Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

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.

Guidance: LLM output constrained by regex and grammar v1.0.0

Use this resource to constrain an LLM's output to a valid format with Guidance

New

  • 463 downloads
  • 122 likes
  • 105 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install guidance-constrained-llm-output

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 Guidance programs that enforce a syntax with regex or grammar, guarantee valid JSON, XML or code, and chain several steps in Python. It connects the chosen model: OpenAI, Transformers, llama.cpp or Claude. You get outputs that always follow the requested format.

Mostly picked by

Updated November 2, 2026

Card for the “Guidance: LLM output constrained by regex and grammar” skill

Details

Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: installation, backends and a first constrained program
  • references/constraints.md: regex and grammar constraints
  • references/examples.md: structured generation examples

Good fit for

  • Your application breaks because of badly formatted output
  • You want dates, emails or identifiers that are always valid

Not for

    Tags

    • guidance
    • structured output
    • grammar

    About

    You say

    “Force my model's answer into JSON with name, date and amount, and no surrounding text.”

    Card for the “Guidance: LLM output constrained by regex and grammar” skill

    Skill published by davila7 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 constrain an LLM's output to a valid format with Guidance
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/backends.md12.3 KB
    • references/constraints.md16.2 KB
    • references/examples.md20.4 KB
    • SKILL.md14.8 KB

    Origin and licence

    Listed unmodified

    Author
    davila7
    Source
    github.com/davila7/claude-code-templates/tree/f57964ebda91cdfb31755661ecea9395f30020f1/cli-tool/components/skills/ai-research/prompt-engineering-guidance
    Licence
    MIT

    Notice

    « prompt-engineering-guidance » (davila7, 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.