5f48ca73e0a94542f", "git_status": { "available": true, "dirty": false, @@ -5328,9 +5372,9 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "164fa736727f9162f4c61860de8fb4c7b450c026c742c6f9233520578e25c860", - "source_contract_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa", - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "evidence_bundle_sha256": "95a01210eb2bacbef1d295e72bd60fdcce075db27930533679397b5aad82e4cf", + "source_contract_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -5365,7 +5409,7 @@ }, "release_lock": { "ready": true, - "commit": "15c743370e53311292e7045b2ec93f3046838055", + "commit": "c325269f10a7c691646aefc5f48ca73e0a94542f", "status_scope": "generation-time status before this report is written", "reason": "clean generation-time HEAD" }, @@ -5375,7 +5419,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "164fa736727f9162f4c61860de8fb4c7b450c026c742c6f9233520578e25c860" + "sha256": "95a01210eb2bacbef1d295e72bd60fdcce075db27930533679397b5aad82e4cf" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -5484,7 +5528,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 117850, - "sha256": "5bbb008aaa73068d0986affe57f8026ea1833972803be020c589f9d09cc7c7ca" + "sha256": "10abf9ec2d104908bbdfa0d7b40c04977dd4c0c2361635d17f128e4ae2f0979a" }, { "label": "python_compatibility", @@ -5498,14 +5542,14 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "b00d7a4a8953f54df1b46553aec850efbdb9040e09b7961aa36acd6ad49db6d3" + "sha256": "ed24d67c538e61177dc30c2a6a9ae1daca9f73db0d61312f65bd97364c49e91f" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "1221d7d1d34d79156e6d6306864592dacf96f7250c40d84f7620f8474ac54790" + "sha256": "33b28ae80672acda503ef7fe032cecb5f80135f47e558b865da3bdbbd6a39250" }, { "label": "install_simulation", @@ -11754,7 +11798,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 211, - "package_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa" + "package_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc" }, "failures": [], "warnings": [], @@ -15940,6 +15984,13 @@ "severity": "pass", "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." }, + { + "path": "tests/verify_review_studio.py", + "lines": 803, + "kind": "test", + "severity": "pass", + "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." + }, { "path": "scripts/skill_report_model.py", "lines": 800, @@ -15947,13 +15998,6 @@ "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." }, - { - "path": "tests/verify_review_studio.py", - "lines": 784, - "kind": "test", - "severity": "pass", - "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." - }, { "path": "scripts/build_skill_atlas.py", "lines": 730, @@ -15991,7 +16035,7 @@ }, { "path": "scripts/review_studio_layout.py", - "lines": 694, + "lines": 703, "kind": "internal-module", "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." @@ -16026,6 +16070,13 @@ "severity": "pass", "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." }, + { + "path": "tests/verify_review_studio.py", + "lines": 803, + "kind": "test", + "severity": "pass", + "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." + }, { "path": "scripts/skill_report_model.py", "lines": 800, @@ -16033,13 +16084,6 @@ "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." }, - { - "path": "tests/verify_review_studio.py", - "lines": 784, - "kind": "test", - "severity": "pass", - "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." - }, { "path": "scripts/build_skill_atlas.py", "lines": 730, @@ -16077,20 +16121,20 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 797, - "other_text_tokens": 1035149, + "other_text_tokens": 1035917, "estimated_initial_load_tokens": 990, - "estimated_total_text_tokens": 1035946, - "deferred_resource_tokens": 477629, + "estimated_total_text_tokens": 1036714, + "deferred_resource_tokens": 478069, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 422712, + "estimated_tokens": 423106, "file_count": 121 }, { "path": "references", - "estimated_tokens": 27945, + "estimated_tokens": 27991, "file_count": 35 }, { @@ -16107,7 +16151,7 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 422712, + "estimated_tokens": 423106, "file_count": 121 } ], @@ -16130,7 +16174,7 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 422712, + "estimated_tokens": 423106, "file_count": 121, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } @@ -22009,8 +22053,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa", - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407" + "package_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6" }, "compatibility": { "openai": "pass", @@ -22041,7 +22085,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -22066,7 +22110,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa" + "package_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc" } ] }, @@ -22089,7 +22133,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "archive_entry_count": 645, "failure_count": 0, "warning_count": 0 @@ -23097,12 +23141,12 @@ { "field": "archive_sha256", "from": "", - "to": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407" + "to": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa" + "to": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc" } ] }, diff --git a/reports/review-viewer.json b/reports/review-viewer.json index 23d7453..1bbfcb4 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -102,7 +102,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 360 个词/字,references 约 16740 个词/字。", + "入口约 360 个词/字,references 约 16770 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。" ] @@ -206,7 +206,7 @@ "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 360 个词/字,references 约 16740 个词/字。" + "上下文成本需要补强:入口约 360 个词/字,references 约 16770 个词/字。" ], "recommendations": [ "先改触发边界,再扩展工作流。", @@ -1001,9 +1001,9 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "164fa736727f9162f4c61860de8fb4c7b450c026c742c6f9233520578e25c860", - "source_contract_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa", - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "evidence_bundle_sha256": "95a01210eb2bacbef1d295e72bd60fdcce075db27930533679397b5aad82e4cf", + "source_contract_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1025,7 +1025,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "15c743370e53311292e7045b2ec93f3046838055", + "commit": "c325269f10a7c691646aefc5f48ca73e0a94542f", "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.", @@ -1130,7 +1130,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 211, - "package_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa" + "package_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc" }, "skill_atlas": { "skill_count": 12, @@ -1168,8 +1168,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa", - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407" + "package_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6" }, "compatibility": { "openai": "pass", @@ -1200,7 +1200,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1216,7 +1216,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "archive_entry_count": 645, "failure_count": 0, "warning_count": 0 @@ -1295,12 +1295,12 @@ { "field": "archive_sha256", "from": "", - "to": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407" + "to": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa" + "to": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc" } ] }, diff --git a/reports/skill-interpretation.html b/reports/skill-interpretation.html index f7d7c6c..d14535a 100644 --- a/reports/skill-interpretation.html +++ b/reports/skill-interpretation.html @@ -764,7 +764,7 @@
-
完整度Completeness100SKILL.md 已存在,是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
触发清晰Trigger clarity100frontmatter description 已存在,具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
上下文成本Context cost42入口约 360 个词/字,references 约 16740 个词/字。Entrypoint is about 360 words/characters; references are about 16740.
