Rag Architect

This is a comprehensive RAG implementation guide that goes well beyond basic vector search setup. It walks you through the full production stack: chunking strategies with overlap and semantic boundaries, embedding selection and indexing with deduplication, hybrid search combining dense retrieval with BM25, reranking with Cohere, and proper evaluation metrics like precision@k and recall@k. The checkpoints after each step are genuinely useful, and the "must not" constraints call out common mistakes like blindly using 512 token chunks. If you're building a RAG system that needs to actually work at scale rather than just demo well, this covers the architectural decisions and implementation patterns that matter.

skills.sh installs: 4.9K
GitHub stars: 12.3K
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

RAG Architect

Core Workflow

Requirements Analysis — Identify retrieval needs, latency constraints, accuracy requirements, and scale
Vector Store Design — Select database, schema design, indexing strategy, sharding approach
Chunking Strategy — Document splitting, overlap, semantic boundaries, metadata enrichment
Retrieval Pipeline — Embedding selection, query transformation, hybrid search, reranking
Evaluation & Iteration — Metrics tracking, retrieval debugging, continuous optimization

For each step, validate before moving on (see checkpoints below).