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.

Retuning a skill corpus for a new model v1.0.0

Use this resource to adapt a skill corpus to a new model while measuring each change

New

  • 499 downloads
  • 167 likes
  • 218 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install retune-skills-for-new-model

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 sets a baseline from run archives, fixes the measurement noise, audits the corpus, then edits in passes. It refuses to start without a benchmark harness that can compare two builds of the corpus.

Mostly picked by

Updated November 2, 2026

Card for the “Retuning a skill corpus for a new model” skill

Details

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

Similar resources

View all

What you get

  • references/: baseline mining, noise floor and corpus audit
  • SKILL.md: the measurement gate and the retuning phases

Good fit for

  • A skill corpus degrades after a model change
  • You have a benchmark harness to compare two versions

Not for

    Tags

    • models
    • benchmark
    • corpus
    • measurement

    About

    You say

    “Retune our skills for the new model using the existing benchmark harness.”

    Card for the “Retuning a skill corpus for a new model” skill

    Skill published by everyinc 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 adapt a skill corpus to a new model while measuring each change
    3. Review and adjust the result

    Content preview

    Files

    • agents/openai.yaml0 KB
    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/baseline-mining.md10.5 KB
    • references/corpus-audit.md12.6 KB
    • references/cut-passes.md10.9 KB
    • references/halt-taxonomy.md11.1 KB
    • references/noise-floor.md13.1 KB
    • references/workflow-shapes.md11.5 KB
    • SKILL.md4.6 KB

    Origin and licence

    Listed unmodified

    Author
    everyinc
    Source
    github.com/everyinc/compound-engineering-plugin/tree/d400846211b6c708f73311f9e7b35cb57d863543/skills/ce-retune
    Licence
    MIT

    Notice

    « ce-retune » (everyinc, 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.