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.

Refine a SKILL.md with an evaluation loop v1.0.0

Use this resource to improve a SKILL.md against measured behaviour

New

  • 596 downloads
  • 107 likes
  • 211 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install refine-skill-md-eval-loop

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 bootstrap, score, propose, apply and status cycle around the @intentsolutions/refiner CLI. Each edit must strictly improve a held-out eval score, and a three-layer hook setup gates skill quality at edit and commit time.

Mostly picked by

Updated November 2, 2026

Card for the “Refine a SKILL.md with an evaluation loop” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: bootstrap, score, propose, apply and status cycle
  • SKILL.md: three-layer hook architecture (sinker, line, hook)

Good fit for

  • You want to improve an existing skill with measurements
  • You need an eval set for a skill

Not for

    Tags

    • skill
    • evaluation
    • refinement
    • claude-code

    About

    You say

    “Refine this SKILL.md and show me the score before and after.”

    Card for the “Refine a SKILL.md with an evaluation loop” skill

    Skill published by Jeremy Longshore <jeremy@intentsolutions.io> under the Apache-2.0 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 improve a SKILL.md against measured behaviour
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md10.8 KB

    Origin and licence

    Listed unmodified

    Author
    Jeremy Longshore <jeremy@intentsolutions.io>
    Source
    github.com/jeremylongshore/tons-of-skills-marketplace/tree/ab85a061f7bcc039dac13ee193de7a4cd4388571/skills/.curated/j-rig
    Licence
    Apache-2.0

    Notice

    « j-rig » (Jeremy Longshore <jeremy@intentsolutions.io>, Apache-2.0) 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.