Run Train

Takes a training command you've already chosen and runs it conservatively, writing everything to a standardized `train_outputs/` directory with status, logs, configs, checkpoints, and metrics. Built for deep learning research repos where you want startup checks, short verification runs, or full training kickoffs with proper evidence collection. It won't pick your research direction or do exploratory sweeps, just execute what you tell it and keep the artifacts organized. The honest take: if you're tired of training runs scattering outputs everywhere and want reproducibility context in one place, this enforces that discipline without getting in your way.

Install to Claude Code

npx -y skills add lllllllama/rigorpilot-skills --skill run-train --agent claude-code