Skip to content
TrustedSkillsbeta
Back to all skills

Audit Agents Skills

Checked
florianbruniaux·vlatest·agents·CC-BY-SA-4.0

Analyzes agent skills & configurations to identify inconsistencies, errors, and optimization opportunities across deployments.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add florianbruniaux/claude-code-ultimate-guide --skill audit-agents-skills --full-depth -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

florianbruniaux

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned florianbruniaux/claude-code-ultimate-guide at a10267c921.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
a10267c921
Manifest
examples/skills/audit-agents-skills/SKILL.md
Scanned
2 files, 901 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill allows you to audit and evaluate the skills of other AI agents. It provides a structured way to assess their capabilities, identify potential weaknesses, and ensure they are performing as expected. The tool helps in understanding how different agent skills interact and contribute to overall system performance.

When to use it

  • Troubleshooting Agent Behavior: When an AI agent is exhibiting unexpected or undesirable behavior, use this skill to examine its underlying skills and dependencies.
  • Performance Optimization: To identify bottlenecks or inefficiencies within a multi-agent system by analyzing the performance of individual skills.
  • Skill Integration Testing: When integrating new skills into an existing agent ecosystem, audit them to ensure compatibility and prevent conflicts.
  • Security Assessment: Evaluate the security implications of using specific AI agent skills in sensitive contexts.

Key capabilities

  • Skill dependency analysis
  • Performance metrics reporting
  • Behavioral anomaly detection
  • Compatibility assessment

Example prompts

  • "Audit the 'data-extraction' skill and report its dependencies."
  • "Analyze the performance of all skills used by agent 'Project Alpha'."
  • "Assess the compatibility of the 'code-generation' skill with the existing 'testing' framework."

Tips & gotchas

This skill requires access to the internal workings and configuration of the AI agents being audited. It is not a standalone tool, but rather an analytical component within a larger agent management system.