[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6R974R9TSTA9KFM68BYTPVM":3,"skill-same:01M6R974R9TSTA9KFM68BYTPVM":66},{"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":18,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":49,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M6R974R9TSTA9KFM68BYTPVM","feature-deep-dive",null,"Build a code-verified mental model of one feature or subsystem. Use before owning, debugging, changing, reviewing, or redesigning a complex area that needs a technical trace from entry point to data, jobs, providers, failures, and tests.","Nairon-AI\u002Fagentic-starter-pack","Nairon-AI","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F260662138?v=4","01M6R8PZ1Y8CSQGFN61VACZGTH","Nairon AI","01M6R8PZ6184VR3BA88YZFBC3N",4,"MIT","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fengineering\u002Ffeature-deep-dive\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"feature deep dive","deep dive","feature","deep","build","point","entry","mental model","verified","tests","debugging","jobs","use","technical","trace","model","Providers","data","code","2026-11-10 10:12:30",false,"---\nname: feature-deep-dive\ndescription: Build a code-verified mental model of one feature or subsystem. Use before owning, debugging, changing, reviewing, or redesigning a complex area that needs a technical trace from entry point to data, jobs, providers, failures, and tests.\n---\n\n# Feature Deep Dive\n\nBuild debug-grade understanding of one feature or subsystem. Do not change code unless the user asks.\n\nOne responsibility: make a developer understand one area well enough to debug\u002Fchange it without guessing.\n\n## Scope\n\nChoose one vertical slice or subsystem only: invite claim, promotion scheduling, content generation callback flow, search ranking, billing checkout, etc.\n\nIf the user needs the whole-system map first, use `rebuild-mental-model`. If this trace changes the global model, update or hand off to `rebuild-mental-model`.\n\n## Output\n\nFollow repo conventions first. If none exist, create\u002Fupdate:\n\n- `docs\u002Ffeature-deep-dives\u002F\u003Cfeature-slug>.md`\n- `CONTEXT.md` if domain language changes and it exists; otherwise `docs\u002Fubiquitous-language.md`\n\nNever include secrets or env values. Provider\u002Fenv var names are fine.\n\n## Workflow\n\n1. **Frame** - user\u002Fbusiness goal, trigger, success condition, core object\u002Fstate, in\u002Fout boundaries.\n2. **Trace** - entry point, API\u002Fservice\u002Fhelper path, persistence\u002Fsource of truth, jobs\u002Fevents, providers\u002Fwebhooks, permissions, tests.\n3. **Pressure-test** - state transitions, idempotency, partial failure, retries, races, legacy behavior, observability, first debug handles.\n4. **Update docs** - write the feature doc, update ubiquitous language when terms drift, record global architecture impacts.\n5. **Teach\u002Fverify** - explain layer by layer, ask for restatement when useful, correct gaps before calling the area understood.\n\n## Feature Doc Contract\n\n- Verification coverage\n- Overview\n- Actor and boundary map\n- Runtime path\n- State transitions\n- Source of truth\n- Providers and external effects\n- Permissions and security notes\n- Failure modes, retries, and idempotency\n- Observability\u002Fdebug playbook\n- Test surface\n- Global architecture impact\n- Open questions and follow-ups\n- Quick recall\n\n## Verification Labels\n\nMark claims explicitly:\n\n- `verified` - confirmed from code\u002Fconfig\u002Fschema\u002Ftests.\n- `partial` - traced but not end-to-end.\n- `not verified` - plausible or doc-derived only.\n- `drift` - docs and code disagree.\n\nNever present intended future behavior as current code.\n\n## Quick Recall Contract\n\nEnd every feature doc with:\n\n```md\n## Quick Recall\n- What this feature does:\n- Main trigger:\n- Source of truth:\n- Top files\u002Fboundaries:\n- Top tables\u002Fmodels:\n- Providers:\n- First debug checks:\n- Biggest trap:\n- Global architecture impact:\n```\n\n## Completion Standard\n\nBefore finishing:\n\n- One feature doc is updated.\n- Verification labels are present.\n- Ubiquitous language is updated or explicitly unchanged.\n- Debug handles and tests are named.\n- Global architecture impacts are listed, even when the answer is `None`.\n","# Feature Deep Dive\n\nBuild debug-grade understanding of one feature or subsystem. Do not change code unless the user asks.\n\nOne responsibility: make a developer understand one area well enough to debug\u002Fchange it without guessing.\n\n## Scope\n\nChoose one vertical slice or subsystem only: invite claim, promotion scheduling, content generation callback flow, search ranking, billing checkout, etc.\n\nIf the user needs the whole-system map first, use `rebuild-mental-model`. If this trace changes the global model, update or hand off to `rebuild-mental-model`.\n\n## Output\n\nFollow repo conventions first. If none exist, create\u002Fupdate:\n\n- `docs\u002Ffeature-deep-dives\u002F\u003Cfeature-slug>.md`\n- `CONTEXT.md` if domain language changes and it exists; otherwise `docs\u002Fubiquitous-language.md`\n\nNever include secrets or env values. Provider\u002Fenv var names are fine.\n\n## Workflow\n\n1. **Frame** - user\u002Fbusiness goal, trigger, success condition, core object\u002Fstate, in\u002Fout boundaries.\n2. **Trace** - entry point, API\u002Fservice\u002Fhelper path, persistence\u002Fsource of truth, jobs\u002Fevents, providers\u002Fwebhooks, permissions, tests.\n3. **Pressure-test** - state transitions, idempotency, partial failure, retries, races, legacy behavior, observability, first debug handles.\n4. **Update docs** - write the feature doc, update ubiquitous language when terms drift, record global architecture impacts.