{"id":"5c14ac8f-96de-49fb-9297-cbbee5013cc0","shortId":"DwUBEU","kind":"skill","title":"yao-meta-skill","tagline":"Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.","description":"# Yao Meta Skill\n\nBuild reusable skill packages, not long prompts.\n\n## Router Rules\n\n- Route by frontmatter `description`.\n- Keep `SKILL.md` lean.\n- Put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.\n- Use the lightest reliable process.\n\n## Modes\n\n- `Scaffold`: exploratory or personal use.\n- `Production`: team reuse with focused gates.\n- `Library`: shared infrastructure or meta skill.\n\nMode rules: [Method](references/skill-engineering-method.md), [Operating Modes](references/operating-modes.md), [Resource Boundaries](references/resource-boundaries.md).\n\n## Compact Workflow\n\n1. Decide whether the request should become a skill and choose the lightest fit.\n2. Capture job, output, exclusions, constraints, and standards.\n3. Run a reference scan: external benchmarks first, user references second, local fit third. Keep synthesis silent unless intent stays unclear or a real design conflict needs a user call.\n4. Write the `description` early and test route quality before expanding the package.\n5. Add output-risk, artifact-design, and prompt-quality profiles only when they matter.\n6. Add only folders and gates that earn their keep.\n7. Surface the top three next iteration directions.\n\nCore playbooks: [Method](references/skill-engineering-method.md), [Intent Dialogue](references/intent-dialogue.md), [Reference Scan](references/reference-scan.md), [Artifact Design](references/artifact-design-doctrine.md), [Prompt Engineering](references/prompt-engineering-doctrine.md).\n\n## First-Turn Style\n\nWhen the skill first activates:\n\n- open warmly, like a thoughtful teacher or design partner\n- start from the user's work and desired outcome before asking for structure\n- ask only `2-3` key questions unless the user already gave enough detail\n- let the user answer naturally first; offer a tiny scaffold only as a shortcut\n- avoid cold field lists and turn benchmark work into one recommendation unless uncertainty or conflict needs a visible call\n\nChinese conversations should sound soft and companion-like rather than procedural.\n\nOpening patterns: [Intent Dialogue](references/intent-dialogue.md).\n\n## Output Contract\n\nUnless the user asks otherwise, produce:\n\n1. a working skill directory\n2. a `SKILL.md`\n3. aligned `agents/interface.yaml`\n4. optional `references/`, `scripts/`, `evals/`, `reports/`, and `manifest.json` only when justified\n5. a short summary of boundary, exclusions, gates, and next steps\n\n## Reference Map\n\nPrimary references: [Method](references/skill-engineering-method.md), [Reference Scan](references/reference-scan.md), [Artifact Design](references/artifact-design-doctrine.md), [Prompt Engineering](references/prompt-engineering-doctrine.md), [Governance](references/governance.md).","tags":["yao","meta","skill","yaojingang","agent-skills","ai-agents","evaluation","governance","meta-skill","portability","skill-engineering","workflow-automation"],"capabilities":["skill","source-yaojingang","skill-yao-meta-skill","topic-agent-skills","topic-ai-agents","topic-evaluation","topic-governance","topic-meta-skill","topic-portability","topic-skill-engineering","topic-workflow-automation"],"categories":["yao-meta-skill"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/yaojingang/yao-meta-skill","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add yaojingang/yao-meta-skill","source_repo":"https://github.com/yaojingang/yao-meta-skill","install_from":"skills.sh"}},"qualityScore":"0.640","qualityRationale":"deterministic score 0.64 from registry signals: · indexed on github topic:agent-skills · 380 github stars · SKILL.md body (2,743 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T18:54:24.696Z","embedding":null,"createdAt":"2026-04-18T23:43:21.989Z","updatedAt":"2026-05-18T18:54:24.696Z","lastSeenAt":"2026-05-18T18:54:24.696Z","tsv":"'-3':262 '1':112,330 '2':126,261,335 '3':134,338 '4':164,341 '5':177,352 '6':194 '7':204 'activ':236 'add':38,178,195 'agent':10 'agents/interface.yaml':340 'align':339 'alreadi':268 'answer':275 'artifact':183,222,372 'artifact-design':182 'ask':21,256,259,327 'avoid':286 'becom':118 'benchmark':140,292 'boundari':108,357 'build':50 'call':163,304 'captur':127 'chines':305 