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 evaluation harness v1.0.0

Use this resource to measure the quality of an AI system repeatably

New

  • 373 downloads
  • 100 likes
  • 146 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-evaluation-harness

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 structures a golden dataset (inputs, expected outputs, criteria), writes scoring rubrics and thresholds per category, then generates a regression report. You get an evaluation run on every commit to catch quality drops.

Mostly picked by

Updated November 2, 2026

Card for the “LLM evaluation harness” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: golden dataset JSON format and test categories
  • SKILL.md: scoring rubrics, example scoring functions and thresholds
  • SKILL.md: regression report and continuous evaluation

Good fit for

  • You switch models or prompts without knowing whether quality drops
  • Your AI outputs are checked by hand

Not for

    Tags

    • evaluation
    • llm
    • golden dataset

    About

    You say

    “Build an evaluation harness for our code generation assistant: fifty cases, per-criterion scores and a 0.8 threshold.”

    Card for the “LLM evaluation harness” skill

    Skill published by patricio0312rev 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 measure the quality of an AI system repeatably
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md6.2 KB

    Origin and licence

    Listed unmodified

    Author
    patricio0312rev
    Source
    github.com/patricio0312rev/skills/tree/79ea6af485698b31060b63f0066f712560757b29/ai-engineering/evaluation-harness
    Licence
    MIT

    Notice

    « evaluation-harness » (patricio0312rev, 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.