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.

Self-improving agent loops v1.0.0

Use this resource to design a loop where an agent improves its own harness or scaffold

New

  • 359 downloads
  • 103 likes
  • 187 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install self-improving-agent-loops

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 examines systems whose optimized target is the harness itself: failure mining, bounded edits, evolutionary search and an acceptance gate. It stresses one rule: accept a change only on empirical measurement. You get a loop design with its invariants and experience archive.

Mostly picked by

Updated November 2, 2026

Card for the “Self-improving agent loops” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: optimization ladder, invariants and acceptance gates
  • references/loop-design-evidence.md: evidence on loop design

Good fit for

  • You want an agent to correct its scaffold from its own failures
  • You compare workflow variants with an automated evaluation

Not for

    Tags

    • self-improvement
    • evolution
    • evaluation
    • optimization

    About

    You say

    “Design a loop that edits my agent's system prompt and keeps a version only if the score goes up.”

    Card for the “Self-improving agent loops” skill

    Skill published by muratcankoylan 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 design a loop where an agent improves its own harness or scaffold
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/loop-design-evidence.md13.5 KB
    • SKILL.md22.2 KB

    Origin and licence

    Listed unmodified

    Author
    muratcankoylan
    Source
    github.com/muratcankoylan/agent-skills-for-context-engineering/tree/9ff0c99108b36d3b886defd825d8ac1f47dba374/skills/self-improvement-loops
    Licence
    MIT

    Notice

    « self-improvement-loops » (muratcankoylan, 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.