Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyzing results, preserving human oversight, and using git plus TSV logs as the research ledger.
Install
npx skills add NVIDIA/skills --skill nemo-rl-auto-researchnpx skills add NVIDIA/skills --skill nemo-rl-auto-research -a claude-code -gnpx skills add NVIDIA/skills --skill nemo-rl-auto-research -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/nemo-rl-auto-researchgh skill install NVIDIA/skills nemo-rl-auto-researchgit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/nemo-rl-auto-research ~/.claude/skills/nemo-rl-auto-research # Claude Code
cp -R /tmp/NVIDIA__skills/skills/nemo-rl-auto-research ~/.agents/skills/nemo-rl-auto-research # Codex, Cursor, Gemini CLI, Copilot, OpenCode