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 and improve AI agent outputs v1.0.0

Use this resource to add self-evaluation and iterative refinement to an agent

New

  • 394 downloads
  • 107 likes
  • 202 saves

Free

Install with the CLI

In a terminal, from the folder you want:

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

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 design a generate, evaluate, critique and refine loop from reusable patterns. It proposes evaluation strategies: outcome-based checks, LLM-as-judge or rubrics. You get a plan for an evaluation pipeline.

Mostly picked by

Updated November 2, 2026

Card for the “Evaluate and improve AI agent outputs” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: reflection and evaluator-optimizer patterns
  • SKILL.md: evaluation strategies (outcome, LLM-as-judge, rubric) and best practices

Good fit for

  • Your agent produces code or reports that must meet a standard
  • You want an automatic judge to compare response versions

Not for

    Tags

    • agent evaluation
    • llm-as-judge
    • rubrics
    • self-critique

    About

    You say

    “Add a self-critique loop to my report generator so it checks the figures before delivery.”

    Card for the “Evaluate and improve AI agent outputs” skill

    Skill published by github 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 add self-evaluation and iterative refinement to an agent
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md5.8 KB

    Origin and licence

    Listed unmodified

    Author
    github
    Source
    github.com/github/awesome-copilot/tree/0fe6545b950671641b2b14b44eb56678fea6c6b4/skills/agentic-eval
    Licence
    MIT

    Notice

    « agentic-eval » (github, 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.