Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL alignment (DPO/RLVR/GRPO/RLHF), BYOB/MCQ benchmarks, checkpoint conversion, ModelOpt optimization, env profiles, and evaluation of trained checkpoints or existing/hosted endpoints.
Install
npx skills add NVIDIA/skills --skill nemotron-customizenpx skills add NVIDIA/skills --skill nemotron-customize -a claude-code -gnpx skills add NVIDIA/skills --skill nemotron-customize -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/nemotron-customizegh skill install NVIDIA/skills nemotron-customizegit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/nemotron-customize ~/.claude/skills/nemotron-customize # Claude Code
cp -R /tmp/NVIDIA__skills/skills/nemotron-customize ~/.agents/skills/nemotron-customize # Codex, Cursor, Gemini CLI, Copilot, OpenCode