Rigor Train skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively for startup verification, short-run verification, full kickoff, or resume, with command, config, seed, log, checkpoint, status, and metric evidence written to standardized `train_outputs/`.
安装
npx skills add lllllllama/RigorPilot-Skills --skill run-trainnpx skills add lllllllama/RigorPilot-Skills --skill run-train -a claude-code -gnpx skills add lllllllama/RigorPilot-Skills --skill run-train -a codex -ggemini skills install https://github.com/lllllllama/RigorPilot-Skills.git --path skills/run-traingh skill install lllllllama/RigorPilot-Skills run-traingit clone --depth 1 https://github.com/lllllllama/RigorPilot-Skills /tmp/lllllllama__RigorPilot-Skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/lllllllama__RigorPilot-Skills/skills/run-train ~/.claude/skills/run-train # Claude Code
cp -R /tmp/lllllllama__RigorPilot-Skills/skills/run-train ~/.agents/skills/run-train # Codex, Cursor, Gemini CLI, Copilot, OpenCode