Mongodb Query Optimizer

What it does

The instruction separates a specific query investigation from cluster-wide performance analysis. It combines index inventory, explain output and bounded document samples when database tools are connected, while Atlas recommendations require a separate working API configuration. Without those observations it falls back to a conditional suggestion based on query shape.

Best for

Developers who have an actual performance question and can identify the database, collection and representative query.

Tradeoffs and requirements

An index recommendation is a hypothesis, with storage and write overhead as well as possible read benefits. The source limits direct index creation and does not turn an absent connection into measured evidence. Its companion indexing references and the live database remain separate verification boundaries.

Best with MongoDB MCP server. Uses collection-indexes and explain when the connection string works; uses Atlas Performance Advisor when Atlas API is configured. Without either, suggest indexes from query shape only. User creates indexes in Atlas or migrations unless tooling allows otherwise.

Data and service requirements

Connected diagnosis can retrieve collection documents, query plans and slow-query logs. Review the selected cluster, permitted data scope and MCP connection before sending that information into an agent session.

Instruction-level disclosure at the checked snapshot; not an independent audit of the service or its current terms.

Install from the source

First time installing a skill? Follow the walkthrough →

Inspect the pinned source snapshot and its supporting files first. The command selects this skill through the open-source skills CLI. Node.js and agent-specific setup may be required. Installation can download code. Catalog ingestion never executes skill instructions or install scripts.

npx skills add https://github.com/mongodb/agent-skills/tree/155bb9c4b42a9a3e019f47be0669de0e4547d1ea/skills/mongodb-query-optimizer --skill mongodb-query-optimizer

Review pinned skill folder ↗ · CLI documentation ↗

After source review, use npx skills check and npx skills update to inspect and apply upstream updates. Re-check changed instructions before running them.

Safety & review signals

Static review only. This is not a security audit or a guarantee of safety.

SKILL.md text only; scripts, dependencies and runtime behavior not audited.

• Credential Reference — review the source context.
• Network Access — review the source context.

Allowed tools declaration: Unknown. Runtime permissions and network behavior: Unknown.

AI Craft Pad Skill Score

85/100 · Metadata coverage 100% · Model 1.0

Scores summarize observable discovery signals. Popularity and repository activity apply to the whole repository. Unknown runtime safety earns no certification.

Documentation

100/100

100

Maintenance

100/100

100

License Clarity

100/100

100

Repository Health

100/100

100

Compatibility Evidence

80/100

80

Popularity

41/100

41

Originality

80/100

80

Static Safety

60/100

60

Suggested workflow

Preserve the original query and workload conditions. Inspect available indexes and the plan before choosing a candidate change, then explain the evidence and expected tradeoff. Apply an approved index through the project migration process rather than silently changing a cluster.

How to judge the result

Compare returned rows, scanned keys and documents, sort behavior and elapsed time under comparable conditions. Check concurrent write behavior and verify that the claimed improvement comes from a fresh result rather than an illustrative source example.