[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C2RQ0FPE2AX1PCYCD1T2JN":3,"skill-same:01M6C2RQ0FPE2AX1PCYCD1T2JN":58},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M6C2RQ0FPE2AX1PCYCD1T2JN","technique-router",null,"Classifies GitHub issues\u002FPRs into PR-type categories and recommends autor techniques. Used by packages\u002Fcore\u002Fsrc\u002Fdecomposer.ts.","jleechanorg\u002Fjleechan-skills","jleechanorg","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F221404966?v=4","01M6C1VJ99XG950X1DWPEBCBGX","01M6C1VJDK5YVDNT3362RT5WSB",6,"MIT","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills_archive\u002F2026-08-27-historical-zero-use\u002Ftechnique-router\u002FSKILL.md",[],[18,19,20,21,22,23,24,25,26,27,28,29,30,31],"router","technique router","github","pr","packages","core","github issues","issues","src","decomposer","type","categories","techniques","prs","2026-11-10 10:12:30",false,"---\nname: technique-router\ndescription: Classifies GitHub issues\u002FPRs into PR-type categories and recommends autor techniques. Used by packages\u002Fcore\u002Fsrc\u002Fdecomposer.ts.\n---\n\n# technique-router — ZFC-Compliant PR Type Classification Skill\n\n## Purpose\n\nClassifies a GitHub issue\u002FPR description into a PR-type category, then recommends the appropriate autor technique. This is **classification-only until routing is wired**: `classifyPrType()` returns PR-type metadata, but technique resolution still happens separately through prompt\u002Fconfig defaults. All classification is delegated to the model API — no heuristic scoring, keyword matching, or hardcoded routing tables.\n\n## PR Types\n\n| Type | Description |\n|------|-------------|\n| `state-bool` | Widening boolean semantics (int 1\u002F0, string '1'\u002F'0' as valid True\u002FFalse) |\n| `data-norm` | Normalizing key names and numeric formats (xp→xp_gained, NaN handling) |\n| `ci-workflow` | GitHub Actions workflow changes (YAML scripting, gate logic) |\n| `typeddict-schema` | TypedDict + validation for previously untyped data structures |\n| `large-arch-refactor` | Module extraction, moving functions between files |\n| `unknown` | Cannot determine from the description |\n\n## Technique Selection (Autor Research — Phase 10)\n\nAll 9 autor techniques converge within rubric noise (~80-85 confidence-interval overlap). **SR-prtype is the safe default** for all PR types. No per-type routing is statistically justified.\n\n| Technique | Description | When to use |\n|-----------|-------------|-------------|\n| `SR-prtype` | Self-Refine with PR-type classification | **Safe default for all types** |\n| `SR-fewshot` | Self-Refine with single prior PR exemplar | When a highly similar prior PR exists |\n| `SR` | Basic 3-round self-refine | Fallback |\n| `ET` | Extended chain-of-thought reasoning | Complex architectural decisions |\n| `PRM` | Process Reward Model (score each step) | Debugging, multi-step reasoning |\n\n## Usage\n\n```bash\n\u002Ftechnique-router \u003Cissue-title> \u003Cissue-body-or-url>\n```\n\n## ZFC Compliance\n\nThis skill does NOT:\n- Match keywords like \"fix\", \"bug\", \"refactor\" to determine type\n- Use regex or substring checks for intent detection\n- Apply hardcoded scoring weights\n- Use if\u002Felse chains that guess intent from text\n\nThis skill DOES:\n- Pass the issue text to the model with a clear classification prompt\n- Return the model's classification as the decision\n- Let the caller decide what to do based on the classification\n\n## Integration\n\nUsed by `packages\u002Fcore\u002Fsrc\u002Fdecomposer.ts`'s `classifyPrType()` function in the AO core library. That function classifies PR type only; it does not yet select or apply a technique directly.\n","# technique-router — ZFC-Compliant PR Type Classification Skill\n\n## Purpose\n\nClassifies a GitHub issue\u002FPR description into a PR-type category, then recommends the appropriate autor technique. This is **classification-only until routing is wired**: `classifyPrType()` returns PR-type metadata, but technique resolution still happens separately through prompt\u002Fconfig defaults. All classification is delegated to the model API — no heuristic scoring, keyword matching, or hardcoded routing tables.\n\n## PR Types\n\n| Type | Description |\n|------|-------------|\n| `state-bool` | Widening boolean semantics (int 1\u002F0, string '1'\u002F'0' as valid True\u002FFalse) |\n| `data-norm` | Normalizing key names and numeric formats (xp→xp_gained, NaN handling) |\n| `ci-workflow` | GitHub Actions workflow changes (YAML scripting, gate logic) |\n| `typeddict-schema` | TypedDict + validation for previously untyped data structures |\n| `large-arch-refactor` | Module extraction, moving functions between files |\n| `unknown` | Cannot determine from the description |\n\n## Technique Selection (Autor Research — Phase 10)\n\nAll 9 autor techniques converge within rubric noise (~80-85 confidence-interval overlap). **SR-prtype is the safe default** for all PR types. No per-type routing is statistically justified.