{"id":"6f6791ee-866c-447a-a48c-8dad65ddaef3","shortId":"mfHecF","kind":"skill","title":"capture-knowledge","tagline":"Capture structured knowledge about a code entry point and save it to the knowledge docs. Use when users ask to document, understand, or map code for a module, file, folder, function, or API.","description":"# Knowledge Capture Assistant\n\nBuild structured understanding of code entry points with an analysis-first workflow.\n\n## Hard Rule\n- Do not create documentation until the entry point is validated and analysis is complete.\n\n## Workflow\n\n1. Gather & Validate\n- Confirm entry point (file, folder, function, API), purpose, and desired depth.\n- Verify it exists; resolve ambiguity or suggest alternatives if not found.\n- Search for existing knowledge before analyzing: `npx ai-devkit@latest memory search --query \"<entry point name or purpose>\"`\n\n2. Collect Source Context\n- Summarize purpose, exports, key patterns.\n- Folders: list structure, highlight key modules.\n- Functions/APIs: capture signature, parameters, return values, error handling.\n\n3. Analyze Dependencies\n- Build dependency view up to depth 3, track visited nodes to avoid loops.\n- Categorize: imports, function calls, services, external packages.\n- Exclude external systems or generated code.\n\n4. Synthesize\n- Overview (purpose, language, high-level behavior).\n- Core logic, execution flow, patterns.\n- Error handling, performance, security considerations.\n- Improvements or risks discovered during analysis.\n\n5. Create Documentation\n- Normalize name to kebab-case (`calculateTotalPrice` → `calculate-total-price`).\n- Create `docs/ai/implementation/knowledge-{name}.md` using the Output Template.\n- Include mermaid diagrams when they clarify flows or relationships.\n\n## Red Flags and Rationalizations\n\n| Rationalization | Why It's Wrong | Do Instead |\n|---|---|---|\n| \"I already understand this code\" | Understanding ≠ documented understanding | Write it down, then verify |\n| \"The code is self-documenting\" | Future readers lack your current context | Capture the why, not just the what |\n| \"Dependencies are obvious\" | Implicit dependencies cause surprises | Map them explicitly to depth 3 |\n\n## Validation\n- Documentation covers all Output Template sections.\n- Summarize key insights, open questions, and related areas for deeper dives.\n- Confirm file path and remind to commit.\n\n## Output Template\n- Overview\n- Implementation Details\n- Dependencies\n- Visual Diagrams (mermaid)\n- Additional Insights\n- Metadata (date, depth, files touched)\n- Next Steps","tags":["capture","knowledge","devkit","codeaholicguy","agent-skills","ai-assisted-development","antigravity","claude-code","codex","cursor","development","engineering"],"capabilities":["skill","source-codeaholicguy","skill-capture-knowledge","topic-agent-skills","topic-ai-assisted-development","topic-antigravity","topic-claude-code","topic-codex","topic-cursor","topic-development","topic-engineering","topic-engineering-enablement","topic-engineering-experience","topic-prd"],"categories":["ai-devkit"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/codeaholicguy/ai-devkit/capture-knowledge","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add codeaholicguy/ai-devkit","source_repo":"https://github.com/codeaholicguy/ai-devkit","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 1174 github stars · SKILL.md body (2,217 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":"2026-05-03T00:52:56.895Z","embedding":null,"createdAt":"2026-04-18T21:55:28.743Z","updatedAt":"2026-05-03T00:52:56.895Z","lastSeenAt":"2026-05-03T00:52:56.895Z","tsv":"'1':70 '2':109 '3':132,141,272 '4':161 '5':186 'addit':307 'ai':103 'ai-devkit':102 'alreadi':229 'altern':91 'ambigu':88 'analysi':50,66,185 'analysis-first':49 'analyz':100,133 'api':36,79 'area':287 'ask':22 'assist':39 'avoid':146 'behavior':169 'build':40,135 'calcul':197 'calculate-total-pric':196 'calculatetotalpric':195 'call':151 'captur':2,4,38,125,253 'capture-knowledg':1 'case':194 'categor':148 'caus':265 'clarifi':213 'code':9,28,44,160,232,242 