Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
8.7
Rating
0
Installs
AI & LLM
Category
Exceptional RAG implementation skill with comprehensive coverage of modern techniques. The description clearly articulates when to use RAG systems. The skill provides extensive task knowledge including multiple retrieval strategies (hybrid search, HyDE, multi-query), advanced patterns with working code examples, diverse vector store configurations, and evaluation metrics. Structure is excellent with logical progression from basics to advanced patterns, though the single-file format is dense (acceptable given complexity). Novelty is strong: implementing production-grade RAG with hybrid search, reranking, and proper evaluation would require significant tokens and expertise from a CLI agent alone. The skill meaningfully reduces cost by providing battle-tested patterns, proper chunking strategies, and vendor-specific configurations. Minor improvement possible by separating some advanced patterns into referenced files, but current structure remains clear and navigable.
Loading SKILL.md…

Skill Author