Run Train

When you've already figured out your training command and just need to run it with proper evidence collection, this is your tool. It handles startup checks, short verification runs, full training kickoffs, and resumes, then writes everything (commands, logs, configs, checkpoints, metrics) into a standardized train_outputs directory. It's not for environment setup or exploratory sweeps. The boundaries are refreshingly clear: you bring a runnable command and a goal, it executes conservatively and gives you structured output including status.json and a scientific changelog. Built for deep learning repos where reproducibility context matters more than moving fast and breaking things.

skills.sh installs: 226
GitHub stars: 289
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add lllllllama/ai-paper-reproduction-skill --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.