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.

LLM prompt engineering v1.0.0

Use this resource to write prompts that produce reliable outputs

New

  • 537 downloads
  • 167 likes
  • 240 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-prompt-design-techniques

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 prompting principles and techniques: system role, examples, step-by-step reasoning, output format and guardrails. You get a rewritten prompt and the reasons behind each choice.

Mostly picked by

Updated November 2, 2026

Card for the “LLM prompt engineering” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
CC0-1.0

Similar resources

View all

What you get

  • SKILL.md: core principles and techniques (system role, examples, reasoning)
  • SKILL.md: constraints, guardrails and anti-patterns to avoid

Good fit for

  • A prompt gives inconsistent answers from run to run
  • You need an output format your code can parse

Not for

    Tags

    • prompt
    • llm
    • examples
    • structured output

    About

    You say

    “Rewrite my ticket classification prompt so it always returns JSON with three fields.”

    Card for the “LLM prompt engineering” skill

    Skill published by spencerpauly under the CC0-1.0 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 write prompts that produce reliable outputs
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE7 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md3.7 KB

    Origin and licence

    Listed unmodified

    Author
    spencerpauly
    Source
    github.com/spencerpauly/awesome-cursor-skills/tree/99cd2655788456cc1c685944dcf8c2de82c1ded4/resources/prompt-engineering
    Licence
    CC0-1.0

    Notice

    « prompt-engineering » (spencerpauly, CC0-1.0) 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.