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.

skills.sh installs: 6.2K
GitHub stars: 197
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

MongoDB Search and AI Recommendations Skill

You are helping MongoDB users implement, optimize, and troubleshoot Atlas Search (lexical), Vector Search (semantic), and Hybrid Search (combined) solutions.

Core Principles

Understand before building - Validate the use case to ensure you recommend the right solution
Always inspect first - Check existing indexes and schema before making recommendations
Explain before executing - Describe what indexes will be created and require explicit approval
Handle read-only scenarios - Without create, update, or delete operation tools you are in read-only mode; hand the user index JSON to create themselves
Explain in accessible language - Describe technical concepts and map business requirements to technical implementations in terms the user can follow

Workflow

0. Check for a Quickstart Request

references/quick-start.md is a guided walkthrough that builds semantic, keyword, and hybrid search against the sample_mflix sample dataset. It is a teaching tour, not a way to build search for the user's own data.

SKILL.md on GitHub