{"id":"a59627e4-2d6e-4376-9702-f724d95dddc2","shortId":"kKLhsH","kind":"skill","title":"rag-implementation","tagline":"RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimization.","description":"# RAG Implementation Workflow\n\n## Overview\n\nSpecialized workflow for implementing RAG (Retrieval-Augmented Generation) systems including embedding model selection, vector database setup, chunking strategies, retrieval optimization, and evaluation.\n\n## When to Use This Workflow\n\nUse this workflow when:\n- Building RAG-powered applications\n- Implementing semantic search\n- Creating knowledge-grounded AI\n- Setting up document Q&A systems\n- Optimizing retrieval quality\n\n## Workflow Phases\n\n### Phase 1: Requirements Analysis\n\n#### Skills to Invoke\n- `ai-product` - AI product design\n- `rag-engineer` - RAG engineering\n\n#### Actions\n1. Define use case\n2. Identify data sources\n3. Set accuracy requirements\n4. Determine latency targets\n5. Plan evaluation metrics\n\n#### Copy-Paste Prompts\n```\nUse @ai-product to define RAG application requirements\n```\n\n### Phase 2: Embedding Selection\n\n#### Skills to Invoke\n- `embedding-strategies` - Embedding selection\n- `rag-engineer` - RAG patterns\n\n#### Actions\n1. Evaluate embedding models\n2. Test domain relevance\n3. Measure embedding quality\n4. Consider cost/latency\n5. Select model\n\n#### Copy-Paste Prompts\n```\nUse @embedding-strategies to select optimal embedding model\n```\n\n### Phase 3: Vector Database Setup\n\n#### Skills to Invoke\n- `vector-database-engineer` - Vector DB\n- `similarity-search-patterns` - Similarity search\n\n#### Actions\n1. Choose vector database\n2. Design schema\n3. Configure indexes\n4. Set up connection\n5. Test queries\n\n#### Copy-Paste Prompts\n```\nUse @vector-database-engineer to set up vector database\n```\n\n### Phase 4: Chunking Strategy\n\n#### Skills to Invoke\n- `rag-engineer` - Chunking strategies\n- `rag-implementation` - RAG implementation\n\n#### Actions\n1. Choose chunk size\n2. Implement chunking\n3. Add overlap handling\n4. Create metadata\n5. Test retrieval quality\n\n#### Copy-Paste Prompts\n```\nUse @rag-engineer to implement chunking strategy\n```\n\n### Phase 5: Retrieval Implementation\n\n#### Skills to Invoke\n- `similarity-search-patterns` - Similarity search\n- `hybrid-search-implementation` - Hybrid search\n\n#### Actions\n1. Implement vector search\n2. Add keyword search\n3. Configure hybrid search\n4. Set up reranking\n5. Optimize latency\n\n#### Copy-Paste Prompts\n```\nUse @similarity-search-patterns to implement retrieval\n```\n\n```\nUse @hybrid-search-implementation to add hybrid search\n```\n\n### Phase 6: LLM Integration\n\n#### Skills to Invoke\n- `llm-application-dev-ai-assistant` - LLM integration\n- `llm-application-dev-prompt-optimize` - Prompt optimization\n\n#### Actions\n1. Select LLM provider\n2. Design prompt template\n3. Implement context injection\n4. Add citation handling\n5. Test generation quality\n\n#### Copy-Paste Prompts\n```\nUse @llm-application-dev-ai-assistant to integrate LLM\n```\n\n### Phase 7: Caching\n\n#### Skills to Invoke\n- `prompt-caching` - Prompt caching\n- `rag-engineer` - RAG optimization\n\n#### Actions\n1. Implement response caching\n2. Set up embedding cache\n3. Configure TTL\n4. Add cache invalidation\n5. Monitor hit rates\n\n#### Copy-Paste Prompts\n```\nUse @prompt-caching to implement RAG caching\n```\n\n### Phase 8: Evaluation\n\n#### Skills to Invoke\n- `llm-evaluation` - LLM evaluation\n- `evaluation` - AI evaluation\n\n#### Actions\n1. Define evaluation metrics\n2. Create test dataset\n3. Measure retrieval accuracy\n4. Evaluate generation quality\n5. Iterate on improvements\n\n#### Copy-Paste