[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M756NM7K2DP7KD475N4S3ZXD":3,"skill-same:01M756NM7K2DP7KD475N4S3ZXD":57},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M756NM7K2DP7KD475N4S3ZXD","understand-knowledge",null,"Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.","Ikeu-1030\u002FiRun","Ikeu-1030","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F229719040?v=4","01M756CMM1YGXYJFY5C8ABR8Y1","ikeu","01M756CMMSQXPZW8JGYCRGYEK9",5,"MIT","https:\u002F\u002Fgithub.com\u002FIkeu-1030\u002FiRun\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Funderstand-anything\u002Funderstand-anything-plugin\u002Fskills\u002Funderstand-knowledge\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: understand-knowledge\ndescription: Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.\nargument-hint: [wiki-directory]\n---\n\n# \u002Funderstand-knowledge\n\nAnalyzes a Karpathy-pattern LLM wiki — a three-layer knowledge base with raw sources, wiki markdown, and a schema file — and produces an interactive knowledge graph dashboard.\n\n## What It Detects\n\nThe **Karpathy LLM wiki pattern** (see https:\u002F\u002Fgist.github.com\u002Fkarpathy\u002F442a6bf555914893e9891c11519de94f):\n- **Raw sources** — immutable source documents (articles, papers, data files)\n- **Wiki** — LLM-generated markdown files with wikilinks (`[[target]]` syntax)\n- **Schema** — CLAUDE.md, AGENTS.md, or similar configuration file\n- **index.md** — content catalog organized by categories\n- **log.md** — chronological operation log\n\nDetection signals: has `index.md` + multiple `.md` files with wikilinks. May have `raw\u002F` directory and schema file.\n\n## Instructions\n\n### Phase 1: DETECT\n\n1. Determine the target directory:\n   - If the user provided a path argument, use that\n   - Otherwise, use the current working directory\n\n2. Run the format detection script bundled with this skill:\n   ```\n   python3 \u003CSKILL_DIR>\u002Fparse-knowledge-base.py \u003CTARGET_DIR>\n   ```\n   - If the script exits with an error, tell the user this doesn't appear to be a Karpathy-pattern wiki and explain what was expected\n   - If successful, proceed. The script writes `scan-manifest.json` to `\u003CTARGET_DIR>\u002F.understand-anything\u002Fintermediate\u002F`\n\n3. Read the scan-manifest.json and announce the results:\n   - \"Detected Karpathy wiki: N articles, N sources, N topics, N wikilinks (N unresolved)\"\n   - List the categories found from index.md\n\n### Phase 2: SCAN (already done)\n\nThe parse script in Phase 1 already performed the deterministic scan. The scan-manifest.json contains:\n- Article nodes (one per wiki .md file) with extracted wikilinks, headings, frontmatter\n- Source nodes (one per raw\u002F file)\n- Topic nodes (from index.md section headings)\n- `related` edges (from wikilinks)\n- `categorized_under` edges (from index.md sections)\n\nNo additional scanning is needed. Proceed to Phase 3.\n\n### Phase 3: ANALYZE\n\nDispatch `article-analyzer` subagents to extract implicit knowledge:\n\n1. Read the scan-manifest.json to get the article list\n\n2. Prepare batches of 10-15 articles each, grouped by category when possible (articles in the same category are more likely to have implicit cross-references)\n\n3. For each batch, dispatch an `article-analyzer` subagent with:\n   - The batch of articles (id, name, summary, wikilinks, category, content from knowledgeMeta)\n   - The full list of existing node IDs (so the agent can reference them)\n   - The batch number for output file naming\n   - The intermediate directory path: `$INTERMEDIATE_DIR = \u003CTARGET_DIR>\u002F.understand-anything\u002Fintermediate`\n   \n   The agent will write `analysis-batch-{N}.json` to the intermediate directory.\n\n4. Run up to 3 batches concurrently. Wait for all batches to complete.\n\n5. If any batch fails, log a warning but continue — the scan-manifest provides a solid base graph even without LLM analysis.