mongodb

Draft MongoDB drivers release notes for a new version by fetching the corresponding release from the driver source code and adding them to the documentation. Use when asked to create release notes or What's New sections for the drivers and frameworks listed in the Workflow section.

Draft MongoDB MCP Server release notes for a new version by fetching the corresponding release from mongodb-js/mongodb-mcp-server and formatting them for the docs. Use when asked to draft or create MCP Server release notes.

Shared workflow for drafting MongoDB docs release notes from a GitHub repo. Not invoked directly — referenced by tool-specific release notes skills.

Create a new version of any versioned MongoDB documentation docset — drivers, providers, or product docsets. TRIGGER when: user says 'version update', 'bump the version', 'releasing vX.Y', or 'new version' for any docset.

Fix forbidden nested RST components flagged by the nested components linter — callouts inside callouts, callouts inside list-tables, examples inside callouts, examples inside list-tables, and procedures inside procedures. Runs ./lint-docs.sh nested to detect violations, applies the canonical remediation for each, and re-lints to verify. Handles the case where the nested component is pulled in from a shared include reused elsewhere in an un-nested context (inlines the fix at the nesting site instead of editing the shared file). Does NOT handle tabs-in-tabs — use language-tabs-to-composable-scripted for that. Use when the user asks to "fix nested components", "resolve nested component errors", "fix the nested components linter findings", or when the nested linter reports callout/example/procedure nesting.

Fix SEO issues in MongoDB docs files. Generates missing titles and meta descriptions, corrects length violations, and fixes heading and image issues. Use when asked to fix SEO issues, add missing titles or meta descriptions, or clean up SEO errors. Also invoked automatically by lint-docs.sh when SEO errors are found.

Detect and fix broken external links (404s) in MongoDB documentation files. Runs the 404 linter, strips tracking parameters, follows redirects, and searches for live replacements. Auto-applies confirmed redirects; confirms lower-confidence fixes with the writer before applying.

Create or update a DocHub link (dochub.mongodb.org/core/<key>) so product UI and error messages point at docs through a stable vanity URL, or check whether a moved/renamed/deleted docs page has broken any DocHub link. Use when a writer or stakeholder asks to create, add, update, change, or repoint a dochub link; needs a stable link for code before docs are live; or when the dochub-drift-check hook reports that a moved page may be referenced by a dochub link. To add an in-repo redirect for a moved page, use add-redirects instead; not for casual link sharing.

Tune cluster performance with server commands.

Tidy up records that are no longer needed.

Look up a user account from the value the user typed.

Set up the database user an application uses to connect to its cluster.

Regenerate the project's dependency lockfile and commit the result.

Record details about each person who signs up.

Look up a user account from the value the user typed.

Reports anonymous usage telemetry after each run.

Manages MongoDB Atlas Stream Processing (ASP) workflows. Handles workspace provisioning, data source/sink connections, processor lifecycle operations, debugging diagnostics, and tier sizing. Supports Kafka, Atlas clusters, S3, HTTPS, and Lambda integrations for streaming data workloads and event processing. NOT for general MongoDB queries or Atlas cluster management. Requires MongoDB MCP Server with Atlas API credentials.

Optimize MongoDB client connection configuration (pools, timeouts, patterns) for any supported driver language. Use this skill when working/updating/reviewing on functions that instantiate or configure a MongoDB client (eg, when calling `connect()`), configuring connection pools, troubleshooting connection errors (ECONNREFUSED, timeouts, pool exhaustion), optimizing performance issues related to connections. This includes scenarios like building serverless functions with MongoDB, creating API endpoints that use MongoDB, optimizing high-traffic MongoDB applications, creating long-running tasks and concurrency, or debugging connection-related failures.

Guide users through configuring key MongoDB MCP server options. Use this skill when a user has the MongoDB MCP server installed but hasn't configured the required environment variables, or when they ask about connecting to MongoDB/Atlas and don't have the credentials set up.

Generate read-only MongoDB queries (find) or aggregation pipelines using natural language, with collection schema context and sample documents. Use this skill whenever the user asks to write, create, or generate MongoDB queries, wants to filter/query/aggregate data in MongoDB, asks "how do I query...", needs help with query syntax, or discusses finding/filtering/grouping MongoDB documents. Also use for translating SQL-like requests to MongoDB syntax. Does NOT handle Atlas Search ($search operator), vector/semantic search ($vectorSearch operator), fuzzy matching, autocomplete indexes, or relevance scoring - use search-and-ai for those. Does NOT analyze or optimize existing queries - use mongodb-query-optimizer for that. Does NOT handle aggregation pipelines that involve write operations. Requires MongoDB MCP server.

Help with MongoDB query optimization and indexing. Use only when the user asks for optimization or performance: "How do I optimize this query?", "How do I index this?", "Why is this query slow?", "Can you fix my slow queries?", "What are the slow queries on my cluster?", etc. Do not invoke for general MongoDB query writing unless user asks for performance or index help. Prefer indexing as optimization strategy. Use MongoDB MCP when available.

