Rag Engineer

If you're building RAG systems, this skill knows the difference between retrieval that works and retrieval that just looks like it works. It covers the full pipeline: semantic chunking strategies that respect document structure, hybrid search combining BM25 with vectors, reranking with cross-encoders, and metadata filtering before you even hit the vector database. The sharp edges section is worth the price alone, calling out traps like cramming maximum context into prompts and not measuring retrieval quality separately from generation. It's opinionated about things that matter, like hybrid search beating pure semantic in most cases and retrieval quality determining generation quality. Good for anyone past the tutorial phase who's hitting real problems with chunk boundaries and hallucinations.

Install to Claude Code

npx -y skills add sickn33/antigravity-awesome-skills --skill rag-engineer --agent claude-code