Skill: MongoDB Search & AI
by MongoDB
MongoDB's official skill for choosing between Atlas Search, Vector Search and Hybrid Search, then building the right indexes and queries for the use case.
MongoDB's official data-modelling skill — embed-vs-reference decisions, relationship patterns and the anti-patterns that quietly wreck performance and cost.
An official MongoDB agent skill covering the part of MongoDB work that indexes cannot rescue you from. As the skill puts it: bad schema is the root cause of most MongoDB performance and cost problems, and queries and indexes cannot fix a fundamentally wrong model. It gives an agent MongoDB's own modelling guidance instead of the half-remembered relational habits that produce over-normalised collections and $lookup-heavy read paths.
Designing a schema from scratch, migrating off a relational database, reviewing an existing model for performance problems, deciding between embedding and referencing, modelling one-to-one / one-to-many / many-to-many relationships, building tree or hierarchical structures, hitting the 16 MB document ceiling, or reacting to an Atlas Schema Suggestion or Performance Advisor warning.
The skill is organised as a quick-reference index into a set of focused reference documents, so the agent loads only the rule it needs:
$lookup from over-normalisation, and unnecessary or overlapping indexes.Apache-2.0, version 1.0.0, maintained by MongoDB in the mongodb/agent-skills repository. Install the whole set with npx skills add mongodb/agent-skills, install the mongodb-atlas plugin from the Claude, Cursor, Codex, Copilot or Grok marketplaces (which bundles the skills alongside the MongoDB-hosted Atlas MCP server over OAuth), or copy the single skill folder into your agent's skills directory.
Once installed, ask your agent something like:
"We're porting an orders table with a line_items child table out of Postgres. Should line items be embedded in the order document, and what breaks if an order can have 5,000 of them?"
The instructions your agent loads, as published by MongoDB.
by MongoDB
MongoDB's official skill for choosing between Atlas Search, Vector Search and Hybrid Search, then building the right indexes and queries for the use case.
by MongoDB
MongoDB's official skill for connection pools and timeouts — it refuses to hand you numbers until it knows your deployment, workload and concurrency.
by Google Cloud
Google's official Spanner skill: provision instances, design primary keys that do not hotspot, write SQL and client-library code, and diagnose slow queries — with DDL and DML gated behind your approval.
Firebase's official skill for Cloud Firestore: it detects or creates the database, picks the Standard or Enterprise edition guides, and covers provisioning, data modelling, indexes, security rules and SDK setup for Web, Python, iOS, Android and Flutter.