skills.rest
handsomelong922
handsomelong922COMMUNITY
Explore all skills by this author →
GitHub

nemo-guardrails

Enforce runtime safety policies for LLM applications with configurable rails.

Updated Apr 3, 2026
Search Tags:#nemoguardrails#llm-safety#toxicity-detection#jailbreak-detection#pii-filtering#runtime-guardrails
One-click install
npx skills add https://github.com/handsomelong922/my-codex-skills --skill nemo-guardrails-handsomelong922
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nemo-guardrails
Source: https://github.com/handsomelong922/my-codex-skills/tree/main/skills/nemo-guardrails
Command: npx skills add https://github.com/handsomelong922/my-codex-skills --skill nemo-guardrails-handsomelong922

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires nemoguardrails, and includes references (resource) components.

What problem does it solve?

NVIDIA's runtime safety framework for LLM applications. Provides programmable rails that enforce safety at runtime, including jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, and toxicity detection.

Core Features & Use Cases

  • Jailbreak detection and prompt safety checks to prevent unsafe requests.
  • Input/output validation and fact-checking to ensure reliability.
  • PII filtering and toxicity detection to protect user data and maintain compliance.

Quick Start

Install nemoguardrails and wrap your LLM with a RailsConfig to enforce safety rails in production.

Frequently Asked Questions about nemo-guardrails

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add runtime guardrails to my LLM application for jailbreak detection and PII filtering?▼

Runtime guardrails enforce safety policies for LLM applications by applying configurable rails for jailbreak detection, PII filtering, and input/output validation. You can programmatically wrap your LLM with a RailsConfig to intercept and check prompts.

What is the best way to prevent hallucination and toxicity in production LLM deployments?▼

Preventing hallucination and toxicity in production LLM deployments requires programmable runtime safety rails. These rails apply fact-checking and toxicity detection across diverse prompts to ensure output reliability and compliance.

Can I use Colang 2.0 workflows to configure input and output validation for LLMs?▼

Yes, Colang 2.0 DSL workflows are supported for configuring modular guardrails. This allows you to define and enforce specific input and output validation rules for your LLM applications.

How do I set up fact-checking and toxicity checks for an existing LLM?▼

To set up fact-checking and toxicity checks, install the nemoguardrails library and wrap your existing LLM with a RailsConfig. This programmatically applies the necessary safety rails to validate inputs and filter toxic outputs.

When do I need programmable safety rails for my LLM application?▼

You need programmable safety rails when deploying LLMs to production environments requiring strict compliance. They are essential when you must enforce runtime policies for jailbreak detection, PII filtering, and toxicity checks across user prompts.

Related Skills

Explore More Software Engineering Skills→
ovachieverovachiever
52

nemo-guardrails

Enforce runtime safety rails for LLM applications using Colang 2.0 DSL.

Community
Advanced
jota-batutajota-batuta

observability

Standardize observability with structured logging, tracing, metrics, and alerting.

Community
Advanced
HemantSudarshanHemantSudarshan

llm-app-patterns

Apply modular patterns for chat interfaces, tool use, and guardrails in LLM applications.

Community
Advanced
workleapworkleap

best-practices

Audit web projects against Lighthouse best-practices guidelines and generate a structured report.

Official
Basic