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.

Automatic prompt optimization with history v1.0.0

Use this resource to automatically optimize the prompts of a complex task using its history

New

  • 367 downloads
  • 170 likes
  • 195 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install automatic-prompt-optimization-loop

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 rewrites complex requests before answering, using a prompt-learning MCP server, then records performance so it improves over time. It requires that server to be installed and does not apply to simple questions.

Mostly picked by

Updated November 2, 2026

Card for the “Automatic prompt optimization with history” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: optimization triggers, learning loop and stopping criteria
  • references/: APE and OPRO implementations, DSPy patterns and learning architecture

Good fit for

  • Your prompts give uneven results from one session to the next
  • You want to systematically improve your agents' prompts

Not for

    Tags

    • prompt
    • optimization
    • mcp
    • learning

    About

    You say

    “Improve this product sheet generation prompt before answering.”

    Card for the “Automatic prompt optimization with history” skill

    Skill published by curiositech 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 automatically optimize the prompts of a complex task using its history
    3. Review and adjust the result

    Content preview

    Files

    • .claude-plugin/plugin.json0.5 KB
    • CHANGELOG.md0.8 KB
    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/ape-opro-implementation.md20.2 KB
    • references/dspy-patterns.md12 KB
    • references/embedding-architecture.md16.3 KB
    • references/iteration-strategy.md2.8 KB
    • references/learning-architecture.md2.6 KB
    • references/mcp-server-spec.md17.9 KB
    • references/optimization-techniques.md3.1 KB
    • SETUP.md10.3 KB
    • SKILL.md5 KB

    Origin and licence

    Listed unmodified

    Author
    curiositech
    Source
    github.com/curiositech/some_claude_skills/tree/f49825290077e5fb46bb3e867dfa8a5b0161152b/.claude/skills/automatic-stateful-prompt-improver
    Licence
    MIT

    Notice

    « automatic-stateful-prompt-improver » (curiositech, 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.