\n\n### Phase 4: MERGE\n\n1. Run the merge script bundled with this skill:\n   ```\n   python3 \u003CSKILL_DIR>\u002Fmerge-knowledge-graph.py \u003CTARGET_DIR>\n   ```\n\n2. The script:\n   - Combines scan-manifest.json + all analysis-batch-*.json files\n   - Deduplicates entities (case-insensitive name matching)\n   - Normalizes node\u002Fedge types via alias maps\n   - Builds layers from index.md categories\n   - Builds a tour from index.md section ordering\n   - Writes `assembled-graph.json` to the intermediate directory\n\n3. Read the merge report from stderr and announce:\n   - Total nodes, edges, layers, tour steps\n   - How many entities\u002Fclaims the LLM analysis added\n\n### Phase 5: SAVE\n\n1. Read the assembled-graph.json\n\n2. Run basic validation:\n   - Every edge source\u002Ftarget must reference an existing node\n   - Every node must have: id, type, name, summary, tags, complexity\n   - Remove any edges with dangling references\n\n3. Copy the validated graph to `\u003CTARGET_DIR>\u002F.understand-anything\u002Fknowledge-graph.json`\n\n4. Write metadata to `\u003CTARGET_DIR>\u002F.understand-anything\u002Fmeta.json`:\n   ```json\n   {\n     \"lastAnalyzedAt\": \"\u003CISO timestamp>\",\n     \"gitCommitHash\": \"\u003Cfrom git rev-parse HEAD or empty>\",\n     \"version\": \"1.0.0\",\n     \"analyzedFiles\": \u003Cnumber of wiki articles>\n   }\n   ```\n\n5. Clean up intermediate files:\n   ```\n   rm -rf \u003CTARGET_DIR>\u002F.understand-anything\u002Fintermediate\n   ```\n\n6. Report summary to the user:\n   - \"Knowledge graph saved: N articles, N entities, N topics, N claims, N sources\"\n   - \"N edges (N wikilink, N categorized, N implicit)\"\n   - \"N layers, N tour steps\"\n\n7. Auto-trigger the dashboard:\n   ```\n   \u002Funderstand-dashboard \u003CTARGET_DIR>\n   ```\n\n## Notes\n\n- The parse script handles ALL deterministic extraction (wikilinks, headings, frontmatter, categories from index.md). The LLM agents only add implicit knowledge that requires inference.\n- Categories and taxonomy come from index.md section headings, NOT from filename prefixes. The Karpathy spec is intentionally abstract about naming conventions.\n- The graph uses `kind: \"knowledge\"` to signal the dashboard to use force-directed layout instead of hierarchical dagre.\n- Source nodes from raw\u002F are lightweight (filename + size only) — we don't parse PDFs or binary files.\n","# \u002Funderstand-knowledge\n\nAnalyzes a Karpathy-pattern LLM wiki — a three-layer knowledge base with raw sources, wiki markdown, and a schema file — and produces an interactive knowledge graph dashboard.\n\n## What It Detects\n\nThe **Karpathy LLM wiki pattern** (see https:\u002F\u002Fgist.github.com\u002Fkarpathy\u002F442a6bf555914893e9891c11519de94f):\n- **Raw sources** — immutable source documents (articles, papers, data files)\n- **Wiki** — LLM-generated markdown files with wikilinks (`[[target]]` syntax)\n- **Schema** — CLAUDE.md, AGENTS.md, or similar configuration file\n- **index.md** — content catalog organized by categories\n- **log.md** — chronological operation log\n\nDetection signals: has `index.md` + multiple `.md` files with wikilinks. May have `raw\u002F` directory and schema file.\n\n## Instructions\n\n### Phase 1: DETECT\n\n1. Determine the target directory:\n   - If the user provided a path argument, use that\n   - Otherwise, use the current working directory\n\n2. Run the format detection script bundled with this skill:\n   ```\n   python3 \u003CSKILL_DIR>\u002Fparse-knowledge-base.py \u003CTARGET_DIR>\n   ```\n   - If the script exits with an error, tell the user this doesn't appear to be a Karpathy-pattern wiki and explain what was expected\n   - If successful, proceed. The script writes `scan-manifest.json` to `\u003CTARGET_DIR>\u002F.understand-anything\u002Fintermediate\u002F`\n\n3. Read the scan-manifest.json and announce the results:\n   - \"Detected Karpathy wiki: N articles, N sources, N topics, N wikilinks (N unresolved)\"\n   - List the categories found from index.md\n\n### Phase 2: SCAN (already done)\n\nThe parse script in Phase 1 already performed the deterministic scan. The scan-manifest.json contains:\n- Article nodes (one per wiki .md file) with extracted wikilinks, headings, frontmatter\n- Source nodes (one per raw\u002F file)\n- Topic nodes (from index.md section headings)\n- `related` edges (from wikilinks)\n- `categorized_under` edges (from index.md sections)\n\nNo additional scanning is needed. Proceed to Phase 3.