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.

Measured iterative improvement v1.0.0

Use this resource to improve code through iterations measured against a benchmark

New

  • 488 downloads
  • 213 likes
  • 152 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install measured-iterative-improvement

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 up the project, proposes variants, scores them on the benchmark, keeps the best ones each round and records the history. The loop stops on the stop conditions defined at the start.

Mostly picked by

Updated November 2, 2026

Card for the “Measured iterative improvement” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md : setup, loop and selection phases
  • SKILL.md : state tracking and agent mapping

Good fit for

  • You optimize a measurable response time or bundle size
  • You want to raise test coverage step by step

Not for

    Tags

    • improvement
    • benchmark
    • optimization
    • iteration

    About

    You say

    “Cut the build time by iterating, measuring after each change.”

    Card for the “Measured iterative improvement” skill

    Skill published by zereight 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 improve code through iterations measured against a benchmark
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md7.2 KB

    Origin and licence

    Listed unmodified

    Author
    zereight
    Source
    github.com/zereight/gitlab-mcp/tree/f917d2272878b99989949a0b0517eaafb93f3f1b/.github/skills/self-improve
    Licence
    MIT

    Notice

    « self-improve » (zereight, 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.