+
完整度Completeness100SKILL.md 已存在,是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
触发清晰Trigger clarity100frontmatter description 已存在,具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
上下文成本Context cost42入口约 360 个词/字,references 约 16770 个词/字。Entrypoint is about 360 words/characters; references are about 16770.
@@ -800,10 +800,10 @@
评分雷达Rating Radar完整度Completeness触发清晰Trigger clarity证据充分Evidence depth可维护性Maintainability可迁移性Portability
评分雷达展示结构完整度、触发边界、证据、维护和迁移的相对强弱。The radar chart compares completeness, trigger clarity, evidence, maintainability, and portability.

成熟度条Maturity Bar

-
  1. 稳定Stable完整度Completeness100SKILL.md 已存在,是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在,具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 360 个词/字,references 约 16740 个词/字。Entrypoint is about 360 words/characters; references are about 16740.
+
  1. 稳定Stable完整度Completeness100SKILL.md 已存在,是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在,具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 360 个词/字,references 约 16770 个词/字。Entrypoint is about 360 words/characters; references are about 16770.
-
完整度Completeness100
  • SKILL.md 已存在,是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在,便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在,便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在,具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
  • compiled_targets.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
可维护性Maintainability100
  • SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  • 入口文件保持克制,可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 360 个词/字,references 约 16740 个词/字。Entrypoint is about 360 words/characters; references are about 16740.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高,建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
+
完整度Completeness100
  • SKILL.md 已存在,是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在,便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在,便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在,具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
  • compiled_targets.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
可维护性Maintainability100
  • SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  • 入口文件保持克制,可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 360 个词/字,references 约 16770 个词/字。Entrypoint is about 360 words/characters; references are about 16770.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高,建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
@@ -878,7 +878,7 @@
- +
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。Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.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。Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.保留并复用Keep
缺口Gap上下文成本需要补强:入口约 360 个词/字,references 约 16740 个词/字。Context cost needs improvement: Entrypoint is about 360 words/characters; references are about 16740.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。Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.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。Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.保留并复用Keep
缺口Gap上下文成本需要补强:入口约 360 个词/字,references 约 16770 个词/字。Context cost needs improvement: Entrypoint is about 360 words/characters; references are about 16770.纳入下一轮修复Fix next
diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index 0f2850f..0a38613 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -102,7 +102,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 360 个词/字,references 约 16740 个词/字。", + "入口约 360 个词/字,references 约 16770 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。" ] @@ -206,7 +206,7 @@ "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 360 个词/字,references 约 16740 个词/字。" + "上下文成本需要补强:入口约 360 个词/字,references 约 16770 个词/字。" ], "recommendations": [ "先改触发边界,再扩展工作流。", @@ -1005,9 +1005,9 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "164fa736727f9162f4c61860de8fb4c7b450c026c742c6f9233520578e25c860", - "source_contract_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa", - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "evidence_bundle_sha256": "95a01210eb2bacbef1d295e72bd60fdcce075db27930533679397b5aad82e4cf", + "source_contract_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1029,7 +1029,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "15c743370e53311292e7045b2ec93f3046838055", + "commit": "c325269f10a7c691646aefc5f48ca73e0a94542f", "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.", @@ -1134,7 +1134,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 211, - "package_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa" + "package_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc" }, "skill_atlas": { "skill_count": 12, @@ -1172,8 +1172,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa", - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407" + "package_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6" }, "compatibility": { "openai": "pass", @@ -1204,7 +1204,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1220,7 +1220,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "archive_entry_count": 645, "failure_count": 0, "warning_count": 0 @@ -1299,12 +1299,12 @@ { "field": "archive_sha256", "from": "", - "to": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407" + "to": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa" + "to": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc" } ] }, diff --git a/reports/skill-overview.html b/reports/skill-overview.html index 41a77ff..497f242 100644 --- a/reports/skill-overview.html +++ b/reports/skill-overview.html @@ -764,7 +764,7 @@
  • 把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。Turn one-off experience into a reusable, evaluable, and portable skill package.
