# Run Train

> 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/`. Do not use for environment setup, exploratory sweeps, speculative idea implementation, or end-to-end orchestration.

Source: https://skillsagentes.com/skills/lllllllama/rigorpilot-skills/run-train
Repository: https://github.com/lllllllama/RigorPilot-Skills
Author: lllllllama
License: MIT
Updated: hace 19 días
Context cost: 111 tok installed, 621 tok once triggered, 4.9k tok with every bundled file
Bundle: 5 files, 19 KB
Permissions requested: none declared

## Install

```bash
npx -y skills add lllllllama/RigorPilot-Skills --skill run-train --agent claude-code
```

## What it does

- Ejecuta de forma conservadora un comando de entrenamiento ya seleccionado (verificación de arranque, run corto, kickoff completo o resume)
- Genera evidencia estandarizada en train_outputs/: SUMMARY.md, COMMANDS.md, LOG.md, SCIENTIFIC_CHANGELOG.md, COMPARABILITY_REPORT.md y status.json
- Registra estados parciales, bloqueados, reanudados o iniciados con claridad
- Conserva contexto de reproducibilidad: configs, seeds, checkpoints, logs, métricas y supuestos de runtime

## Use it when

- El comando de entrenamiento ya fue seleccionado y debe ejecutarse de forma conservadora
- Se necesita verificación de arranque, verificación de run corto, kickoff completo o manejo de resume
- Se requiere reporte estructurado de estado, checkpoints y métricas del entrenamiento

## Don't bother when

- La tarea principal es configuración de entorno, descarga de assets, o ejecución solo de inferencia/evaluación
- La tarea es exploración especulativa, sweeps multi-variante o implementación autónoma de ideas
- El usuario aún necesita intake del repositorio o resolución de gaps del paper

## What triggers it

- "Ejecuta el comando de entrenamiento seleccionado en modo verificación corta"
- "Haz un kickoff completo del entrenamiento y registra checkpoints y métricas"
- "Reanuda el entrenamiento desde el último checkpoint y documenta el estado"

## Before you install

- Requiere que ya exista un objetivo de entrenamiento seleccionado y un comando ejecutable, junto con los archivos de referencia y scripts del skill (training-policy.md, run_training.py, write_outputs.py).

## Files

- SKILL.md — 2 KB
- agents/openai.yaml — 331 B
- references/training-policy.md — 1 KB
- scripts/run_training.py — 15 KB
- scripts/write_outputs.py — 813 B

## SKILL.md

Reproduced verbatim from lllllllama/RigorPilot-Skills under MIT. This section is the upstream document and is in English.

# run-train

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

Use the shared operating principles in
`../../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.

## Clear boundaries

- This skill executes a selected training command and normalizes the resulting evidence.
- It does not choose the overall research goal on its own.
- It does not own exploratory branching or speculative code adaptation.
- It should record partial, blocked, resumed, and kicked-off states clearly.
- It should preserve reproducibility context such as configs, seeds,
  checkpoints, logs, metrics, and runtime assumptions when available.

## Input expectations

- selected training goal
- runnable training command
- environment and asset assumptions
- run mode such as startup verification, short-run verification, full kickoff, or resume

## Output expectations

- `train_outputs/SUMMARY.md`
- `train_outputs/COMMANDS.md`
- `train_outputs/LOG.md`
- `train_outputs/SCIENTIFIC_CHANGELOG.md`
- `train_outputs/COMPARABILITY_REPORT.md`
- `train_outputs/status.json`

## Notes

Use `references/training-policy.md`, `../../references/deep-learning-experiment-principles.md`, `scripts/run_training.py`, and `scripts/write_outputs.py`.

---

Skills Agentes — https://skillsagentes.com/skills/lllllllama/rigorpilot-skills/run-train