免费在 GitHub 公开

yao-meta-skill

Build, improve, or audit reusable agent skills from workflows, prompts, procedures, or scripts. It helps define the skill’s purpose and output contract, route requests through its description, and apply evaluations and release checks appropriate to its operating mode.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Create, improve, or evaluate an existing skill from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install/trust checks, 优化已有 skill, 补 trigger 评测. Exclude summary/translation/docs, brainstorming, one-off prompts, copy-only edits, outline-only requests.

yaojingang/yao-meta-skill

实测评分未实测

查看安装方法

适用场景

Turning a repeated workflow into an agent skill
Improving a skill’s request triggers
Auditing a skill before a governed release

包含的文件（200）

SKILL.md3.0 KB
.github/workflows/test.yml356 B
.gitignore932 B
.previews/yao-meta-skill-2-comparison/index.html57.5 KB
.previews/yao-meta-skill-2-comparison/yao-meta-skill-1-vs-2-en.png771.1 KB
.previews/yao-meta-skill-2-comparison/yao-meta-skill-1-vs-2-mobile.png684.6 KB
.previews/yao-meta-skill-2-comparison/yao-meta-skill-1-vs-2.png1.1 MB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/agents/interface.yaml963 B
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/evals/output_cases.jsonl561 B
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/evals/trigger_cases.jsonl878 B
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/manifest.json516 B
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/README.md6.1 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/references/brief-structure.md1.3 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/references/review-checklist.md544 B
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/adoption_drift_report.json1.7 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/adoption_drift_report.md1.0 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/artifact-design-profile.json4.4 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/artifact-design-profile.md3.5 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/compiled_targets.json85.2 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/compiled_targets.md4.1 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/intent-confidence.json3.0 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/intent-confidence.md1.6 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/intent-context.json521 B
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/intent-dialogue.json4.2 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/intent-dialogue.md3.9 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/iteration-directions.json2.6 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/iteration-directions.md3.0 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/output-risk-profile.json6.6 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/output-risk-profile.md2.3 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/prompt-quality-profile.json5.3 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/prompt-quality-profile.md3.9 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/reference-scan.json2.1 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/reference-scan.md2.8 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/reference-synthesis.json6.9 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/reference-synthesis.md3.7 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/review_annotations.json622 B
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/review_annotations.md530 B
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/review_waivers.json1.1 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/review_waivers.md514 B
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/review-studio.html49.8 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/review-studio.json176.6 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/review-viewer.html21.8 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/review-viewer.json76.5 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/skill-ir.json3.6 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/skill-overview.html72.7 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/skill-overview.json36.7 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/system-model.json7.6 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/reports/system-model.md6.4 KB
.previews/yao-meta-skill-v2-report-demo/geo-content-brief-skill/SKILL.example.md3.7 KB
AGENTS.md17.3 KB
agents/interface.yaml713 B
assets/review-studio.css20.2 KB
assets/review-viewer.css3.1 KB
assets/skill-overview.css18.5 KB
assets/skill-overview.js1.8 KB
docs/assets/social-preview.png47.1 KB
docs/assets/social-preview.svg3.6 KB
docs/migration-1.2.0.md3.8 KB
docs/migration-v2.md2.7 KB
docs/README.fr-FR.md14.5 KB
docs/README.ja-JP.md14.7 KB
docs/README.ru-RU.md19.0 KB
docs/README.zh-CN.md22.2 KB
docs/release-notes-1.2.0.md3.1 KB
evals/adaptation/user_signals.example.jsonl743 B
evals/adversarial/trigger_cases.json1.2 KB
evals/baseline_description.txt33 B
evals/blind_holdout/trigger_cases_v2.json5.2 KB
evals/blind_holdout/trigger_cases_v2.lock.json221 B
evals/blind_holdout/trigger_cases.json1.2 KB
evals/confusion/route_cases.json3.2 KB
evals/dev/trigger_cases.json3.8 KB
evals/failure-cases.md889 B
evals/history/2026-03-31-context-first-pack.json686 B
evals/history/2026-03-31-family-suite-expansion.json635 B
evals/history/2026-03-31-governance-quality-gates.json654 B
evals/history/2026-03-31-governed-assets-and-history.json699 B
evals/history/2026-04-01-route-scorecard-foundation.json769 B
evals/history/description_optimization/2026-03-31-description-optimization-suite.json1.4 KB
evals/history/description_optimization/2026-04-01-adversarial-calibration-and-family-drift.json11.8 KB
evals/history/description_optimization/2026-04-01-blind-holdout-and-drift-history.json3.0 KB
evals/history/description_optimization/2026-04-01-judge-backed-blind-eval.json14.8 KB
evals/history/description_optimization/README.md660 B
evals/history/README.md440 B
evals/holdout/trigger_cases.json2.4 KB
evals/improved_description.txt312 B
evals/output/cases.jsonl6.4 KB
evals/output/fixtures/release-brief-source.md387 B
evals/output/holdout_cases.jsonl3.1 KB
evals/output/holdout_cases.zh-CN.jsonl3.9 KB
evals/output/provider_matrix.json826 B
evals/output/schema.json2.4 KB
evals/packaging_expectations.json1.0 KB
evals/promotion_policy.md2.1 KB
