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.

Evaluation set for an agent or prompt v1.0.0

Use this resource to check that an agent or prompt works and catch regressions

New

  • 458 downloads
  • 167 likes
  • 238 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install prompt-agent-evaluation-harness

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 defines checkable pass criteria, builds about twenty cases, scores the outputs and reruns the set on every change. You get a reusable evaluation set to compare models and versions before release.

Mostly picked by

Updated November 2, 2026

Card for the “Evaluation set for an agent or prompt” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: pass criteria, set construction and scoring method
  • SKILL.md: rules for running it as a test and output format

Good fit for

  • You want to compare two models or two prompt versions
  • An agent gives inconsistent output and you do not know why

Not for

    Tags

    • evaluation
    • prompt
    • regression

    About

    You say

    “Build a twenty-case evaluation set for our ticket triage prompt and compare it with the new version.”

    Card for the “Evaluation set for an agent or prompt” skill

    Skill published by onewave-ai 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 check that an agent or prompt works and catch regressions
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md4.2 KB

    Origin and licence

    Listed unmodified

    Author
    onewave-ai
    Source
    github.com/onewave-ai/claude-skills/tree/b2267d9171af4f56848d82992381b20b89b44056/agent-eval-harness
    Licence
    MIT

    Notice

    « agent-eval-harness » (onewave-ai, 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.