{"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` first.\n- Keep `SKILL.md` to routing plus a minimal execution skeleton.\n- Put long guidance in `references/`, deterministic logic in `scripts/`, and evidence in `reports/`.\n- Use the lightest process that still makes the skill reliable.\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: [Operating Modes](references/operating-modes.md), [QA Ladder](references/qa-ladder.md), [Resource Boundary Spec](references/resource-boundaries.md), [Method](references/skill-engineering-method.md).\n\n## Compact Workflow\n\n1. Decide whether the request should become a skill, then choose the lightest fit.\n2. Run a short intent dialogue to capture the real job, outputs, exclusions, constraints, and standards.\n3. Run a reference scan: external benchmarks first, user references second, local fit checks third.\n4. Write the `description` early and test route quality before expanding the package.\n5. Add only the folders and gates that earn their keep.\n6. After the first package exists, 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), [Archetypes](references/skill-archetypes.md), [Gate Selection](references/gate-selection.md), [Iteration Philosophy](references/iteration-philosophy.md), [Non-Skill Decision Tree](references/non-skill-decision-tree.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` high-leverage questions unless the user already gave enough detail\n- let the user answer naturally first; offer a tiny scaffold only as an optional shortcut\n- do not default to cold field lists such as `Name / Capability / Inputs / Outputs`\n\nChinese conversations should sound soft and companion-like rather than procedural.\n\nFor concrete opening patterns, see [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, references, gates, and next steps\n\n## Reference Map\n\nPrimary references: [Method](references/skill-engineering-method.md), [Reference Scan](references/reference-scan.md), [Intent Dialogue](references/intent-dialogue.md), [Governance](references/governance.md), [Resource Boundaries](references/resource-boundaries.md).","tags":["yao","meta","skill","yaojingang","agent-skills","ai-agents","meta-skill","prompt-engineering","skill-engineering","workflow-automation"],"capabilities":["skill","source-yaojingang","skill-yao-meta-skill","topic-agent-skills","topic-ai-agents","topic-meta-skill","topic-prompt-engineering","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":"0.599","qualityRationale":"deterministic score 0.60 from registry signals: · indexed on github topic:agent-skills · 299 github stars · SKILL.md body (2,867 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":"2026-04-22T18:55:12.630Z","embedding":null,"createdAt":"2026-04-18T23:43:21.989Z","updatedAt":"2026-04-22T18:55:12.630Z","lastSeenAt":"2026-04-22T18:55:12.630Z","tsv":"'-3':270 '1':130,338 '2':144,269,343 '3':160,346 '4':175,349 '5':188,360 '6':199 'activ':244 'add':38,189 'agent':10 'agents/interface.yaml':348 'align':347 'alreadi':278 'answer':285 'archetyp':222 'ask':21,264,267,335 'becom':136 'benchmark':166 'boundari':123,365,387 'build':50 'capabl':307 'captur':151 'check':173 'chines':310 'choos':140 'cold':301 'compact':128 'companion':317 'companion-lik':316 'concret':323 'constraint':157 'contract':331 'convers':311 'core':212 'creat':5,23 'decid':131 'decis':233 'default':299 'descript':62,178 'design':252 'desir':261 'detail':281 'determinist':78 'dialogu':149,217,328,382 'direct':211 'directori':342 'doc':16 'earli':179 'earn':196 'enough':280 'eval':39,353 'evalu':7 'evid':83 'exclus':156,366 'execut':71 'exist':36,204 'expand':185 'exploratori':98 'extern':165 'field':302 'first':63,167,202,237,243,287 'first-turn':236 'fit':143,172 'focus':106 'folder':192 'frontmatt':61 'gate':107,194,224,368 'gave':279 'govern':384 'guidanc':75 'high':272 'high-leverag':271 'improv':34 'infrastructur':110 'input':308 'intent':148,216,327,381 'iter':210,227 'job':154 'justifi':359 'keep':64,198 'ladder':120 'let':282 'leverag':273 'librari':108 'lightest':88,142 'like':247,318 'list':303 'local':171 'logic':79 'long':55,74 'make':92 'manifest.json':356 'map':373 'meta':3,48,112 'method':126,214,376 'minim':70 'mode':96,114,117 'name':306 'natur':286 'next':209,370 'non':231 'non-skil':230 'note':18 'offer':288 'open':245,324 'oper':116 'option':295,350 'otherwis':336 'outcom':262 'output':155,309,330 'packag':9,41,53,187,203 'partner':253 'pattern':325 'person':100 'philosophi':228 'playbook':213 'plus':68 'primari':374 'procedur':321 'process':29,89 'produc':337 'product':102 'prompt':14,56 'put':73 'qa':119 'qualiti':183 'question':274 'rather':319 'real':153 'refactor':6 'refer':77,163,169,219,351,367,372,375,378 'references/gate-selection.md':226 'references/governance.md':385 'references/intent-dialogue.md':218,329,383 'references/iteration-philosophy.md':229 'references/non-skill-decision-tree.md':235 'references/operating-modes.md':118 'references/qa-ladder.md':121 'references/reference-scan.md':221,380 'references/resource-boundaries.md':125,388 'references/skill-archetypes.md':223 'references/skill-engineering-method.md':127,215,377 'reliabl':95 'repeat':28 'report':85,354 'request':134 'resourc':122,386 'reus':46,104 'reusabl':32,51 'rout':59,67,182 'router':57 'rule':58,115 'run':145,161 'scaffold':97,291 'scan':164,220,379 'script':81,352 'second':170 'see':326 'select':225 'share':109 'short':147,362 'shortcut':296 'skeleton':72 'skill':4,11,25,33,37,43,49,52,94,113,138,232,242,341 'skill-yao-meta-skill' 'skill.md':65,345 'soft':314 'sound':313 'source-yaojingang' 'spec':124 'standard':159 'start':254 'step':371 'still':91 'structur':266 'style':239 'summari':363 'surfac':205 'teacher':250 'team':45,103 'test':181 'third':174 'thought':249 'three':208 'tini':290 'top':207 'topic-agent-skills' 'topic-ai-agents' 'topic-meta-skill' 'topic-prompt-engineering' 'topic-skill-engineering' 'topic-workflow-automation' 'transcript':15 'tree':234 'turn':26,238 'unless':275,332 'use':19,86,101 'user':168,257,277,284,334 'warm':246 'whether':132 'work':259,340 'workflow':13,129 'write':176 '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":"2026-04-22T18:55:12.630Z"}],"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":299,"topics":["agent-skills","ai-agents","meta-skill","prompt-engineering","skill-engineering","workflow-automation"],"license":"mit","html_url":"https://github.com/yaojingang/yao-meta-skill","pushed_at":"2026-04-19T03:47:26Z","description":"YAO = Yielding AI Outcomes. A lightweight but rigorous system for creating, evaluating, packaging, and governing reusable agent skills.","skill_md_sha":"05807ffebade6174ae35b04d58c767f47b3b397a","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":"2026-04-22T18:55:12.630Z"}}