evals/README.md6.6 KB
evals/semantic_config.json12.1 KB
evals/train/trigger_cases.json4.5 KB
evals/trigger_cases.json14.1 KB
evidence/world_class/intake.schema.json12.5 KB
evidence/world_class/README.md4.4 KB
evidence/world_class/templates/human-adjudication.intake.json2.3 KB
evidence/world_class/templates/native-client-telemetry.intake.json1.9 KB
evidence/world_class/templates/native-permission-enforcement.intake.json2.5 KB
evidence/world_class/templates/provider-holdout.intake.json1.9 KB
examples/complex-release-orchestrator/design-summary.md757 B
examples/complex-release-orchestrator/generated-skill/agents/interface.yaml291 B
examples/complex-release-orchestrator/generated-skill/evals/trigger_cases.json632 B
examples/complex-release-orchestrator/generated-skill/input/release_input_example.json1.2 KB
examples/complex-release-orchestrator/generated-skill/manifest.json453 B
examples/complex-release-orchestrator/generated-skill/outputs/release_packet_example.md1.0 KB
examples/complex-release-orchestrator/generated-skill/references/migration-template.md372 B
examples/complex-release-orchestrator/generated-skill/references/release-checklist.md705 B
examples/complex-release-orchestrator/generated-skill/references/risk-matrix.md619 B
examples/complex-release-orchestrator/generated-skill/references/stakeholder-comms.md526 B
examples/complex-release-orchestrator/generated-skill/reports/context_budget.json1.3 KB
examples/complex-release-orchestrator/generated-skill/scripts/build_release_packet.py1.4 KB
examples/complex-release-orchestrator/generated-skill/SKILL.example.md2.8 KB
examples/complex-release-orchestrator/raw-workflow.md919 B
examples/evolution-frontend-review/eval-delta.md319 B
examples/evolution-frontend-review/final/SKILL.example.md966 B
examples/evolution-frontend-review/raw-workflow.md220 B
examples/evolution-frontend-review/README.md291 B
examples/evolution-frontend-review/v0/SKILL.example.md149 B
examples/evolution-frontend-review/v1/SKILL.example.md518 B
examples/governed-incident-command/design-summary.md917 B
examples/governed-incident-command/generated-skill/agents/interface.yaml411 B
examples/governed-incident-command/generated-skill/evals/trigger_cases.json522 B
examples/governed-incident-command/generated-skill/input/incident_input_example.json613 B
examples/governed-incident-command/generated-skill/manifest.json539 B
examples/governed-incident-command/generated-skill/outputs/incident_packet_example.md815 B
examples/governed-incident-command/generated-skill/references/comms-policy.md336 B
examples/governed-incident-command/generated-skill/references/review-policy.md397 B
examples/governed-incident-command/generated-skill/references/severity-matrix.md332 B
examples/governed-incident-command/generated-skill/reports/context_budget.json1.3 KB
examples/governed-incident-command/generated-skill/reports/governance_score.json772 B
examples/governed-incident-command/generated-skill/reports/revision_history.md163 B
examples/governed-incident-command/generated-skill/scripts/build_incident_packet.py1.1 KB
examples/governed-incident-command/generated-skill/SKILL.example.md2.6 KB
examples/governed-incident-command/optimization/adversarial/trigger_cases.json1.2 KB
examples/governed-incident-command/optimization/baseline_description.txt376 B
examples/governed-incident-command/optimization/blind_holdout/trigger_cases.json1.0 KB
examples/governed-incident-command/optimization/dev/trigger_cases.json1.2 KB
examples/governed-incident-command/optimization/holdout/trigger_cases.json927 B
examples/governed-incident-command/optimization/reports/description_optimization.json191.9 KB
examples/governed-incident-command/optimization/reports/description_optimization.md2.1 KB
examples/governed-incident-command/optimization/semantic_config.json3.5 KB
examples/governed-incident-command/raw-workflow.md794 B
examples/README.md1.9 KB
examples/simple-note-cleanup/design-summary.md268 B
examples/simple-note-cleanup/generated-skill/agents/interface.yaml223 B
examples/simple-note-cleanup/generated-skill/SKILL.example.md488 B
examples/simple-note-cleanup/raw-workflow.md336 B
examples/team-frontend-review/design-summary.md350 B
examples/team-frontend-review/generated-skill/agents/interface.yaml203 B
examples/team-frontend-review/generated-skill/references/checklist.md361 B
examples/team-frontend-review/generated-skill/SKILL.example.md1.0 KB
examples/team-frontend-review/optimization/adversarial/trigger_cases.json1.2 KB
examples/team-frontend-review/optimization/baseline_description.txt210 B
examples/team-frontend-review/optimization/blind_holdout/trigger_cases.json941 B
examples/team-frontend-review/optimization/dev/trigger_cases.json1.5 KB
examples/team-frontend-review/optimization/holdout/trigger_cases.json934 B
examples/team-frontend-review/optimization/reports/description_optimization.json204.1 KB
examples/team-frontend-review/optimization/reports/description_optimization.md2.2 KB
examples/team-frontend-review/optimization/semantic_config.json3.2 KB
examples/team-frontend-review/raw-workflow.md356 B
failures/document-export-vs-agent-skill/cases.json664 B
failures/document-export-vs-agent-skill/README.md721 B
failures/explain-not-package/cases.json595 B
failures/explain-not-package/README.md718 B
failures/future-outline-vs-build/cases.json552 B
failures/future-outline-vs-build/README.md805 B
failures/one-off-vs-reusable/cases.json497 B
failures/one-off-vs-reusable/README.md713 B
failures/README.md493 B
LICENSE1.0 KB
Makefile13.1 KB
manifest.json566 B
README.md59.7 KB
references/artifact-design-doctrine.md2.8 KB
references/authoring-discipline.md3.4 KB
references/autonomous-adaptation.md4.2 KB
references/distribution-registry-method.md4.0 KB
references/eval-playbook.md1.3 KB
references/evidence-publication.md2.2 KB
references/gate-selection.md1.7 KB
references/governance.md3.0 KB
references/human-review-template.md1.3 KB
references/intent-dialogue.md7.6 KB
references/iteration-philosophy.md1.1 KB
references/non-skill-decision-tree.md955 B
references/operating-modes.md3.0 KB
references/output-eval-method.md5.2 KB
references/output-quality-risk.md2.0 KB
references/output-visual-quality.md2.1 KB
references/packaging-contracts.md2.7 KB
references/pattern-extraction-doctrine.md2.5 KB
references/platform-capability-matrix.md3.0 KB
references/prompt-engineering-doctrine.md3.5 KB
references/provider-output-evaluation.md2.6 KB
references/qa-ladder.md1.3 KB