Prompts\n```\nUse @llm-evaluation to evaluate RAG system\n```\n\n## RAG Architecture\n\n```\nUser Query -> Embedding -> Vector Search -> Retrieved Docs -> LLM -> Response\n                |              |              |              |\n            Model         Vector DB     Chunk Store    Prompt + Context\n```\n\n## Quality Gates\n\n- [ ] Embedding model selected\n- [ ] Vector DB configured\n- [ ] Chunking implemented\n- [ ] Retrieval working\n- [ ] LLM integrated\n- [ ] Evaluation passing\n\n## Related Workflow Bundles\n\n- `ai-ml` - AI/ML development\n- `ai-agent-development` - AI agents\n- `database` - Vector databases\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.","tags":["rag","implementation","antigravity","awesome","skills","sickn33","agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows"],"capabilities":["skill","source-sickn33","skill-rag-implementation","topic-agent-skills","topic-agentic-skills","topic-ai-agent-skills","topic-ai-agents","topic-ai-coding","topic-ai-workflows","topic-antigravity","topic-antigravity-skills","topic-claude-code","topic-claude-code-skills","topic-codex-cli","topic-codex-skills"],"categories":["antigravity-awesome-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/sickn33/antigravity-awesome-skills/rag-implementation","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add sickn33/antigravity-awesome-skills","source_repo":"https://github.com/sickn33/antigravity-awesome-skills","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 34616 github stars · SKILL.md body (4,302 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":"2026-04-23T00:51:27.738Z","embedding":null,"createdAt":"2026-04-18T21:43:14.244Z","updatedAt":"2026-04-23T00:51:27.738Z","lastSeenAt":"2026-04-23T00:51:27.738Z","tsv":"'1':83,101,152,204,253,303,367,418,465 '2':105,135,156,208,257,307,371,422,469 '3':109,160,184,211,260,311,375,427,473 '4':113,164,214,236,264,315,379,430,477 '5':117,167,218,267,284,319,383,434,481 '6':344 '7':402 '8':451 'accuraci':111,476 'action':100,151,203,252,302,366,417,464 'add':261,308,340,380,431 'agent':541,544 'ai':70,90,92,127,354,396,462,535,540,543 'ai-agent-develop':539 'ai-ml':534 'ai-product':89,126 'ai/ml':537 'analysi':85 'applic':62,132,352,360,394 'architectur':498 'ask':581 'assist':355,397 'augment':7,33 'boundari':589 'build':58 'bundl':533 'cach':403,409,411,421,426,432,445,449 'case':104 'choos':205,254 'chunk':17,43,237,245,255,259,281,511,523 'citat':381 'clarif':583 'clear':556 'configur':212,312,428,522 'connect':217 'consid':165 'context':377,514 'copi':122,171,222,272,323,388,439,486 'copy-past':121,170,221,271,322,387,438,485 'cost/latency':166 'cover':11 'creat':66,265,470 'criteria':592 'data':107 'databas':15,41,186,193,207,228,234,545,547 'dataset':472 'db':196,510,521 'defin':102,130,466 'describ':560 'design':94,209,372 'determin':114 'dev':353,361,395 'develop':538,542 'doc':505 'document':73 'domain':158 'embed':12,37,136,142,144,154,162,176,181,425,501,517 'embedding-strategi':141,175 'engin':97,99,148,194,229,244,278,414 'environ':572 'environment-specif':571 'evalu':48,119,153,452,458,460,461,463,467,478,492,494,529 'expert':577 'gate':516 'generat':8,34,385,479 'ground':69 'handl':263,382 'hit':436 'hybrid':297,300,313,336,341 'hybrid-search-implement':296,335 'identifi':106 'implement':3,9,23,29,63,249,251,258,280,286,299,304,332,338,376,419,447,524 'improv':484 'includ':36 'index':213 'inject':378 'input':586 'integr':346,357,399,528 'invalid':433 'invok':88,140,190,241,289,349,406,455 'iter':482 'keyword':309 'knowledg':68 'knowledge-ground':67 'latenc':115,321 'limit':548 'llm':345,351,356,359,369,393,400,457,459,491,506,527 'llm-application-dev-ai-assist':350,392 