'choos':122 'cold':287 'compact':110 'companion':312 'companion-lik':311 'conflict':159,300 'constraint':131 'contract':323 'convers':306 'core':212 'creat':5,23 'decid':113 'descript':62,167 'design':158,184,223,244,373 'desir':253 'detail':271 'dialogu':217,320 'direct':211 'directori':334 'doc':16 'earli':168 'earn':201 'engin':226,376 'enough':270 'eval':39,345 'evalu':7 'evid':74 'exclus':130,358 'exist':36 'expand':174 'exploratori':84 'extern':139 'field':288 'first':141,229,235,277 'first-turn':228 'fit':125,146 'focus':92 'folder':197 'frontmatt':61 'gate':93,199,359 'gave':269 'govern':378 'guidanc':67 'improv':34 'infrastructur':96 'intent':152,216,319 'iter':210 'job':128 'justifi':351 'keep':63,148,203 'key':263 'lean':65 'let':272 'librari':94 'lightest':79,124 'like':239,313 'list':289 'local':145 'logic':70 'long':55 'manifest.json':348 'map':364 'matter':193 'meta':3,48,98 'method':102,214,367 'mode':82,100,105 'natur':276 'need':160,301 'next':209,361 'note':18 'offer':278 'one':295 'open':237,317 'oper':104 'option':342 'otherwis':328 'outcom':254 'output':129,180,322 'output-risk':179 'packag':9,41,53,176 'partner':245 'pattern':318 'person':86 'playbook':213 'primari':365 'procedur':316 'process':29,81 'produc':329 'product':88 'profil':189 'prompt':14,56,187,225,375 'prompt-qual':186 'put':66 'qualiti':172,188 'question':264 'rather':314 'real':157 'recommend':296 'refactor':6 'refer':69,137,143,219,343,363,366,369 'references/artifact-design-doctrine.md':224,374 'references/governance.md':379 'references/intent-dialogue.md':218,321 'references/operating-modes.md':106 'references/prompt-engineering-doctrine.md':227,377 'references/reference-scan.md':221,371 'references/resource-boundaries.md':109 'references/skill-engineering-method.md':103,215,368 'reliabl':80 'repeat':28 'report':76,346 'request':116 'resourc':107 'reus':46,90 'reusabl':32,51 'risk':181 'rout':59,171 'router':57 'rule':58,101 'run':135 'scaffold':83,281 'scan':138,220,370 'script':72,344 'second':144 'share':95 'short':354 'shortcut':285 'silent':150 'skill':4,11,25,33,37,43,49,52,99,120,234,333 'skill-yao-meta-skill' 'skill.md':64,337 'soft':309 'sound':308 'source-yaojingang' 'standard':133 'start':246 'stay':153 'step':362 'structur':258 'style':231 'summari':355 'surfac':205 'synthesi':149 'teacher':242 'team':45,89 'test':170 'third':147 'thought':241 'three':208 'tini':280 'top':207 'topic-agent-skills' 'topic-ai-agents' 'topic-evaluation' 'topic-governance' 'topic-meta-skill' 'topic-portability' 'topic-skill-engineering' 'topic-workflow-automation' 'transcript':15 'turn':26,230,291 'uncertainti':298 'unclear':154 'unless':151,265,297,324 'use':19,77,87 'user':142,162,249,267,274,326 'visibl':303 'warm':238 'whether':114 'work':251,293,332 'workflow':13,111 'write':165 'yao':2,47 'yao-meta-skil':1","prices":[{"id":"45dccee6-8e7b-467d-9bc1-935b75cd848a","listingId":"5c14ac8f-96de-49fb-9297-cbbee5013cc0","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"yaojingang","category":"yao-meta-skill","install_from":"skills.sh"},"createdAt":"2026-04-18T23:43:21.989Z"}],"sources":[{"listingId":"5c14ac8f-96de-49fb-9297-cbbee5013cc0","source":"github","sourceId":"yaojingang/yao-meta-skill","sourceUrl":"https://github.com/yaojingang/yao-meta-skill","isPrimary":false,"firstSeenAt":"2026-04-18T23:43:21.989Z","lastSeenAt":"2026-05-18T18:54:24.696Z"}],"details":{"listingId":"5c14ac8f-96de-49fb-9297-cbbee5013cc0","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"yaojingang","slug":"yao-meta-skill","github":{"repo":"yaojingang/yao-meta-skill","stars":380,"topics":["agent-skills","ai-agents","evaluation","governance","meta-skill","portability","skill-engineering","workflow-automation"],"license":"mit","html_url":"https://github.com/yaojingang/yao-meta-skill","pushed_at":"2026-05-09T07:48:38Z","description":"YAO = Yielding AI Outcomes. A rigorous engineering, evaluation, governance, and portability system for reusable agent skills.","skill_md_sha":"983b71fd7b048474977aeeb8a3b0e88ad93b0e60","skill_md_path":"SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/yaojingang/yao-meta-skill"},"layout":"root","source":"github","category":"yao-meta-skill","frontmatter":{"name":"yao-meta-skill","description":"Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse."},"skills_sh_url":"https://skills.sh/yaojingang/yao-meta-skill"},"updatedAt":"2026-05-18T18:54:24.696Z"}}