Rag Architect

Looking at this one, you're getting help designing retrieval augmented generation systems from the ground up. It walks you through the architecture decisions that actually matter: how to chunk your documents, which embedding model makes sense for your use case, whether you need hybrid search or can get away with pure vector similarity, and how to structure your retrieval pipeline. Useful when you're past the POC stage and need to build something that won't fall apart when you move from a dozen test documents to production scale. The guidance skews practical rather than theoretical, focusing on tradeoffs you'll actually face when implementing RAG rather than just explaining what it is.

skills.sh installs: 646
GitHub stars: 29.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add alirezarezvani/claude-skills --skill rag-architect --agent claude-code

Installs into .claude/skills of the current project.

Files

RAG Architect

Design, tune, and evaluate production RAG pipelines with three deterministic tools. Run the tools against the actual corpus and requirements — do not pick chunk sizes or databases by intuition.

Hard rules

Never present model names or vendor prices as current facts. Embedding models and vector-DB pricing rot in months. Recommend a tier (see table below), name a current-generation candidate, and tell the user to verify against the provider's live pricing page.
Every design ends with an evaluation run. A RAG design without retrieval_evaluator.py numbers is a hypothesis, not a deliverable.
Chunking is corpus-driven. Run chunking_optimizer.py on the real documents before choosing a strategy.