audit-tool-definition
Skill7 starsChanged 49 days agoNo licenceView on GitHub
Audit one or many individual agent-facing tool/function definitions — name, description, inputSchema, output/error contract, and MCP annotations — for the ergonomics failures that make an agent mis-select or misuse a tool, and emit a findings report. Invoke when reviewing the quality of individual tool definitions (function-calling specs, or the per-tool defs an MCP server exposes) or diagnosing why an agent picks or calls a tool wrong. Skip when the goal is to produce the corrected description/schema — for one tool, or a whole set rewritten one tool at a time (use write-tool-description), to audit an MCP server's own declaration — primitive choice, transport, server instructions, tool-count budget, annotation presence/defaults — rather than its individual tool defs (use audit-mcp-server), or to audit per-path data/egress security architecture (use audit-lethal-trifecta).
In this repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- architecture-committeeSkill
- audit-geo-contentSkill
- audit-github-actions-securitySkill
- audit-harness-safetySkill
- audit-instruction-fileSkill
- audit-lethal-trifectaSkill
- audit-mcp-serverSkill
- audit-memory-retrieval-integritySkill
- audit-multi-agent-orchestrationSkill
- audit-observability-setupSkill
- audit-prompt-cache-hygieneSkill
- audit-prompt-hook-placementSkill
- audit-secret-exposureSkill
- audit-self-improvement-protocolSkill
- audit-skill-qualitySkill
- audit-supply-chain-sinksSkill
- audit-verification-gatesSkill
- compress-promptSkill
- conflicting-instruction-detectorSkill
- review-codeSkill
- write-skillSkill
- write-testsSkill
- write-tool-descriptionSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.