Mongodb Search And Ai

This one walks you through building Atlas Search, Vector Search, or Hybrid Search solutions in MongoDB without assuming you know which approach you need. It inspects your schema and existing indexes first, then asks clarifying questions about your use case before recommending lexical search for keyword matching and autocomplete, vector search for semantic similarity and RAG apps, or hybrid for combining both. The workflow is opinionated in a good way: it makes you confirm before creating indexes, steers you away from using regex or the legacy text operator for search workloads, and won't let you use rank or score fusion operators unless your cluster version actually supports them. Includes reference patterns for indexing and querying each search type.

Install to Claude Code

npx -y skills add mongodb/agent-skills --skill mongodb-search-and-ai --agent claude-code