Does it help reduce LLM hallucinations?

Absolutely. By focusing on retrieval quality and implementing relevance thresholds, it ensures the LLM receives only accurate, relevant context to ground its responses.

How does this skill improve AI search accuracy?

It implements advanced patterns like semantic chunking and hybrid search to ensure the most relevant information is retrieved, moving beyond simple keyword matching.

What is the RAG Engineer skill?

It is a specialized capability for Claude Code that provides expert guidance on building, optimizing, and evaluating Retrieval-Augmented Generation (RAG) systems.

Can I use this for vector database management?

Yes, it includes best practices for similarity metrics, embedding dimensions, and metadata indexing strategies for vector databases like Pinecone, Weaviate, or Milvus.

RAG Systems Engineer

Name: RAG Systems Engineer
Author: claudiodearaujo

byclaudiodearaujo

•

Ciencia de Datos y ML

Implements high-performance Retrieval-Augmented Generation systems by optimizing embeddings, chunking strategies, and vector search pipelines.

Acerca de

The RAG Engineer skill transforms Claude into a specialized architect for building intelligent document retrieval systems. It provides deep expertise in bridging raw data with LLM generation, focusing on critical optimizations like semantic chunking, hierarchical retrieval, and hybrid search. Use this skill when building AI-powered knowledge bases, semantic search engines, or any application where the accuracy of retrieved context is vital to preventing hallucinations and ensuring high-quality LLM outputs.

Características Principales

Advanced semantic chunking and document preprocessing
Hybrid search implementation (keyword + semantic)
Multi-level hierarchical retrieval design
Retrieval pipeline quality evaluation and benchmarking
Context window and similarity threshold optimization
1 GitHub stars

Casos de Uso

Building an AI-powered documentation search engine with high precision
Optimizing vector database performance for large-scale document retrieval
Reducing LLM hallucinations by refining the quality of retrieved context

What are Skills?·How to Install

Install with 🐟 Skill.Fish

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

For use in Claude.ai and ChatGPT

Download Skill

GitHub