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.

Design and evaluate prompts for LLMs v1.0.0

Use this resource to design, optimise and evaluate the prompts of an LLM application

New

  • 455 downloads
  • 136 likes
  • 110 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-prompt-design-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 writes and refactors prompts, generates JSON output or function-calling schemas, applies patterns such as step-by-step reasoning or few-shot examples, and builds rubrics and test suites to measure quality.

Mostly picked by

Updated November 2, 2026

Card for the “Design and evaluate prompts for LLMs” skill

Details

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

Similar resources

View all

What you get

  • references/prompt-patterns.md and system-prompts.md: prompt patterns and system prompts
  • references/structured-outputs.md, evaluation-frameworks.md, prompt-optimization.md: structured outputs and evaluation

Good fit for

  • Your assistant answers the same question inconsistently
  • You must guarantee valid JSON output for automated processing

Not for

    Tags

    • prompt
    • llm
    • evaluation
    • structured-output

    About

    You say

    “Refactor this system prompt so it returns JSON validated by this schema, then write a ten-case evaluation rubric.”

    Card for the “Design and evaluate prompts for LLMs” skill

    Skill published by jeffallan 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, optimise and evaluate the prompts of an LLM application
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/context-management.md7.6 KB
    • references/evaluation-frameworks.md23.9 KB
    • references/prompt-optimization.md17.8 KB
    • references/prompt-patterns.md16.3 KB
    • references/structured-outputs.md19.3 KB
    • references/system-prompts.md19.1 KB
    • SKILL.md6 KB

    Origin and licence

    Listed unmodified

    Author
    jeffallan
    Source
    github.com/jeffallan/claude-skills/tree/b7f220d32a0925c9bbfd24995e208e76bb74507c/skills/prompt-engineer
    Licence
    MIT

    Notice

    « prompt-engineer » (jeffallan, 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.