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 a binary LLM judge prompt v1.0.0

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

New

  • 392 downloads
  • 247 likes
  • 139 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-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 helps you write a judge prompt that checks exactly one failure mode. It sets the task and criterion, the Pass and Fail definitions, few-shot examples and a structured output format. You get a judge prompt ready to be calibrated.

Mostly picked by

Updated November 2, 2026

Card for the “Writing a binary LLM judge prompt” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: the four components of a judge prompt
  • SKILL.md: Pass/Fail definitions and annotated examples

Good fit for

  • A failure mode needs judgement (tone, faithfulness, relevance) that code cannot check
  • You already have human labels for this failure mode

Not for

    Tags

    • llm judge
    • prompt
    • evaluation
    • pass fail

    About

    You say

    “Write a Pass/Fail judge that detects when our assistant promises a delivery date it cannot know.”

    Card for the “Writing a binary LLM judge prompt” skill

    Skill published by hamelsmu 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 write a binary LLM judge for a subjective evaluation criterion
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md7.7 KB

    Origin and licence

    Listed unmodified

    Author
    hamelsmu
    Source
    github.com/hamelsmu/evals-skills/tree/22418da2bfb159f28a1b0dcf64e969e14ae56c99/skills/write-judge-prompt
    Licence
    MIT

    Notice

    « write-judge-prompt » (hamelsmu, 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.