  • Skill 作者、复用团队和后续 reviewer。Skill authors, reuse teams, and later reviewers.
  • 创建完成后建议先打开 reports/skill-overview.html,再继续扩展包体。After creation, open reports/skill-overview.html before expanding the package further.
-
完整度Completeness100SKILL.md 已存在,是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
触发清晰Trigger clarity100frontmatter description 已存在,具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
上下文成本Context cost42入口约 360 个词/字,references 约 16740 个词/字。Entrypoint is about 360 words/characters; references are about 16740.
+
完整度Completeness100SKILL.md 已存在,是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
触发清晰Trigger clarity100frontmatter description 已存在,具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
上下文成本Context cost42入口约 360 个词/字,references 约 16770 个词/字。Entrypoint is about 360 words/characters; references are about 16770.
@@ -800,10 +800,10 @@
评分雷达Rating Radar完整度Completeness触发清晰Trigger clarity证据充分Evidence depth可维护性Maintainability可迁移性Portability
评分雷达展示结构完整度、触发边界、证据、维护和迁移的相对强弱。The radar chart compares completeness, trigger clarity, evidence, maintainability, and portability.

成熟度条Maturity Bar

-
  1. 稳定Stable完整度Completeness100SKILL.md 已存在,是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在,具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 360 个词/字,references 约 16740 个词/字。Entrypoint is about 360 words/characters; references are about 16740.
+
  1. 稳定Stable完整度Completeness100SKILL.md 已存在,是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在,具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 360 个词/字,references 约 16770 个词/字。Entrypoint is about 360 words/characters; references are about 16770.
-
完整度Completeness100
  • SKILL.md 已存在,是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在,便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在,便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在,具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
  • compiled_targets.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
可维护性Maintainability100
  • SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  • 入口文件保持克制,可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 360 个词/字,references 约 16740 个词/字。Entrypoint is about 360 words/characters; references are about 16740.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高,建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
+
完整度Completeness100
  • SKILL.md 已存在,是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在,便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在,便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在,具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
  • compiled_targets.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
可维护性Maintainability100
  • SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  • 入口文件保持克制,可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 360 个词/字,references 约 16770 个词/字。Entrypoint is about 360 words/characters; references are about 16770.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高,建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
@@ -878,7 +878,7 @@
- +
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。Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.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。Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.保留并复用Keep
缺口Gap上下文成本需要补强:入口约 360 个词/字,references 约 16740 个词/字。Context cost needs improvement: Entrypoint is about 360 words/characters; references are about 16740.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。Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.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。Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.保留并复用Keep
缺口Gap上下文成本需要补强:入口约 360 个词/字,references 约 16770 个词/字。Context cost needs improvement: Entrypoint is about 360 words/characters; references are about 16770.纳入下一轮修复Fix next
diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 1ed5ace..b4f9714 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -101,7 +101,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 360 个词/字,references 约 16740 个词/字。", + "入口约 360 个词/字,references 约 16770 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。" ] @@ -205,7 +205,7 @@ "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 360 个词/字,references 约 16740 个词/字。" + "上下文成本需要补强:入口约 360 个词/字,references 约 16770 个词/字。" ], "recommendations": [ "先改触发边界,再扩展工作流。", @@ -1000,9 +1000,9 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "164fa736727f9162f4c61860de8fb4c7b450c026c742c6f9233520578e25c860", - "source_contract_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa", - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "evidence_bundle_sha256": "95a01210eb2bacbef1d295e72bd60fdcce075db27930533679397b5aad82e4cf", + "source_contract_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1024,7 +1024,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "15c743370e53311292e7045b2ec93f3046838055", + "commit": "c325269f10a7c691646aefc5f48ca73e0a94542f", "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.", @@ -1129,7 +1129,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 211, - "package_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa" + "package_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc" }, "skill_atlas": { "skill_count": 12, @@ -1167,8 +1167,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa", - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407" + "package_sha256": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6" }, "compatibility": { "openai": "pass", @@ -1199,7 +1199,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1215,7 +1215,7 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407", + "archive_sha256": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6", "archive_entry_count": 645, "failure_count": 0, "warning_count": 0 @@ -1294,12 +1294,12 @@ { "field": "archive_sha256", "from": "", - "to": "167bcde6bde563dfbffa949455c36bb55a70c4e7573bf166d9a4beb36cb95407" + "to": "c26d85598e496b35e5ae4d0867a58652c62541c505c12fab5a9d6ea0598b99a6" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "8db4f8cfb8963484c2afb548453c44adca024b726e3f8cbd2ce1dcd4411cadfa" + "to": "f7b3e6749356356d3cc8b8e36bdf46a9eeedd6615f6831e033540d5bdda2b2bc" } ] },