Skip to content
TrustedSkillsbeta
Back to all skills

Agent Evaluation

Checked
zpankz·vlatest·agents

Evaluates agent performance based on provided metrics, offering actionable insights for improvement and optimization.

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 zpankz/mcp-skillset --skill agent-evaluation -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

zpankz

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 zpankz/mcp-skillset at d9355d58c0.

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

Commit
d9355d58c0
Manifest
agent-evaluation/SKILL.md
Scanned
3 files, 1,597 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, zpankz-agent-evaluation, provides a framework for evaluating AI agents. It allows users to define evaluation criteria and then assess an agent's performance against those criteria, generating structured feedback. The tool aims to provide objective assessments of agent capabilities, identifying strengths and areas for improvement.

When to use it

  • Agent Performance Review: After an agent has completed a series of tasks or interactions, evaluate its effectiveness and identify potential issues.
  • Comparative Analysis: Compare the performance of different AI agents on the same set of criteria to determine which is best suited for a specific purpose.
  • Iterative Improvement: Use evaluation results to guide adjustments to an agent's design, training data, or prompting strategies.
  • Benchmarking: Establish baseline performance metrics for agents over time to track progress and identify regressions.

Key capabilities

  • Defines evaluation criteria.
  • Assesses agent performance against defined criteria.
  • Generates structured feedback reports.
  • Provides objective assessments of agent capabilities.

Example prompts

  • "Evaluate the agent's response to this user query: [query text]"
  • "Assess the agent’s ability to summarize this document: [document content]"
  • "Compare Agent A and Agent B on these criteria: [criteria list]"

Tips & gotchas

The quality of the evaluation depends heavily on clearly defined and relevant evaluation criteria. Ensure that your criteria are specific, measurable, achievable, relevant, and time-bound (SMART) for best results.