SKILL.md（原文）

安装前可以查看交给 AI 代理的指令内容。

Yao Meta Skill

Router Rules

Route by frontmatter description using the lightest mode.
Keep SKILL.md lean: guidance in references/, logic in scripts/, evidence in reports/.

Modes

Scaffold: exploratory; Production: team; Library: shared; Governed: release-critical.
Rules: Method, Modes, Boundaries.

Compact Workflow

Require repeated use + reusable output contract; skip one-offs.
Lock target path + identity before writes; self-edits require --self.
Capture job, output, exclusions, constraints, standards, mode.
Scan 3-5 useful external/user/local references.
Write description early; route edits need trigger_eval.py; release gates follow risk.
Add deeper profiles only when earned.

Playbooks: Target Safety, Intent, Skill IR, Output Eval, Review Studio.

Updates

Activation: scripts/yao.py check-update --notice --self; show notice_text if requested; continue. “更新”: scripts/yao.py self-update --self --yes.

Skill OS 2.0 Gates

For production/library/governed releases, run Skill IR, compiler, trigger/output eval, Atlas, conformance, trust, package/install, upgrade, drift, waiver, Review Studio.

Governed Package Boundary

Governed/file-backed packages: label input_files a file-backed fixture; include owner, review cadence, output contract, rollback boundary; require trust report and reports/output_quality_scorecard.md; mark unavailable telemetry/approvals/metrics/benchmarks as missing evidence; never fabricate evidence.

Preserve labels literally when they apply: file-backed fixture, input_files, output contract, rollback boundary, trust report, reports/output_quality_scorecard.md, missing evidence.

First-Turn Style

Infer non-core gaps; ask one core-fork question per round, max two, then use recorded preferred inference.
In Chinese, sound soft and companion-like; use Intent Dialogue.

Output Contract

Builds: SKILL.md, aligned interface, justified assets, boundary/gate summary. Audits: findings + fixes; edit only when asked. No-skill: no files.

Reference Map

Primary: Method, Artifact Design, Systems, Governance, SkillOps.

评价

还没有评价。欢迎分享你的使用感受。

无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

报告此技能的问题

安装

用命令安装

npx skills add https://github.com/yaojingang/yao-meta-skill --skill yao-meta-skill

粘贴到终端中运行（需要 Node.js）。可以选择安装到 Claude Code、Codex 等代理。

让代理安装

请安装以下 Agent Skill。
https://github.com/yaojingang/yao-meta-skill

请先检查 SKILL.md 和附带文件的内容，确认没有可疑的处理（向外部发送数据、读取认证信息等）后，再放到 ~/.claude/skills/yao-meta-skill/（Claude Code）或 ~/.agents/skills/yao-meta-skill/（Codex）。

把这段文字直接发给 Claude Code 或 Codex，它会先检查内容再安装。

在 GitHub 查看源代码

仓库: yaojingang/yao-meta-skill
星标: 2,707
复刻: 251
分类: 数据与 AI
许可证: MIT
原文语言: 英语
最后更新: 2026年8月17日

技能是给 AI 代理的指令和脚本的集合。cccskills 不保证其内容的安全性，安装前请务必确认内容。