[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ADB89V0KYRJP9Q5APDD2WJ":3,"skill-same:01M6ADB89V0KYRJP9Q5APDD2WJ":73},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":48,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6ADB89V0KYRJP9Q5APDD2WJ","reskill",null,"Team-wide charter and history optimization through skill extraction","github\u002Fgh-aw","github","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9919?v=4","01M6AC83DS133TPXFSP1DHNCC6","GitHub","01M6AD3VCZ4WKQSFSRTPN7N9DN",5636,"MIT","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Freskill\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35],"extraction","Optimization","team","history","context","directive","manual","high","wide","reduce","overhead","charter","2026-11-10 10:12:30",false,"---\nname: \"reskill\"\ndescription: \"Team-wide charter and history optimization through skill extraction\"\ndomain: \"team-optimization\"\nconfidence: \"high\"\nsource: \"manual — Brady directive to reduce per-agent context overhead\"\n---\n\n## Context\n\nWhen the coordinator hears \"team, reskill\" (or similar: \"optimize context\", \"slim down charters\"), trigger a team-wide optimization pass. The goal: reduce per-agent context consumption by extracting shared patterns from charters and histories into reusable skills.\n\nThis is a periodic maintenance activity. Run whenever charter\u002Fhistory bloat is suspected.\n\n## Process\n\n### Step 1: Audit\nRead all agent charters and histories. Measure byte sizes. Identify:\n\n- **Boilerplate** — sections repeated across ≥3 charters with \u003C10% variation (collaboration, model, boundaries template)\n- **Shared knowledge** — domain knowledge duplicated in 2+ charters (incident postmortems, technical patterns)\n- **Mature learnings** — history entries appearing 3+ times across agents that should be promoted to skills\n\n### Step 2: Extract\nFor each identified pattern:\n1. Create or update a skill at `.squad\u002Fskills\u002F{skill-name}\u002FSKILL.md`\n2. Follow the skill template format (frontmatter + Context + Patterns + Examples + Anti-Patterns)\n3. Set confidence: low (first observation), medium (2+ agents), high (team-wide)\n\n### Step 3: Trim\n**Charters** — target ≤1.5KB per agent:\n- Remove Collaboration section entirely (spawn prompt + agent-collaboration skill covers it)\n- Remove Voice section (tagline blockquote at top of charter already captures it)\n- Trim Model section to single line: `Preferred: {model}`\n- Remove \"When I'm unsure\" boilerplate from Boundaries\n- Remove domain knowledge now covered by a skill — add skill reference comment if helpful\n- Keep: Identity, What I Own, unique How I Work patterns, Boundaries (domain list only)\n\n**Histories** — target ≤8KB per agent:\n- Apply history-hygiene skill to any history >12KB\n- Promote recurring patterns (3+ occurrences across agents) to skills\n- Summarize old entries into `## Core Context` section\n- Remove session-specific metadata (dates, branch names, requester names)\n\n### Step 4: Report\nOutput a savings table:\n\n| Agent | Charter Before | Charter After | History Before | History After | Saved |\n|-------|---------------|---------------|----------------|---------------|-------|\n\nInclude totals and percentage reduction.\n\n## Patterns\n\n### Minimal Charter Template (target format after reskill)\n\n```\n# {Name} — {Role}\n\n> {Tagline — one sentence capturing voice and philosophy}\n\n## Identity\n- **Name:** {Name}\n- **Role:** {Role}\n- **Expertise:** {comma-separated list}\n\n## What I Own\n- {bullet list of owned artifacts\u002Fdomains}\n\n## How I Work\n- {unique patterns and principles — NOT boilerplate}\n\n## Boundaries\n**I handle:** {domain list}\n**I don't handle:** {explicit exclusions}\n\n## Model\nPreferred: {model}\n```\n\n### Skill Extraction Threshold\n- **1 charter** → leave in charter (unique to that agent)\n- **2 charters** → consider extracting if >500 bytes of overlap\n- **3+ charters** → always extract to a shared skill\n\n## Anti-Patterns\n- Don't delete unique per-agent identity or domain-specific knowledge\n- Don't create skills for content only one agent uses\n- Don't merge unrelated patterns into a single mega-skill\n- Don't remove Model preference line (coordinator needs it for model selection)\n- Don't touch `.squad\u002Fdecisions.md` during reskill\n- Don't remove the tagline blockquote — it's the charter's soul in one line\n","## Context\n\nWhen the coordinator hears \"team, reskill\" (or similar: \"optimize context\", \"slim down charters\"), trigger a team-wide optimization pass. The goal: reduce per-agent context consumption by extracting shared patterns from charters and histories into reusable skills.\n\nThis is a periodic maintenance activity. Run whenever charter\u002Fhistory bloat is suspected.\n\n## Process\n\n### Step 1: Audit\nRead all agent charters and histories. Measure byte sizes. Identify:\n\n- **Boilerplate** — sections repeated across ≥3 charters with \u003C10% variation (collaboration, model, boundaries template)\n- **Shared knowledge** — domain knowledge duplicated in 2+ charters (incident postmortems, technical patterns)\n- **Mature learnings** — history entries appearing 3+ times across agents that should be promoted to skills\n\n### Step 2: Extract\nFor each identified pattern:\n1. Create or update a skill at `.squad\u002Fskills\u002F{skill-name}\u002FSKILL.md`\n2. Follow the skill template format (frontmatter + Context + Patterns + Examples + Anti-Patterns)\n3. Set confidence: low (first observation), medium (2+ agents), high (team-wide)\n\n### Step 3: Trim\n**Charters** — target ≤1.5KB per agent:\n- Remove Collaboration section entirely (spawn prompt + agent-collaboration skill covers it)\n- Remove Voice section (tagline blockquote at top of charter already captures it)\n- Trim Model section to single line: `Preferred: {model}`\n- Remove \"When I'm unsure\" boilerplate from Boundaries\n- Remove domain knowledge now covered by a skill — add skill reference comment if helpful\n- Keep: Identity, What I Own, unique How I Work patterns, Boundaries (domain list only)\n\n**Histories** — target ≤8KB per agent:\n- Apply history-hygiene skill to any history >12KB\n- Promote recurring patterns (3+ occurrences across agents) to skills\n- Summarize old entries into `## Core Context` section\n- Remove session-specific metadata (dates, branch names, requester names)\n\n### Step 4: Report\nOutput a savings table:\n\n| Agent | Charter Before | Charter After | History Before | History After | Saved |\n|-------|---------------|---------------|----------------|---------------|-------|\n\nInclude totals and percentage reduction.