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.

Guardrails for language model applications v1.0.0

Use this resource to protect an LLM application with guardrails

New

  • 495 downloads
  • 148 likes
  • 149 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-safety-guardrails

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 places checks before and after the model: input moderation, injection detection, personal data filtering and response validation. You get a chain of checks that fails closed when in doubt.

Mostly picked by

Updated November 2, 2026

Card for the “Guardrails for language model applications” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: LLM safety principles and the agent's role
  • references/patterns.md: moderation, detection and validation patterns
  • references/sharp_edges.md: common bypasses and guardrails that fail silently

Good fit for

  • Your public chatbot receives messages trying to override its instructions
  • Your responses could expose personal data taken from documents

Not for

    Tags

    • safety
    • prompt injection
    • moderation
    • personal data
    • guardrail

    About

    You say

    “Add guardrails to our customer assistant: message moderation, card number detection and refusal when in doubt.”

    Card for the “Guardrails for language model applications” skill

    Skill published by omer-metin under the Apache-2.0 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 protect an LLM application with guardrails
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE10.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/patterns.md21 KB
    • references/sharp_edges.md18 KB
    • references/validations.md5 KB
    • SKILL.md2.2 KB

    Origin and licence

    Listed unmodified

    Author
    omer-metin
    Source
    github.com/omer-metin/skills-for-antigravity/tree/e8dcf4e8737921a10088bd5c9eb65e81f74c051f/skills/ai-safety-alignment
    Licence
    Apache-2.0

    Notice

    « ai-safety-alignment » (omer-metin, Apache-2.0) 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.