Rag Implementation

This one teaches Claude RAG patterns beyond the basic "chunk and embed" approach that tends to fail at scale. You get semantic chunking strategies, hybrid search that combines vector and keyword retrieval, and contextual reranking to surface what's actually relevant. The sharp edges table is practical: it calls out that poor chunking ruins everything, warns about mixing embedding models, and acknowledges the latency hit RAG introduces. Use this when you're building retrieval systems and want to avoid the common mistakes that only show up once you're dealing with real document volumes. The emphasis on when RAG is unnecessary overhead is refreshingly honest.

Install to Claude Code

npx -y skills add davila7/claude-code-templates --skill rag-implementation --agent claude-code