\n5. **Teach\u002Fverify** - explain layer by layer, ask for restatement when useful, correct gaps before calling the area understood.\n\n## Feature Doc Contract\n\n- Verification coverage\n- Overview\n- Actor and boundary map\n- Runtime path\n- State transitions\n- Source of truth\n- Providers and external effects\n- Permissions and security notes\n- Failure modes, retries, and idempotency\n- Observability\u002Fdebug playbook\n- Test surface\n- Global architecture impact\n- Open questions and follow-ups\n- Quick recall\n\n## Verification Labels\n\nMark claims explicitly:\n\n- `verified` - confirmed from code\u002Fconfig\u002Fschema\u002Ftests.\n- `partial` - traced but not end-to-end.\n- `not verified` - plausible or doc-derived only.\n- `drift` - docs and code disagree.\n\nNever present intended future behavior as current code.\n\n## Quick Recall Contract\n\nEnd every feature doc with:\n\n```md\n## Quick Recall\n- What this feature does:\n- Main trigger:\n- Source of truth:\n- Top files\u002Fboundaries:\n- Top tables\u002Fmodels:\n- Providers:\n- First debug checks:\n- Biggest trap:\n- Global architecture impact:\n```\n\n## Completion Standard\n\nBefore finishing:\n\n- One feature doc is updated.\n- Verification labels are present.\n- Ubiquitous language is updated or explicitly unchanged.\n- Debug handles and tests are named.\n- Global architecture impacts are listed, even when the answer is `None`.\n",{"name":5,"description":7},"main","c9d0c408715983e993b2f9ebffdbfa7f10153bcb","engineering\u002Ffeature-deep-dive",0,"https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack","https:\u002F\u002Fgithub.com\u002FNairon-AI","https:\u002F\u002Fwww.naironai.com\u002F","Building the future of Work","2026-09-20 17:40:05",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add Nairon-AI\u002Fagentic-starter-pack --skill feature-deep-dive",{"tool":58,"command":59},"bunx","bunx skills add Nairon-AI\u002Fagentic-starter-pack --skill feature-deep-dive",{"tool":61,"command":62},"pnpm","pnpm dlx skills add Nairon-AI\u002Fagentic-starter-pack --skill feature-deep-dive","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fengineering\u002Ffeature-deep-dive\u002FSKILL.md",true,[],[67,103,125,146,166,187],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":83,"publishedAt":38},"01M6RBCG630Y8X99XWR9Q4GYNY","writing-shape","Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fwriting-shape\u002FSKILL.md",[73,78],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[84,85,86,87,88,89,90,91,92,31,93,94,95,96,97,98,99,100,101,102],"writing","writing shape","shape","notes","help","file","markdown","format","session","take","draft","article","material","it","about","quotes","at","candidate","when",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":111,"publishedAt":38},"01M6RBCCCB1KMF01P5SYGFWBSW","writing-fragments","Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions \"fragments\", \"ideate\", or \"raw material\" for writing.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fwriting-fragments\u002FSKILL.md",[109,110],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},[84,112,113,114,115,116,92,31,117,118,119,95,120,96,121,122,123,124,102],"writing fragments","grilling","ideate","develop","user","document","structure","ideas","as","sharp","claims","for","single",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":133,"publishedAt":38},"01M6RBC8V7NHHKMTAZB4BPXVYQ","writing-beats","Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fwriting-beats\u002FSKILL.md",[131,132],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},[84,134,135,136,31,137,138,86,139,140,141,95,142,120,143,96,144,145,123,102],"writing beats","choose","write","assemble","only","journey","next","options","end","style","narrative","argument",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":154,"publishedAt":38},"01M6RBC58SG5Y5SC4ZV4ZNEFHC","stop-slop","Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fstop-slop\u002FSKILL.md",[152,153],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},[155,156,157,84,158,159,160,161,162,31,163,164,165,123,102],"stop","stop slop","slop","content","https","text","editing","remove","prose","patterns","drafts",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":174,"publishedAt":38},"01M6RBBJTTCJ7KZCP16G9JDFZH","humanizer","Remove signs of AI-generated writing from text. Use when editing or reviewing\ntext to make it sound more natural and human-written. Based on Wikipedia's\ncomprehensive \"Signs of AI writing\" guide. Detects and fixes patterns including:\ninflated symbolism, promotional language, superficial -ing analyses, vague\nattributions, em dash overuse, rule of three, AI vocabulary words, passive\nvoice, negative parallelisms, and filler phrases.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fhumanizer\u002FSKILL.md",[172,173],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},[168,84,37,175,160,176,136,177,178,162,179,180,164,181,182,183,184,185,186,102],"em dash","read","edit","generated","guide","opencode","three","human","make","wikipedia","vague","dash",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":193,"publishedAt":38},"01M6RBBEQKJ5HRH8AV9J85QB1T","feedback","Prepare, deliver, and debrief timely interpersonal feedback using a question-first coaching flow, observable behavior, owned experience, and concrete impact. Use when drafting feedback, coaching managers, rehearsing a feedback conversation, praising specific behavior, or reviewing whether feedback landed.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Ffeedback\u002FSKILL.md",[],[189,194,195,196,197,198,31,199,200,201,202,203,102,204],"prepare","flow","first","question","behavior","conversation","coaching","debrief","impact","managers","deliver"]