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.

Writing an LLM judge prompt for a subjective criterion v1.0.0

Use this resource to write a binary LLM judge prompt for a subjective criterion

New

  • 454 downloads
  • 125 likes
  • 241 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-as-judge-prompt-design

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 designs an LLM judge that checks a single failure mode: task and criterion, pass and fail definitions, annotated examples including borderline cases, and a structured output format. If a code rule is enough, it points you to a code evaluator.

Mostly picked by

Updated November 2, 2026

Card for the “Writing an LLM judge prompt for a subjective criterion” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: the four components of a judge prompt
  • SKILL.md: pass, fail and borderline examples, structured output format

Good fit for

  • Your criterion concerns the tone or faithfulness of an answer
  • You have already identified a failure mode to judge

Not for

    Tags

    • llm judge
    • prompt
    • evaluation
    • criterion

    About

    You say

    “Write a judge that checks whether the answer stays faithful to the provided documents, with borderline examples.”

    Card for the “Writing an LLM judge prompt for a subjective criterion” skill

    Skill published by ai-evals-course under the Apache-2.0 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 write a binary LLM judge prompt for a subjective criterion
    3. Review and adjust the result

    Content preview

    Files

    • agents/openai.yaml0.2 KB
    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md7.7 KB

    Origin and licence

    Listed unmodified

    Author
    ai-evals-course
    Source
    github.com/ai-evals-course/evals-skills/tree/80d5f7b0127c7572ed9e9339937adbfd7240ffeb/skills/write-judge-prompt
    Licence
    Apache-2.0

    Notice

    « write-judge-prompt » (ai-evals-course, Apache-2.0) 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.