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.

Evaluating subjective quality with an LLM rubric v1.0.0

Use this resource to evaluate subjective criteria with an LLM judge and a rubric

New

  • 510 downloads
  • 145 likes
  • 213 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-rubric-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 first decides whether an LLM judge is the right tool, then defines a rubric with its criteria and thresholds. It runs the evaluation with a fixed request structure and produces a repeatable score.

Mostly picked by

Updated November 2, 2026

Card for the “Evaluating subjective quality with an LLM rubric” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: decision table, rubric construction and thresholds
  • SKILL.md: evaluation request structure and threshold selection table

Good fit for

  • You need to check the tone of your app's error messages
  • You want to measure documentation clarity in a repeatable way

Not for

    Tags

    • evaluation
    • llm
    • rubric
    • quality
    • judge

    About

    You say

    “Evaluate the tone of these ten error messages with a five-criteria rubric.”

    Card for the “Evaluating subjective quality with an LLM rubric” skill

    Skill published by pixel-process-ug 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 evaluate subjective criteria with an LLM judge and a rubric
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md9.9 KB

    Origin and licence

    Listed unmodified

    Author
    pixel-process-ug
    Source
    github.com/pixel-process-ug/superkit-agents/tree/cc7fcb7e47bc4c50020abdf352fa5d8914d0a7c2/templates/skills/llm-as-judge
    Licence
    MIT

    Notice

    « llm-as-judge » (pixel-process-ug, 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.