add-llm-guardrails

Official

Add robust safety guardrails to LLM/agent apps

AuthorContextJet-ai
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides comprehensive safety and security guardrails for LLM/agent applications, preventing prompt injection, PII leakage, and toxic outputs.

Core Features & Use Cases

  • Input Guardrails: Detects and prevents prompt injection, PII detection, and off-topic requests before they reach the model.
  • Output Guardrails: Validates structured output, checks for toxicity, groundedness, and sensitive data egress.
  • Implementation: Integrates with popular guardrail libraries and can be wrapped around model calls.
  • Use Case: Use this Skill to enhance the security and reliability of your LLM/agent applications, especially in regulated or enterprise environments.

Quick Start

To add guardrails to your LLM app, use the 'add-llm-guardrails' skill with the command: "apply guardrails to my-app".

Dependency Matrix

Required Modules

guardrails-aillm-guardnvidia-guardrails

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: add-llm-guardrails
Download link: https://github.com/ContextJet-ai/awesome-llm-observability/archive/main.zip#add-llm-guardrails

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.