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.

Improving through verifiable loops v1.0.0

Use this resource to improve a system through loops against measurable criteria

New

  • 443 downloads
  • 157 likes
  • 107 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install measurable-iterative-refinement

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 improves a script, pipeline, prompt or config over repeated cycles, each checked by a measurable pass/fail condition. It runs subagents in parallel and keeps the main context lean, so each regression is traced to the edit that caused it. For a one-off tweak, the method is not needed.

Mostly picked by

Updated November 2, 2026

Card for the “Improving through verifiable loops” skill

Details

Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: the loop, success conditions and context economics
  • references/worked_example.md: a detailed example and recovery from regressions

Good fit for

  • You tune a detector against a metric
  • A surprising number needs a methodical investigation

Not for

    Tags

    • iteration
    • metrics
    • loop
    • criteria

    About

    You say

    “Improve this detector until it reaches the precision threshold, checking each change.”

    Card for the “Improving through verifiable loops” skill

    Skill published by sammcj 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 system through loops against measurable criteria
    3. Review and adjust the result

    Content preview

    Files

    • evals/trigger_evals.json2.9 KB
    • LICENSE11.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/worked_example.md1.8 KB
    • SKILL.md12.8 KB

    Origin and licence

    Listed unmodified

    Author
    sammcj
    Source
    github.com/sammcj/agentic-coding/tree/3f58e2fcd85f52cc7ba7459016b8253686f20ae0/Skills_disabled/iterative-refinement
    Licence
    Apache-2.0

    Notice

    « iterative-refinement » (sammcj, 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.