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.

skills.sh installs: 352.8K
GitHub stars: 486
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

run-train

Use this as the Rigor Train skill. The installed slug remains run-train for compatibility.

Use the shared operating principles in ../ai-research-reproduction/references/agent-operating-principles.md; this skill should keep training evidence bounded while leaving repository-specific monitoring details to the model.

When to apply

When the training command has already been selected and should be executed conservatively.
When the researcher wants startup verification, short-run verification, full training kickoff, or resume handling.
When the run needs structured training status, checkpoint, and metric reporting.

When not to apply

When the main task is environment setup or asset download.
When the researcher wants inference-only or evaluation-only execution.
When the task is speculative exploration, multi-variant sweeps, or autonomous idea implementation.
When the user still needs repository intake or paper gap resolution.