\n\n### Phase 3: ANALYZE\n\nDispatch `article-analyzer` subagents to extract implicit knowledge:\n\n1. Read the scan-manifest.json to get the article list\n\n2. Prepare batches of 10-15 articles each, grouped by category when possible (articles in the same category are more likely to have implicit cross-references)\n\n3. For each batch, dispatch an `article-analyzer` subagent with:\n   - The batch of articles (id, name, summary, wikilinks, category, content from knowledgeMeta)\n   - The full list of existing node IDs (so the agent can reference them)\n   - The batch number for output file naming\n   - The intermediate directory path: `$INTERMEDIATE_DIR = \u003CTARGET_DIR>\u002F.understand-anything\u002Fintermediate`\n   \n   The agent will write `analysis-batch-{N}.json` to the intermediate directory.\n\n4. Run up to 3 batches concurrently. Wait for all batches to complete.\n\n5. If any batch fails, log a warning but continue — the scan-manifest provides a solid base graph even without LLM analysis.\n\n### Phase 4: MERGE\n\n1. Run the merge script bundled with this skill:\n   ```\n   python3 \u003CSKILL_DIR>\u002Fmerge-knowledge-graph.py \u003CTARGET_DIR>\n   ```\n\n2. The script:\n   - Combines scan-manifest.json + all analysis-batch-*.json files\n   - Deduplicates entities (case-insensitive name matching)\n   - Normalizes node\u002Fedge types via alias maps\n   - Builds layers from index.md categories\n   - Builds a tour from index.md section ordering\n   - Writes `assembled-graph.json` to the intermediate directory\n\n3. Read the merge report from stderr and announce:\n   - Total nodes, edges, layers, tour steps\n   - How many entities\u002Fclaims the LLM analysis added\n\n### Phase 5: SAVE\n\n1. Read the assembled-graph.json\n\n2. Run basic validation:\n   - Every edge source\u002Ftarget must reference an existing node\n   - Every node must have: id, type, name, summary, tags, complexity\n   - Remove any edges with dangling references\n\n3. Copy the validated graph to `\u003CTARGET_DIR>\u002F.understand-anything\u002Fknowledge-graph.json`\n\n4. Write metadata to `\u003CTARGET_DIR>\u002F.understand-anything\u002Fmeta.json`:\n   ```json\n   {\n     \"lastAnalyzedAt\": \"\u003CISO timestamp>\",\n     \"gitCommitHash\": \"\u003Cfrom git rev-parse HEAD or empty>\",\n     \"version\": \"1.0.0\",\n     \"analyzedFiles\": \u003Cnumber of wiki articles>\n   }\n   ```\n\n5. Clean up intermediate files:\n   ```\n   rm -rf \u003CTARGET_DIR>\u002F.understand-anything\u002Fintermediate\n   ```\n\n6. Report summary to the user:\n   - \"Knowledge graph saved: N articles, N entities, N topics, N claims, N sources\"\n   - \"N edges (N wikilink, N categorized, N implicit)\"\n   - \"N layers, N tour steps\"\n\n7. Auto-trigger the dashboard:\n   ```\n   \u002Funderstand-dashboard \u003CTARGET_DIR>\n   ```\n\n## Notes\n\n- The parse script handles ALL deterministic extraction (wikilinks, headings, frontmatter, categories from index.md). The LLM agents only add implicit knowledge that requires inference.\n- Categories and taxonomy come from index.md section headings, NOT from filename prefixes. The Karpathy spec is intentionally abstract about naming conventions.\n- The graph uses `kind: \"knowledge\"` to signal the dashboard to use force-directed layout instead of hierarchical dagre.\n- Source nodes from raw\u002F are lightweight (filename + size only) — we don't parse PDFs or binary files.