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.

Prompt optimization and evaluation v1.0.0

Use this resource to optimize a prompt and test it on varied cases

New

  • 496 downloads
  • 106 likes
  • 192 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install prompt-optimization-evaluation

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 applies prompt structuring techniques, generates synthetic test data and evaluates the prompt on edge cases. You get a revised prompt and a way to check its reliability.

Mostly picked by

Updated November 2, 2026

Card for the “Prompt optimization and evaluation” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: workflow, principles and deliverables checklist
  • references/techniques.md: prompt structuring techniques
  • references/synthetic-data.md: test data generation

Good fit for

  • You are writing the system prompt of an assistant or agent
  • Your LLM outputs vary a lot from one call to the next

Not for

    Tags

    • prompt
    • llm
    • evaluation
    • agents

    About

    You say

    “Improve our support assistant's prompt and generate twenty test cases, including ambiguous requests.”

    Card for the “Prompt optimization and evaluation” skill

    Skill published by nickcrew 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 optimize a prompt and test it on varied cases
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/synthetic-data.md9 KB
    • references/techniques.md9.9 KB
    • SKILL.md2.8 KB

    Origin and licence

    Listed unmodified

    Author
    nickcrew
    Source
    github.com/nickcrew/claude-cortex/tree/bb47af79ad3befe01ae01940fcf5f16e30a1b6df/skills/prompt-engineering
    Licence
    MIT

    Notice

    « prompt-engineering » (nickcrew, 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.