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.

LLM pipeline evaluation with a judge model v1.0.0

Use this resource to evaluate the output quality of an LLM pipeline on a reference dataset

New

  • 354 downloads
  • 228 likes
  • 232 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-pipeline-evaluation-judge

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 runs the pipeline on the test cases, has a judge model score each output on weighted dimensions, then finds the weak steps. You get a scored report and prompt recommendations.

Mostly picked by

Updated November 2, 2026

Card for the “LLM pipeline evaluation with a judge model” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: discovery, scope configuration and evaluation phases
  • SKILL.md: --cases, --steps, --skip-pipeline, --judge-model and --dry-run options

Good fit for

  • You change a prompt and want to measure its effect on a reference set
  • You compare two judge models on the same outputs

Not for

    Tags

    • llm
    • evaluation
    • judge
    • prompts
    • quality

    About

    You say

    “Evaluate cases 1 to 3 across steps 1 to 3 with gpt-4o as judge, dry run first.”

    Card for the “LLM pipeline evaluation with a judge model” skill

    Skill published by tony363 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 the output quality of an LLM pipeline on a reference dataset
    3. Review and adjust the result

    Content preview

    Files

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

    Origin and licence

    Listed unmodified

    Author
    tony363
    Source
    github.com/tony363/superclaude/tree/6634f8ef5d5e67f17285df4a2c8a361638849c70/.claude/skills/sc-evaluate
    Licence
    MIT

    Notice

    « sc-evaluate » (tony363, 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.