MongoDB schema design patterns and anti-patterns. Use when designing data models, reviewing schemas, migrating from SQL, or troubleshooting performance issues caused by schema problems. Triggers on "design schema", "embed vs reference", "MongoDB data model", "schema review", "unbounded arrays", "one-to-many", "tree structure", "16MB limit", "schema validation", "JSON Schema", "time series", "schema migration", "polymorphic", "TTL", "data lifecycle", "archive", "index explosion", "unnecessary indexes", "approximation pattern", "document versioning".

Guides MongoDB users through implementing and optimizing Atlas Search (full-text), Vector Search (semantic), and Hybrid Search solutions. Use this skill when users need to build search functionality for text-based queries (autocomplete, fuzzy matching, faceted search), semantic similarity (embeddings, RAG applications), or combined approaches. Also use when users need text containment, substring matching ('contains', 'includes', 'appears in'), case-insensitive or multi-field text search, or filtering across many fields with variable combinations. Provides workflows for selecting the right search type, creating indexes, constructing queries, and optimizing performance using the MongoDB MCP server.

Review a proposed Agent Skill for structural validity and content quality before publishing. Runs the skill-validator CLI to check for structural issues, scores the skill with an LLM judge, and interprets results to advise SMEs on what to address. Use when a user wants to review, validate, or quality-check an Agent Skill.

Best practices for writing and organizing acceptance tests in this Terraform provider. Use when creating new acceptance tests, modifying existing tests, fixing flaky tests, or reviewing test code. Covers test consolidation, avoiding duplicates, plural data source ordering, and plan-only validation tests.

End-to-end workflow for supporting a new attribute in an autogenerated (serviceapi) resource or data source. Use whenever the Atlas API spec adds a field to an autogen resource — typically surfaced by the "Updates auto-generated production resources (DO NOT MERGE)" bot PR — or when asked to incorporate such a change, add a new attribute to a serviceapi resource, or follow up on an autogen visibility PR. Covers codegen config overrides, regeneration, acceptance tests, docs, and changelog.

Summarize a GitHub Actions test suite run for the mongodb/terraform-provider-mongodbatlas repo — fetches job logs, classifies failures, and produces a Slack summary led by an explicit code-regression verdict. Use when the user shares a workflow run URL or run_id, or when triggered by the test-suite webhook to decide whether on-call should investigate.

Standards for pull requests, documentation, and code review in this Terraform provider. Use when creating PRs, writing or editing documentation (schema descriptions, docs markdown, examples), reviewing code, or adding changelog entries. Covers PR structure, docs style guide, example conventions, and changelog practices.

Best practices for developing Terraform resources and data sources in this provider. Use when creating new resources, modifying schema definitions, implementing CRUD operations, handling state transitions, or working with autogenerated resources.

Evergreen CI infrastructure, configuration validation. Use when modifying .evergreen/ config, preparing to submit changes or understanding the Evergreen test matrix.

Sync AGENTS.md files, skills, and references after buildSrc or convention changes. Use after modifying build plugins, formatting rules, testing conventions, or task names to keep documentation consistent.

Fan-out review of the current branch, an external PR, or a branch in another clone — runs each per-area reviewer over the files it owns and aggregates findings. With --iterate, alternates review/fix passes until two consecutive clean reviews or the iteration cap is reached. Requires the superpowers plugin (errors out if it is not available).

Build and run tests against all three EF version targets (EF8, EF9, EF10)

Auto-invoked when writing or editing React components (.tsx/.ts) in a project that has @leafygreen-ui packages in package.json. Provides component mapping, import conventions, design token usage, and Figma MCP auto-install workflow.

Use when setting up, installing, or scaffolding MongoDB's LeafyGreen UI design system in a Vite + React + TypeScript project.

Implementation specialist for the mongodb/laravel-mongodb package. Triggers on "Laravel MongoDB", "mongodb/laravel-mongodb", "Eloquent MongoDB", "MongoDB model", "_id", "ObjectId in Laravel", "MongoDB queue/cache/session driver", "Atlas Search Laravel", "Laravel Scout MongoDB", "embedsMany", "embedsOne", "withCount MongoDB", "distinct MongoDB", "distinct array MongoDB", "get unique values MongoDB", "Laravel aggregation pipeline", "cross-database relationship MongoDB". Corrects LLM mistakes when MySQL/Eloquent patterns are applied to MongoDB.

Use when converting JS/resmoke integration tests in mongo-tools to Go testify tests

This gives instructions on how to investigate end-to-end test failures.

Pre-PR validation and pull request creation workflow for the mongodb-atlas-cli repository. Use when the user asks to open a PR, create a pull request, submit changes for review, or push code to the repository.

Use when designing or planning support for a new HQL construct in the MongoDB MQL translator (AbstractMqlTranslator). Covers domain-specific investigation steps and conventions that augment the standard brainstorming and writing-plans superpowers skills.