Home/Skills/RAG
Category

RAG skills for Claude Code

Retrieval-augmented generation skills for Claude Code — routing queries to the right store, handling empty-retrieval fallbacks, and diagnosing why a RAG pipeline returns the wrong answer.

Quick answer

Loreto has 6 RAG skills for Claude Code — each a packaged SKILL.md with references and a runnable test, ready to drop into .claude/skills/.

RAG

Agentic RAG Fallback

Designs a Retrieve-Check-Route fallback pattern for agentic (multi-tool) RAG systems so that when every retriever tool…

RAG

Agentic RAG Routing

Designs an agentic RAG architecture where an LLM agent acts as a dynamic router, semantically selecting the correct dom…

RAG

RAG Pipeline Vector DB

Designs a traditional RAG pipeline organized around the Query-Retrieve-Augment-Generate (QRAG) flow and its single-LLM-…

RAG

RAG Pipeline Vector Store

Designs a baseline single-hop RAG pipeline that grounds LLM answers in private or domain-specific documents via vector…

RAG

RAG Query Routing

Designs and implements LLM-backed query routing across multiple domain-specific vector stores using the retriever-tool…

RAG

RAG Relevance Fallback

Designs a conditional fallback branch in a single-store RAG pipeline so that when retrieved documents are irrelevant or…

Need a RAG skill that doesn't exist yet?

Generate one from any source in minutes — a paper, a talk, a doc, or your own hard-won workflow.