'llm-application-dev-prompt-optim':358 'llm-evalu':456,490 'match':557 'measur':161,474 'metadata':266 'metric':120,468 'miss':594 'ml':536 'model':38,155,169,182,508,518 'monitor':435 'optim':21,46,77,180,320,363,365,416 'output':566 'overlap':262 'overview':25 'pass':530 'past':123,172,223,273,324,389,440,487 'pattern':150,200,293,330 'permiss':587 'phase':81,82,134,183,235,283,343,401,450 'plan':118 'power':61 'product':91,93,128 'prompt':124,173,224,274,325,362,364,373,390,408,410,441,444,488,513 'prompt-cach':407,443 'provid':370 'q':74 'qualiti':79,163,270,386,480,515 'queri':220,500 'rag':2,4,22,30,60,96,98,131,147,149,243,248,250,277,413,415,448,495,497 'rag-engin':95,146,242,276,412 'rag-implement':1,247 'rag-pow':59 'rate':437 'relat':531 'relev':159 'requir':84,112,133,585 'rerank':318 'respons':420,507 'retriev':6,20,32,45,78,269,285,333,475,504,525 'retrieval-aug':5,31 'review':578 'safeti':588 'schema':210 'scope':559 'search':65,199,202,292,295,298,301,306,310,314,329,337,342,503 'select':13,39,137,145,168,179,368,519 'semant':64 'set':71,110,215,231,316,423 'setup':16,42,187 'similar':198,201,291,294,328 'similarity-search-pattern':197,290,327 'size':256 'skill':86,138,188,239,287,347,404,453,551 'skill-rag-implementation' 'sourc':108 'source-sickn33' 'special':26 'specif':573 'stop':579 'store':512 'strategi':18,44,143,177,238,246,282 'substitut':569 'success':591 'system':35,76,496 'target':116 'task':555 'templat':374 'test':157,219,268,384,471,575 'topic-agent-skills' 'topic-agentic-skills' 'topic-ai-agent-skills' 'topic-ai-agents' 'topic-ai-coding' 'topic-ai-workflows' 'topic-antigravity' 'topic-antigravity-skills' 'topic-claude-code' 'topic-claude-code-skills' 'topic-codex-cli' 'topic-codex-skills' 'treat':564 'ttl':429 'use':51,54,103,125,174,225,275,326,334,391,442,489,549 'user':499 'valid':574 'vector':14,40,185,192,195,206,227,233,305,502,509,520,546 'vector-database-engin':191,226 'work':526 'workflow':10,24,27,53,56,80,532","prices":[{"id":"a7b12173-780a-49f4-9276-425eb7ca5600","listingId":"a59627e4-2d6e-4376-9702-f724d95dddc2","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"sickn33","category":"antigravity-awesome-skills","install_from":"skills.sh"},"createdAt":"2026-04-18T21:43:14.244Z"}],"sources":[{"listingId":"a59627e4-2d6e-4376-9702-f724d95dddc2","source":"github","sourceId":"sickn33/antigravity-awesome-skills/rag-implementation","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/rag-implementation","isPrimary":false,"firstSeenAt":"2026-04-18T21:43:14.244Z","lastSeenAt":"2026-04-23T00:51:27.738Z"}],"details":{"listingId":"a59627e4-2d6e-4376-9702-f724d95dddc2","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"rag-implementation","github":{"repo":"sickn33/antigravity-awesome-skills","stars":34616,"topics":["agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows","antigravity","antigravity-skills","claude-code","claude-code-skills","codex-cli","codex-skills","cursor","cursor-skills","developer-tools","gemini-cli","gemini-skills","kiro","mcp","skill-library"],"license":"mit","html_url":"https://github.com/sickn33/antigravity-awesome-skills","pushed_at":"2026-04-22T06:40:00Z","description":"Installable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.","skill_md_sha":"28c3afc17db9fcf48f6661945831e173137d5d9e","skill_md_path":"skills/rag-implementation/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/rag-implementation"},"layout":"multi","source":"github","category":"antigravity-awesome-skills","frontmatter":{"name":"rag-implementation","description":"RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimization."},"skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/rag-implementation"},"updatedAt":"2026-04-23T00:51:27.738Z"}}