Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Evaluate the quality of an agent or skill v1.0.0

Use this resource to test the quality of AI skills and agents before deployment

New

  • 370 downloads
  • 162 likes
  • 119 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install evaluate-agent-skill-quality

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent scores a skill or agent on a five-dimension rubric, using direct scoring, an LLM judge or pairwise comparison. You get documented scores and the points to fix before deployment.

Mostly picked by

Updated November 2, 2026

Card for the “Evaluate the quality of an agent or skill” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: five-dimension scoring rubric and evaluation methods
  • Sections on the LLM judge, pairwise comparison and the judge prompt template

Good fit for

  • You have just created a skill and want to check that it works
  • An agent's behaviour is inconsistent from one session to the next

Not for

    Tags

    • evaluation
    • agents
    • quality

    About

    You say

    “Evaluate this code review skill on the five dimensions and give a score per criterion.”

    Card for the “Evaluate the quality of an agent or skill” skill

    Skill published by guia-matthieu under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to test the quality of AI skills and agents before deployment
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md8.5 KB

    Origin and licence

    Listed unmodified

    Author
    guia-matthieu
    Source
    github.com/guia-matthieu/clawfu-skills/tree/4108f5c010ccaa8b5707fa05ca1d888ae167e548/skills/meta/agent-evaluation
    Licence
    MIT

    Notice

    « agent-evaluation » (guia-matthieu, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.