# Minimal Run And Audit

> Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.

Source: https://skillsagentes.com/skills/lllllllama/rigorpilot-skills/minimal-run-and-audit
Repository: https://github.com/lllllllama/RigorPilot-Skills
Author: lllllllama
License: MIT
Updated: hace 19 días
Context cost: 124 tok installed, 679 tok once triggered, 3.7k tok with every bundled file
Bundle: 5 files, 14 KB
Permissions requested: none declared

## Install

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

## What it does

- Ejecuta o normaliza evidencia de un smoke test, inferencia o evaluación documentada y escribe archivos estandarizados en repro_outputs/
- Genera SCIENTIFIC_CHANGELOG.md cuando cambia el significado científico y COMPARABILITY_REPORT.md para comparar con README/paper/baseline
- Distingue claramente entre estados verificado, parcial y bloqueado
- Produce PATCHES.md cuando se modificaron archivos del repositorio

## Use it when

- Ya existe un objetivo de reproducción y un plan de configuración
- El skill principal necesita evidencia de ejecución y salidas normalizadas
- Es apropiado un smoke test, una ejecución de inferencia/evaluación documentada u otra verificación corta sin entrenamiento
- El usuario ya sabe qué comando intentar y solo quiere ejecución más reporte

## Don't bother when

- Durante el escaneo inicial del repositorio o cuando el entorno/assets aún están indefinidos
- Cuando la tarea es una búsqueda bibliográfica y no una ejecución del repositorio
- Cuando el usuario aún está decidiendo qué objetivo de reproducción será el principal

## What triggers it

- "Ejecuta el smoke test documentado y guarda la evidencia en repro_outputs/"
- "Corre el comando de inferencia del README y normaliza los resultados"
- "Necesito el reporte de comparabilidad tras correr la evaluación documentada"

## Before you install

- Requiere que ya exista un objetivo de reproducción seleccionado y comandos ejecutables o de smoke test definidos.

## Files

- SKILL.md — 3 KB
- agents/openai.yaml — 313 B
- references/reporting-policy.md — 747 B
- scripts/run_command.py — 10 KB
- scripts/write_outputs.py — 811 B

## SKILL.md

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

# minimal-run-and-audit

Use this as the Rigor Run skill. The installed slug remains
`minimal-run-and-audit` for compatibility.

Use the shared operating principles in
`../../references/agent-operating-principles.md`; this skill should make run
evidence auditable without turning every command into a rigid protocol.

## When to apply

- After a reproduction target and setup plan exist.
- When the main skill needs execution evidence and normalized outputs.
- When a smoke test, documented inference run, documented evaluation run, or other short non-training verification is appropriate.
- When the user already knows what command should be attempted and wants execution plus reporting only.

## When not to apply

- During initial repo scanning.
- When environment or assets are still undefined enough to make execution meaningless.
- When the task is a literature lookup rather than repository execution.
- When the user is still deciding which reproduction target should count as the main run.

## Clear boundaries

- This skill owns normalized reporting for an attempted command.
- It may receive execution evidence from the main skill or a thin helper.
- It does not choose the overall target on its own.
- It does not perform broad paper analysis.
- It does not own training startup, resume, or long-running training state.
- It should not normalize risky code edits into acceptable practice.
- It must not hide changes that alter evaluation, preprocessing, checkpoints,
  metrics, or other scientific meaning.

## Input expectations

- selected reproduction goal
- runnable commands or smoke commands
- environment and asset assumptions
- optional patch metadata

## Output expectations

- execution result summary
- standardized `repro_outputs/` files
- `SCIENTIFIC_CHANGELOG.md` for changed scientific meaning and evidence status
- `COMPARABILITY_REPORT.md` for README/paper/baseline comparability
- clear distinction between verified, partial, and blocked states
- `PATCHES.md` when repo files changed

## Notes

Use `references/reporting-policy.md`, `../../references/research-rigor-principles.md`, `scripts/run_command.py`, and `scripts/write_outputs.py`.

---

Skills Agentes — https://skillsagentes.com/skills/lllllllama/rigorpilot-skills/minimal-run-and-audit