\n\n| Technique | Description | When to use |\n|-----------|-------------|-------------|\n| `SR-prtype` | Self-Refine with PR-type classification | **Safe default for all types** |\n| `SR-fewshot` | Self-Refine with single prior PR exemplar | When a highly similar prior PR exists |\n| `SR` | Basic 3-round self-refine | Fallback |\n| `ET` | Extended chain-of-thought reasoning | Complex architectural decisions |\n| `PRM` | Process Reward Model (score each step) | Debugging, multi-step reasoning |\n\n## Usage\n\n```bash\n\u002Ftechnique-router \u003Cissue-title> \u003Cissue-body-or-url>\n```\n\n## ZFC Compliance\n\nThis skill does NOT:\n- Match keywords like \"fix\", \"bug\", \"refactor\" to determine type\n- Use regex or substring checks for intent detection\n- Apply hardcoded scoring weights\n- Use if\u002Felse chains that guess intent from text\n\nThis skill DOES:\n- Pass the issue text to the model with a clear classification prompt\n- Return the model's classification as the decision\n- Let the caller decide what to do based on the classification\n\n## Integration\n\nUsed by `packages\u002Fcore\u002Fsrc\u002Fdecomposer.ts`'s `classifyPrType()` function in the AO core library. That function classifies PR type only; it does not yet select or apply a technique directly.\n",{"name":5,"description":7},"main","42ccd02cbf5e8e47839dc3eab6fc754dc6b339cf",".claude\u002Fskills_archive\u002F2026-08-27-historical-zero-use\u002Ftechnique-router",0,"https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills","https:\u002F\u002Fgithub.com\u002Fjleechanorg","2026-11-11 09:18:40",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add jleechanorg\u002Fjleechan-skills --skill technique-router",{"tool":50,"command":51},"bunx","bunx skills add jleechanorg\u002Fjleechan-skills --skill technique-router",{"tool":53,"command":54},"pnpm","pnpm dlx skills add jleechanorg\u002Fjleechan-skills --skill technique-router","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills_archive\u002F2026-08-27-historical-zero-use\u002Ftechnique-router\u002FSKILL.md",true,[],[59,77,99,113,127,143],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":32},"01M716Y5MTJ6GYJZ2ATXCJK8G4","instinct","Use when the user invokes \u002Finstinct or \u002Fin, or asks to \"message Instinct\", \"ask Instinct\", \"tell Instinct\", \"check Instinct\", or read replies from the configured peer assistant. iMessage first, WhatsApp Web as fallback.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Finstinct\u002FSKILL.md",[],[61,66,67,68,69,70,71,72,73,74,75,76],"user","when","replies","check","use","identity","whatsapp","gmail","read","message","ask",{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":88,"publishedAt":32},"01M716Y4HF7FVVMJSA2CCVN5VF","hr","Compatibility alias for history-resume; produce the same fresh-state, provenance-aware resume briefing.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhr\u002FSKILL.md",[83],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[79,89,90,91,92,93,94,95,96,97,98],"resume","compatibility","provenance","for","history","produce","alias","briefing","state","fresh",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":106,"publishedAt":32},"01M716Y1FFNFKFJYYKF8HQA6T8","history-resume","Resume briefing for the current repository branch or worktree using fresh state and admitted history sources.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhistory-resume\u002FSKILL.md",[105],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},[93,89,107,108,66,109,96,110,92,111,112,97,98],"history resume","branch","analysis","repository","worktree","sources",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":32},"01M716XWXJ8EPHK4RH9T14TR85","grok","Alias for the canonical grokbot browser conversation workflow; \u002Fgrok talks to the Grok bot the same way \u002Fdot talks to Dot.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgrok\u002FSKILL.md",[],[115,120,121,122,92,123,95,124,125,126],"dot","bot","workflow","canonical","conversation","browser","grokbot",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":32},"01M70N9Q07DTE0EW5KFXMMMSJ0","codexa-bench","Compare `codexa` and normal `codex` on a fair split of comparable work by default; use `--strict` for duplicate runs of the exact same task.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcodexa-bench\u002FSKILL.md",[],[134,135,136,70,137,92,138,139,140,141,142],"codexa bench","work","split","default","duplicate","task","compare","normal","codex",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":147,"licenseFileUrl":148,"sourceHtmlUrl":149,"categories":150,"keywords":162,"publishedAt":32},"01M6C24S2X60SP8BBFGAEKPEGW","frontend-design","Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML\u002FCSS layouts, or when styling\u002Fbeautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ffrontend-design\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ffrontend-design\u002FSKILL.md",[151,156,159],{"categoryNo":152,"categoryName":153,"taxonomyType":154,"taxonomyTypeDesc":155},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",{"categoryNo":157,"categoryName":158,"taxonomyType":154,"taxonomyTypeDesc":155},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":160,"categoryName":161,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000032","设计师",[163,164,165,70,166,167,168,66,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,67,187],"frontend","design","frontend design","generic","ui design","react","html","components","code","artifacts","ui","aesthetics","Production","web components","landing","applications","quality","web","css","create","examples","with","react components","web ui","pages"]