\n",{"name":5,"description":7,"argument-hint":24},[25],"wiki-directory","main","14d19341a5ae6e5a3c751328fcc273395da5bd21",".claude\u002Fskills\u002Funderstand-anything\u002Funderstand-anything-plugin\u002Fskills\u002Funderstand-knowledge","https:\u002F\u002Fgithub.com\u002FIkeu-1030\u002FiRun","https:\u002F\u002Fgithub.com\u002FIkeu-1030","Action shatters illusion\u002F","2026-07-02 15:19:58",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Ikeu-1030\u002FiRun --skill understand-knowledge",{"tool":39,"command":40},"bunx","bunx skills add Ikeu-1030\u002FiRun --skill understand-knowledge",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Ikeu-1030\u002FiRun --skill understand-knowledge","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FIkeu-1030\u002FiRun\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Funderstand-anything\u002Funderstand-anything-plugin\u002Fskills\u002Funderstand-knowledge\u002FSKILL.md",true,[47,53],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"merge-knowledge-graph.py","SCRIPT","脚本",16157,"https:\u002F\u002Fgithub.com\u002FIkeu-1030\u002FiRun\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Funderstand-anything\u002Funderstand-anything-plugin\u002Fskills\u002Funderstand-knowledge\u002Fmerge-knowledge-graph.py",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"parse-knowledge-base.py",18429,"https:\u002F\u002Fgithub.com\u002FIkeu-1030\u002FiRun\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Funderstand-anything\u002Funderstand-anything-plugin\u002Fskills\u002Funderstand-knowledge\u002Fparse-knowledge-base.py",[58,65,72,79,86,93],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M756NR65N494G30JZP84MS7R","understand","Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships","https:\u002F\u002Fgithub.com\u002FIkeu-1030\u002FiRun\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Funderstand-anything\u002Funderstand-anything-plugin\u002Fskills\u002Funderstand\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M756NPH7BMV8655NPXER0ZAS","understand-onboard","Use when you need to generate an onboarding guide for new team members joining a project","https:\u002F\u002Fgithub.com\u002FIkeu-1030\u002FiRun\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Funderstand-anything\u002Funderstand-anything-plugin\u002Fskills\u002Funderstand-onboard\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M756NJPJADZ13YRP1D9PEVEF","understand-explain","Use when you need a deep-dive explanation of a specific file, function, or module in the codebase","https:\u002F\u002Fgithub.com\u002FIkeu-1030\u002FiRun\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Funderstand-anything\u002Funderstand-anything-plugin\u002Fskills\u002Funderstand-explain\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M756NF79MR3DD69W7XJAT2PB","understand-domain","Extract business domain knowledge from a codebase and generate an interactive domain flow graph. Works standalone (lightweight scan) or derives from an existing \u002Funderstand knowledge graph.","https:\u002F\u002Fgithub.com\u002FIkeu-1030\u002FiRun\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Funderstand-anything\u002Funderstand-anything-plugin\u002Fskills\u002Funderstand-domain\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M756NCF0HHCSJTMDV85G7KR2","understand-diff","Use when you need to analyze git diffs or pull requests to understand what changed, affected components, and risks","https:\u002F\u002Fgithub.com\u002FIkeu-1030\u002FiRun\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Funderstand-anything\u002Funderstand-anything-plugin\u002Fskills\u002Funderstand-diff\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M756NA0ZYHV493C2DHEGG1TF","understand-dashboard","Launch the interactive web dashboard to visualize a codebase's knowledge graph","https:\u002F\u002Fgithub.com\u002FIkeu-1030\u002FiRun\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Funderstand-anything\u002Funderstand-anything-plugin\u002Fskills\u002Funderstand-dashboard\u002FSKILL.md",[],[]]