'collect':110 'commit':297 'complet':68 'confirm':73,291 'consider':179 'context':112,252 'core':170 'cover':275 'creat':57,187,200 'current':251 'date':310 'deeper':289 'depend':134,136,260,264,303 'depth':83,140,271,311 'desir':82 'detail':302 'devkit':104 'diagram':210,305 'discov':183 'dive':290 'doc':18 'docs/ai/implementation/knowledge-':201 'document':24,58,188,234,246,274 'entri':10,45,61,74 'error':130,175 'exclud':155 'execut':172 'exist':86,97 'explicit':269 'export':115 'extern':153,156 'file':32,76,292,312 'first':51 'flag':218 'flow':173,214 'folder':33,77,118 'found':94 'function':34,78,150 'functions/apis':124 'futur':247 'gather':71 'generat':159 'handl':131,176 'hard':53 'high':167 'high-level':166 'highlight':121 'implement':301 'implicit':263 'import':149 'improv':180 'includ':208 'insight':282,308 'instead':227 'kebab':193 'kebab-cas':192 'key':116,122,281 'knowledg':3,6,17,37,98 'lack':249 'languag':165 'latest':105 'level':168 'list':119 'logic':171 'loop':147 'map':27,267 'md':203 'memori':106 'mermaid':209,306 'metadata':309 'modul':31,123 'name':190,202 'next':314 'node':144 'normal':189 'npx':101 'obvious':262 'open':283 'output':206,277,298 'overview':163,300 'packag':154 'paramet':127 'path':293 'pattern':117,174 'perform':177 'point':11,46,62,75 'price':199 'purpos':80,114,164 'queri':108 'question':284 'ration':220,221 'reader':248 'red':217 'relat':286 'relationship':216 'remind':295 'resolv':87 'return':128 'risk':182 'rule':54 'save':13 'search':95,107 'section':279 'secur':178 'self':245 'self-docu':244 'servic':152 'signatur':126 'skill' 'skill-capture-knowledge' 'sourc':111 'source-codeaholicguy' 'step':315 'structur':5,41,120 'suggest':90 'summar':113,280 'surpris':266 'synthes':162 'system':157 'templat':207,278,299 'topic-agent-skills' 'topic-ai-assisted-development' 'topic-antigravity' 'topic-claude-code' 'topic-codex' 'topic-cursor' 'topic-development' 'topic-engineering' 'topic-engineering-enablement' 'topic-engineering-experience' 'topic-prd' 'total':198 'touch':313 'track':142 'understand':25,42,230,233,235 'use':19,204 'user':21 'valid':64,72,273 'valu':129 'verifi':84,240 'view':137 'visit':143 'visual':304 'workflow':52,69 'write':236 'wrong':225","prices":[{"id":"1bb5adfb-6259-432b-94a3-129ca3d697bc","listingId":"6f6791ee-866c-447a-a48c-8dad65ddaef3","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"codeaholicguy","category":"ai-devkit","install_from":"skills.sh"},"createdAt":"2026-04-18T21:55:28.743Z"}],"sources":[{"listingId":"6f6791ee-866c-447a-a48c-8dad65ddaef3","source":"github","sourceId":"codeaholicguy/ai-devkit/capture-knowledge","sourceUrl":"https://github.com/codeaholicguy/ai-devkit/tree/main/skills/capture-knowledge","isPrimary":false,"firstSeenAt":"2026-04-18T21:55:28.743Z","lastSeenAt":"2026-05-03T00:52:56.895Z"}],"details":{"listingId":"6f6791ee-866c-447a-a48c-8dad65ddaef3","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"codeaholicguy","slug":"capture-knowledge","github":{"repo":"codeaholicguy/ai-devkit","stars":1174,"topics":["agent-skills","ai","ai-assisted-development","antigravity","claude-code","codex","cursor","development","engineering","engineering-enablement","engineering-experience","prd"],"license":null,"html_url":"https://github.com/codeaholicguy/ai-devkit","pushed_at":"2026-05-03T00:18:58Z","description":"A universal CLI toolkit for AI agent skills, enabling structured AI-assisted development across tools like Cursor, Claude Code, Codex, and more.","skill_md_sha":"c65bd86e3a8e9bb1dc2ffc9a1ed23c723c19ac27","skill_md_path":"skills/capture-knowledge/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/codeaholicguy/ai-devkit/tree/main/skills/capture-knowledge"},"layout":"multi","source":"github","category":"ai-devkit","frontmatter":{"name":"capture-knowledge","description":"Capture structured knowledge about a code entry point and save it to the knowledge docs. Use when users ask to document, understand, or map code for a module, file, folder, function, or API."},"skills_sh_url":"https://skills.sh/codeaholicguy/ai-devkit/capture-knowledge"},"updatedAt":"2026-05-03T00:52:56.895Z"}}