Search Vector Architect

Design and implement production-grade semantic search and RAG systems. Use when building search infrastructure, RAG pipelines, or troubleshooting retrieval quality in LLM-powered applications. Covers embedding model selection, chunking strategy, hybrid search (BM25 + vector), reranking, retrieval evaluation (NDCG, MRR), and production concerns (latency, index size, cost).

k1lgor Updated 9 repo stars
Mega-Mind Skills System — a glowing circuit brain orchestrating a ring of skill nodes

File contents

k1lgor/mega-mind-skills commit f0b7eab47d

Frequently asked questions

npx get-skill add k1lgor/search-vector-architect-2