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.

Agent output evaluation and refinement v1.0.0

Use this resource to design evaluation and refinement loops for AI-generated output

New

  • 555 downloads
  • 206 likes
  • 165 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install agent-output-self-evaluation-2

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 helps you define an explicit rubric, then builds a generate, evaluate, refine loop with stop conditions. You get a workflow outline and clear acceptance criteria.

Mostly picked by

Updated November 2, 2026

Card for the “Agent output evaluation and refinement” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: three patterns (basic reflection, evaluator-optimizer, code-specific reflection)
  • SKILL.md: evaluation strategies: outcome-based, LLM-as-judge and rubric-based

Good fit for

  • You want an agent to review and fix its own code or report
  • You need an automated check before output is published

Not for

    Tags

    • evaluation
    • agents
    • loop
    • criteria

    About

    You say

    “Set up an evaluation loop for my meeting summaries: five criteria, three iterations at most.”

    Card for the “Agent output evaluation and refinement” skill

    Skill published by practicalswan 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 design evaluation and refinement loops for AI-generated output
    3. Review and adjust the result

    Content preview

    Files

    • CHANGELOG.md6.2 KB
    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md8.5 KB

    Origin and licence

    Listed unmodified

    Author
    practicalswan
    Source
    github.com/practicalswan/agent-skills/tree/6cf63517700aa9ba0b80e711a93837e3bea13d0a/agentic-eval
    Licence
    MIT

    Notice

    « agentic-eval » (practicalswan, 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.