Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

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.

Test whether a light model can run a skill v1.0.0

Use this resource to check that a lightweight model can execute a skill, not just understand it

New

  • 358 downloads
  • 167 likes
  • 145 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install skill-executability-eval-matrix

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 skill's evals on Haiku, Sonnet or Opus with real tool execution, grades the outputs with deterministic checks first, then gives a verdict per model. You learn whether the skill holds up on a cheaper model.

Mostly picked by

Updated November 2, 2026

Card for the “Test whether a light model can run a skill” skill

Details

Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: eval resolution, serialized runs and grading
  • SKILL.md: aggregation into model-matrix.json and final report

Good fit for

  • You want a skill that a cheap model can use
  • A skill passes with Opus but fails with Haiku

Not for

    Tags

    • evaluation
    • skills
    • haiku
    • models

    About

    You say

    “Run the evaluation matrix for this skill on Haiku and Opus.”

    Card for the “Test whether a light model can run a skill” skill

    Skill published by laurigates 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 check that a lightweight model can execute a skill, not just understand it
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md9.8 KB

    Origin and licence

    Listed unmodified

    Author
    laurigates
    Source
    github.com/laurigates/claude-plugins/tree/3cbda15de062aa6d3302afd330afb0ff1c8979df/evaluate-plugin/skills/evaluate-matrix
    Licence
    MIT

    Notice

    « evaluate-matrix » (laurigates, 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.