[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72D5Z9761NMP03QBCFPHP9V":3,"skill-same:01M72D5Z9761NMP03QBCFPHP9V":50},{"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":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":13,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M72D5Z9761NMP03QBCFPHP9V","rag-implementation",null,"Retrieval-Augmented Generation patterns including chunking, embeddings, vector stores, and retrieval optimization Use when: rag, retrieval augmented, vector search, embeddings, semantic search.","Sansar35\u002Fclaude-agent","Sansar35","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F145020281?v=4","01M724CQ2SCC86MGNSD87D0D4K","01M724CQ3965G9WJ3QXE3AJ5YY",1,"MIT","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Frag-implementation\u002FSKILL.md",[],[],"2026-11-10 18:39:20",false,"---\nname: rag-implementation\ndescription: \"Retrieval-Augmented Generation patterns including chunking, embeddings, vector stores, and retrieval optimization Use when: rag, retrieval augmented, vector search, embeddings, semantic search.\"\nsource: vibeship-spawner-skills (Apache 2.0)\n---\n\n# RAG Implementation\n\nYou're a RAG specialist who has built systems serving millions of queries over\nterabytes of documents. You've seen the naive \"chunk and embed\" approach fail,\nand developed sophisticated chunking, retrieval, and reranking strategies.\n\nYou understand that RAG is not just vector search—it's about getting the right\ninformation to the LLM at the right time. You know when RAG helps and when\nit's unnecessary overhead.\n\nYour core principles:\n1. Chunking is critical—bad chunks mean bad retrieval\n2. Hybri\n\n## Capabilities\n\n- document-chunking\n- embedding-models\n- vector-stores\n- retrieval-strategies\n- hybrid-search\n- reranking\n\n## Patterns\n\n### Semantic Chunking\n\nChunk by meaning, not arbitrary size\n\n### Hybrid Search\n\nCombine dense (vector) and sparse (keyword) search\n\n### Contextual Reranking\n\nRerank retrieved docs with LLM for relevance\n\n## Anti-Patterns\n\n### ❌ Fixed-Size Chunking\n\n### ❌ No Overlap\n\n### ❌ Single Retrieval Strategy\n\n## ⚠️ Sharp Edges\n\n| Issue | Severity | Solution |\n|-------|----------|----------|\n| Poor chunking ruins retrieval quality | critical | \u002F\u002F Use recursive character text splitter with overlap |\n| Query and document embeddings from different models | critical | \u002F\u002F Ensure consistent embedding model usage |\n| RAG adds significant latency to responses | high | \u002F\u002F Optimize RAG latency |\n| Documents updated but embeddings not refreshed | medium | \u002F\u002F Maintain sync between documents and embeddings |\n\n## Related Skills\n\nWorks well with: `context-window-management`, `conversation-memory`, `prompt-caching`, `data-pipeline`\n","# RAG Implementation\n\nYou're a RAG specialist who has built systems serving millions of queries over\nterabytes of documents. You've seen the naive \"chunk and embed\" approach fail,\nand developed sophisticated chunking, retrieval, and reranking strategies.\n\nYou understand that RAG is not just vector search—it's about getting the right\ninformation to the LLM at the right time. You know when RAG helps and when\nit's unnecessary overhead.\n\nYour core principles:\n1. Chunking is critical—bad chunks mean bad retrieval\n2. Hybri\n\n## Capabilities\n\n- document-chunking\n- embedding-models\n- vector-stores\n- retrieval-strategies\n- hybrid-search\n- reranking\n\n## Patterns\n\n### Semantic Chunking\n\nChunk by meaning, not arbitrary size\n\n### Hybrid Search\n\nCombine dense (vector) and sparse (keyword) search\n\n### Contextual Reranking\n\nRerank retrieved docs with LLM for relevance\n\n## Anti-Patterns\n\n### ❌ Fixed-Size Chunking\n\n### ❌ No Overlap\n\n### ❌ Single Retrieval Strategy\n\n## ⚠️ Sharp Edges\n\n| Issue | Severity | Solution |\n|-------|----------|----------|\n| Poor chunking ruins retrieval quality | critical | \u002F\u002F Use recursive character text splitter with overlap |\n| Query and document embeddings from different models | critical | \u002F\u002F Ensure consistent embedding model usage |\n| RAG adds significant latency to responses | high | \u002F\u002F Optimize RAG latency |\n| Documents updated but embeddings not refreshed | medium | \u002F\u002F Maintain sync between documents and embeddings |\n\n## Related Skills\n\nWorks well with: `context-window-management`, `conversation-memory`, `prompt-caching`, `data-pipeline`\n",{"name":5,"source":23,"description":7},"vibeship-spawner-skills (Apache 2.0)","main","d046d088ce5a79a083f0abc0fe1b7ded73bc5b1f","claude-config\u002Fskills\u002Frag-implementation","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent","https:\u002F\u002Fgithub.com\u002FSansar35","2026-05-10 16:04:53",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add Sansar35\u002Fclaude-agent --skill rag-implementation",{"tool":36,"command":37},"bunx","bunx skills add Sansar35\u002Fclaude-agent --skill rag-implementation",{"tool":39,"command":40},"pnpm","pnpm dlx skills add Sansar35\u002Fclaude-agent --skill rag-implementation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Frag-implementation\u002FSKILL.md",true,[44],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},".skill-source.json","REFERENCE","参考文档",430,"https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Frag-implementation\u002F.skill-source.json",[51,58,65,72,79,87],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M72DVAN1JYEA302MT0C5MGD6","zustand-store-ts","Create Zustand stores following established patterns with proper TypeScript types and middleware.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzustand-store-ts\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M72DV8J5NBRRM4RPDFRV95N7","zod-validation-expert","Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzod-validation-expert\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M72DV5EMHW0BHP9BZ167MDCB","zinc-database","Access ZINC (230M+ purchasable compounds). Search by ZINC ID\u002FSMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzinc-database\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M72DV216QY0E693ZPEVQ0DBS","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":83,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M72DTXQREMCRKA8NHCVKHN4W","zapier-workflows","Manage and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to \"run\" any process. Also handles Perplexity-based research and Google Sheets data tracking.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-workflows\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-workflows\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":18},"01M72DTT17TBSJ0Y8J2XZ4C9TZ","zapier-make-patterns","No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points.  This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-make-patterns\u002FSKILL.md",[],[]]