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.

Filtering LLM inputs and outputs with LlamaGuard v1.0.0

Use this resource to classify and filter LLM input and output messages by safety category

New

  • 479 downloads
  • 153 likes
  • 206 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llamaguard-content-moderation-2

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 guides you through loading LlamaGuard, checking a user message or model reply, then interpreting the risk category flagged. It covers input filtering, output filtering and a deployment with vLLM.

Mostly picked by

Updated November 2, 2026

Card for the “Filtering LLM inputs and outputs with LlamaGuard” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: model loading and input and output filtering
  • SKILL.md: vLLM deployment and safety categories

Good fit for

  • You want to filter risky requests before they reach your LLM
  • You moderate the replies of a public assistant

Not for

    Tags

    • moderation
    • safety
    • filtering
    • llm

    About

    You say

    “Check with LlamaGuard whether this message asks for help with a crime.”

    Card for the “Filtering LLM inputs and outputs with LlamaGuard” skill

    Skill published by Orchestra Research 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 classify and filter LLM input and output messages by safety category
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md9.3 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/orchestra-research/ai-research-skills/tree/773a52944ba4747a18bd4ae9ade53fff041adcbc/07-safety-alignment/llamaguard
    Licence
    MIT

    Notice

    « llamaguard » (Orchestra Research, 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.