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.
Install
npx skills add NVIDIA/skills --skill nemotron-policy-generatornpx skills add NVIDIA/skills --skill nemotron-policy-generator -a claude-code -gnpx skills add NVIDIA/skills --skill nemotron-policy-generator -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/nemotron-policy-generatorgh skill install NVIDIA/skills nemotron-policy-generatorgit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/nemotron-policy-generator ~/.claude/skills/nemotron-policy-generator # Claude Code
cp -R /tmp/NVIDIA__skills/skills/nemotron-policy-generator ~/.agents/skills/nemotron-policy-generator # Codex, Cursor, Gemini CLI, Copilot, OpenCode