Stats
Actions
Tags
From rag-skills
Route RAG retrieval quality work across hybrid search, reranking, query transformation, HyDE, Self-RAG, RAPTOR, CRAG, and Graph RAG.
How this skill is triggered — by the user, by Claude, or both
Slash command
/rag-skills:retrieval-strategiesThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this parent skill when the main RAG problem is search quality, ranking, recall, context selection, or evidence traceability. Route to the child skill that best matches the retrieval failure.
Use this parent skill when the main RAG problem is search quality, ranking, recall, context selection, or evidence traceability. Route to the child skill that best matches the retrieval failure.
Embedding search alone often misses exact terms, ranks weak evidence too high, or retrieves incomplete context. RAG systems need retrieval strategies that adapt to query type and evidence requirements.
Identify whether the issue is recall, ranking, query mismatch, missing context, or poor citations.
Choose hybrid search for exact-term misses, reranking for noisy top-k results, query transformation for vague questions, and corrective patterns for unreliable evidence.
Measure recall at k, MRR or nDCG, citation accuracy, answer faithfulness, and latency impact.
npx claudepluginhub goodnight77/rag-skills --plugin rag-skillsCovers RAG architecture including design patterns, chunking strategies, embedding models, retrieval techniques, hybrid search, and context assembly for LLM pipelines.
Provides production RAG patterns for grounded LLM responses including core RAG, embeddings, hybrid search, contextual retrieval, HyDE, agentic/multimodal RAG, query decomposition, reranking, and pgvector.
Designs and implements production-grade RAG systems: chunking documents, generating embeddings, configuring vector stores, hybrid search, reranking, and retrieval evaluation.