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.

Audit of AI phase evaluation coverage v1.0.0

Use this resource to verify that a finished AI phase is evaluated on every planned dimension

New

  • 335 downloads
  • 148 likes
  • 160 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install audit-ai-evaluation-coverage

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 compares the evaluation strategy in AI-SPEC.md with what was actually implemented. It grades each dimension COVERED, PARTIAL or MISSING, then writes EVAL-REVIEW.md with a score, a verdict, the gaps and the remediation plan.

Mostly picked by

Updated November 2, 2026

Card for the “Audit of AI phase evaluation coverage” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: COVERED, PARTIAL or MISSING grade for each dimension
  • SKILL.md: EVAL-REVIEW.md with score, verdict and remediation plan

Good fit for

  • An AI feature shipped without evidence that it is evaluated
  • You must justify an agent's quality to a team

Not for

    Tags

    • evaluation
    • AI
    • coverage
    • audit

    About

    You say

    “Audit the evaluations of the agent's phase 2.”

    Card for the “Audit of AI phase evaluation coverage” skill

    Skill published by davepoon 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 verify that a finished AI phase is evaluated on every planned dimension
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md0.9 KB

    Origin and licence

    Listed unmodified

    Author
    davepoon
    Source
    github.com/davepoon/buildwithclaude/tree/75c22add059d710b269153142600ec8ef21c2092/plugins/gsd/skills/eval-review
    Licence
    MIT

    Notice

    « gsd:eval-review » (davepoon, 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.