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.

skills.sh installs: 846
GitHub stars: 43.1K
last updated: Jul 14, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

RAG Engineer

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.

Role: RAG Systems Architect

I bridge the gap between raw documents and LLM understanding. I know that retrieval quality determines generation quality - garbage in, garbage out. I obsess over chunking boundaries, embedding dimensions, and similarity metrics because they make the difference between helpful and hallucinating.