Nemotron Policy Generator — Agent Skill by NVIDIA

From the author

Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety. Produces a Markdown policy, JSON taxonomy, and drop-in inference prompts. Maps rough words or an existing policy to V2 categories, adding custom categories or topic-following rules.

— the description by Shyamala Prayaga

Install

Get the skill from its source (we cannot redistribute it):
https://github.com/NVIDIA/skills/tree/fce3cca4170be75e82c64920654d56ee2811b005/skills/nemotron-policy-generator

Documentation by Shyamala Prayaga

The licence of this skill does not allow us to copy its documentation. Read it at the source

Files

BENCHMARK.md(opens on GitHub)Not mirrored: opens on GitHub4.1 KiB
SKILL.md(opens on GitHub)Not mirrored: opens on GitHub19.4 KiB
assets/nemotron_policy_generator.html(opens on GitHub)Not mirrored: opens on GitHub43.8 KiB
assets/nemotron_system_prompt_template.txt(opens on GitHub)Not mirrored: opens on GitHub13.2 KiB
assets/policy_json_schema.json(opens on GitHub)Not mirrored: opens on GitHub3.0 KiB
assets/policy_md_template.md(opens on GitHub)Not mirrored: opens on GitHub2.4 KiB
evals/EVAL.md(opens on GitHub)Not mirrored: opens on GitHub4.4 KiB
evals/evals.json(opens on GitHub)Not mirrored: opens on GitHub9.6 KiB
references/content_safety_taxonomy.md(opens on GitHub)Not mirrored: opens on GitHub12.7 KiB
references/policy_patterns.md(opens on GitHub)Not mirrored: opens on GitHub3.3 KiB
references/target_models.md(opens on GitHub)Not mirrored: opens on GitHub4.6 KiB
skill-card.md(opens on GitHub)Not mirrored: opens on GitHub3.9 KiB
skill.oms.sig(opens on GitHub)Not mirrored: opens on GitHub6.4 KiB

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

The author says: nvidia/Nemotron-Content-Safety-Reasoning-4B (text, EN, /think) · nvidia/Nemotron-3-Content-Safety (multimodal, 12 langs, BYO + /think) · Gemma-3-4B-it · vLLM / SGLang / TRTLLM / Transformers · NeMo Guardrails

Security

What our scanner noticed· Medium risk

Large base64-encoded blobs

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Security And Hardening
Addy Osmani· Community
A comprehensive framework for building secure, hardened web applications through threat modeling and defensive coding practices.
SecurityClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository113.9k
Claude Security
AnthropicOfficial
Claude Security: scan the codebase (the whole repository or a scoped part of it), scan changes (this branch's or a pull request's diff, or one commit), or suggest patches (findings turned into targeted patch files, each verified by a panel of agents, that you apply when you choose). Use when the user asks to scan, audit or check code with Claude Security, to scan their changes with Claude Security, or to fix or patch Claude Security findings.
SecurityClaude CodeClaude appsOpenAI Codex+14 more
Link-onlyGitHub stars of the source repository46.3k
Mtls Configuration
Seth Hobson· Community
A comprehensive guide and template library for implementing mutual TLS (mTLS) to secure service-to-service communication in zero-trust environments.
SecurityClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k
Secrets Management
Seth Hobson· Community
A guide to implementing secure secrets management in CI/CD pipelines using industry-standard tools and best practices.
SecurityClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k
K8s Security Policies
Seth Hobson· Community
A comprehensive guide for implementing production-grade security policies in Kubernetes clusters.
SecurityClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k
Jfrog Sec
GitHubOfficial
A specialized DevSecOps agent for automated security remediation using JFrog intelligence.
SecurityGitHub Copilot
MITGitHub stars of the source repository40.9k