Can this skill help reduce LLM hallucinations?

Absolutely. By optimizing the retrieval phase and ensuring only high-quality, relevant data enters the context window, it minimizes the chances of the LLM generating incorrect information.

Does it support hybrid search patterns?

Yes, it includes patterns for combining keyword-based search (like BM25) with vector similarity using Reciprocal Rank Fusion for superior results.

What is the RAG Engineer skill?

It is a specialized capability for Claude Code that provides domain-specific patterns and best practices for building, optimizing, and evaluating Retrieval-Augmented Generation systems.

How does this skill improve AI retrieval quality?

It advocates for semantic chunking over fixed-size windows and implements reranking steps to ensure the context provided to the LLM is highly relevant and structured.

RAG Architect & Engineer

Name: RAG Architect & Engineer
Author: claudiodearaujo

byclaudiodearaujo

データサイエンスとML

Architects high-performance Retrieval-Augmented Generation systems using advanced chunking, vector embeddings, and retrieval optimization.

概要

The RAG Engineer skill transforms Claude into a specialized systems architect for Retrieval-Augmented Generation, bridging the gap between raw data and LLM generation. It provides deep expertise in critical components like semantic chunking, vector database management, and hybrid search implementation. By focusing on retrieval quality through reranking and metadata filtering, this skill ensures that LLM applications receive the most relevant context, significantly reducing hallucinations and improving the accuracy of generated responses.

主な機能

Hybrid search implementation (Keyword + Semantic)
Vector embedding and similarity search optimization
Semantic and hierarchical document chunking
Retrieval pipeline evaluation and reranking
Context window and metadata filtering strategies
0 GitHub stars

ユースケース

Implementing hybrid search for complex, multi-modal document retrieval
Building enterprise knowledge bases from unstructured document sets
Optimizing existing RAG pipelines to reduce LLM hallucinations

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add claudiodearaujo/sistema-de-narra-o-de-livro-front rag-engineer

For use in Claude.ai and ChatGPT

Download Skill

GitHub

概要