\n\n## Patterns\n\n### Minimal Charter Template (target format after reskill)\n\n```\n# {Name} — {Role}\n\n> {Tagline — one sentence capturing voice and philosophy}\n\n## Identity\n- **Name:** {Name}\n- **Role:** {Role}\n- **Expertise:** {comma-separated list}\n\n## What I Own\n- {bullet list of owned artifacts\u002Fdomains}\n\n## How I Work\n- {unique patterns and principles — NOT boilerplate}\n\n## Boundaries\n**I handle:** {domain list}\n**I don't handle:** {explicit exclusions}\n\n## Model\nPreferred: {model}\n```\n\n### Skill Extraction Threshold\n- **1 charter** → leave in charter (unique to that agent)\n- **2 charters** → consider extracting if >500 bytes of overlap\n- **3+ charters** → always extract to a shared skill\n\n## Anti-Patterns\n- Don't delete unique per-agent identity or domain-specific knowledge\n- Don't create skills for content only one agent uses\n- Don't merge unrelated patterns into a single mega-skill\n- Don't remove Model preference line (coordinator needs it for model selection)\n- Don't touch `.squad\u002Fdecisions.md` during reskill\n- Don't remove the tagline blockquote — it's the charter's soul in one line\n",{"name":5,"domain":41,"source":42,"confidence":31,"description":7},"team-optimization","manual — Brady directive to reduce per-agent context overhead","main","8541229759617347888641eba917d3b0ad66a984",".squad\u002Ftemplates\u002Fskills\u002Freskill",626,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw","https:\u002F\u002Fgh.io\u002Fgh-aw","https:\u002F\u002Fgithub.com\u002Fgithub","https:\u002F\u002Fgithub.com\u002Fabout","How people build software.","2026-11-15 06:45:15",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add github\u002Fgh-aw --skill reskill",{"tool":59,"command":60},"bunx","bunx skills add github\u002Fgh-aw --skill reskill",{"tool":62,"command":63},"pnpm","pnpm dlx skills add github\u002Fgh-aw --skill reskill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Freskill\u002FSKILL.md",true,[67],{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"agents\u002Fopenai.yaml","REFERENCE","参考文档",166,"https:\u002F\u002Fgithub.com\u002Fajrussellaudio\u002Fdotfiles\u002Fblob\u002Fmain\u002Fagents\u002F.claude\u002Fskills\u002Fto-questionnaire\u002Fagents\u002Fopenai.yaml",[74,82,90,115,132,157],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":81},"01M7DQYVZ9W9DDXKQ9452SNP8J","cracktro","Edit, preview, and verify the standalone interactive talk deck in docs\u002Fpublic\u002Fcracktro (slides, SVG diagrams, transitions, WebAudio sound).","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fcracktro\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":89},"01M7612HQ4378TK8QZ5HPAF4KR","create-connector","Create or extend a declaration-only third-party connector, with narrow reads, separate safe outputs, optional protected triggers, and offline conformance evidence.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fcreate-connector\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":100,"publishedAt":36},"01M6ADC942STTXHFV410J4DH0X","GitHub Agentic Workflows","GitHub Agentic Workflows (`gh-aw`) is a GitHub CLI extension for writing Agentic Workflows in markdown and compiling them to GitHub Actions.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002FSKILL.md",[96,99],{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[9,101,102,103,104,105,106,107,108,109,110,111,112,113,114],"github agentic workflows","agentic workflows","workflows","agentic","extension","markdown","github cli","cli","gh","for","compiling","writing","github actions","actions",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":36},"01M6ADC6ZXSA46N9XD6VNAP1MS","windows-compatibility","Cross-platform path handling and command patterns","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fwindows-compatibility\u002FSKILL.md",[],[122,123,124,125,126,127,128,31,129,130,131],"windows","windows compatibility","compatibility","command","git","bugs","platform","patterns","cross-platform","path",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":36},"01M6ADC44957SVQF96R5YY247P","versioning-policy","Semver versioning rules for Squad SDK and CLI — prevents prerelease version incidents","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fversioning-policy\u002FSKILL.md",[],[139,140,141,142,143,108,144,145,146,147,148,149,150,151,110,152,153,154,155,156],"versioning","policy","versioning policy","gate","implementation","workspace","pr","sdk","release","ci","npm","semver","squad","incident","incidents","Rules","version","resolution",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":167,"publishedAt":36},"01M6ADC1PHMEAEVR87F8PDR89X","tiered-memory","Three-tier agent memory model (hot\u002Fcold\u002Fwiki) for context reduction per spawn","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Ftiered-memory\u002FSKILL.md",[163,166],{"categoryNo":164,"categoryName":165,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[168,169,170,171,172,173,174,175,176,177,178,28,179,110,180,181],"tiered memory","memory","performance","design","agent memory","proposal","cold","model","wiki","spawn","memory-management","three","runtime","management"]