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.

Run a single experiment iteration v1.0.0

Use this resource to run one manual experiment iteration on a target file

New

  • 354 downloads
  • 200 likes
  • 175 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install single-experiment-iteration

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 reviews the experiment's configuration, strategy and history, prepares the dedicated branch, makes one change, commits it, then evaluates it. The change is kept or discarded according to the metric.

Mostly picked by

Updated November 2, 2026

Card for the “Run a single experiment iteration” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: context loading (configuration, strategy, history)
  • SKILL.md: single-change rule, commit and evaluation

Good fit for

  • You want to test one optimisation idea before starting a loop
  • You resume an experiment by hand between two sessions

Not for

    Tags

    • experiment
    • iteration
    • evaluation
    • branch

    About

    You say

    “Run one iteration on engineering/api-speed and tell me whether we keep the change.”

    Card for the “Run a single experiment iteration” skill

    Skill published by alirezarezvani 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 run one manual experiment iteration on a target file
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md2.6 KB

    Origin and licence

    Listed unmodified

    Author
    alirezarezvani
    Source
    github.com/alirezarezvani/claude-skills/tree/5434623a788ec3105d238328cfe554e1e2242ff7/engineering/autoresearch-agent/skills/ar-run
    Licence
    MIT

    Notice

    « ar-run » (alirezarezvani, 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.