# Repo Intake And Plan

> Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.

Source: https://skillsagentes.com/skills/lllllllama/rigorpilot-skills/repo-intake-and-plan
Repository: https://github.com/lllllllama/RigorPilot-Skills
Author: lllllllama
License: MIT
Updated: hace 19 días
Context cost: 116 tok installed, 531 tok once triggered, 4.3k tok with every bundled file
Bundle: 5 files, 17 KB
Permissions requested: none declared

## Install

```bash
npx -y skills add lllllllama/RigorPilot-Skills --skill repo-intake-and-plan --agent claude-code
```

## What it does

- Escanea la estructura de un repositorio y lee el README y archivos de proyecto comunes
- Extrae comandos documentados del repositorio
- Clasifica candidatos de inferencia, evaluación y entrenamiento de forma conservadora
- Devuelve al orquestador principal el plan de reproducción mínimo y confiable, junto con ambigüedades o riesgos

## Use it when

- Al inicio de un trabajo de reproducción basado en README
- Cuando el skill principal necesita un mapa rápido de la estructura del repo y sus comandos documentados
- Cuando hay que clasificar candidatos de inferencia, evaluación y entrenamiento con criterio conservador
- Cuando el usuario quiere inspeccionar el repo primero sin ejecutar nada todavía

## Don't bother when

- Cuando la ejecución ya empezó y la tarea es correr comandos o escribir salidas
- Cuando el objetivo no es una tarea de reproducción respaldada por un repositorio
- Cuando el usuario ya tiene un comando documentado seleccionado y solo necesita setup o ejecución

## What triggers it

- "Escanea este repo y dime qué comandos documentados tiene antes de ejecutar nada"
- "Necesito un mapa rápido de este repositorio y candidatos de inferencia/evaluación/entrenamiento"
- "Inspecciona el README y archivos del proyecto para armar un plan mínimo de reproducción"

## Before you install

- Requiere acceso a la ruta del repositorio objetivo y a su README y archivos de proyecto comunes.

## Files

- SKILL.md — 2 KB
- agents/openai.yaml — 368 B
- references/repo-scan-rules.md — 1 KB
- scripts/extract_commands.py — 10 KB
- scripts/scan_repo.py — 3 KB

## SKILL.md

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

# repo-intake-and-plan

Use this as the Rigor Intake helper. The installed slug remains
`repo-intake-and-plan` for compatibility.

## When to apply

- At the beginning of README-first reproduction work.
- When the main skill needs a fast map of repo structure and documented commands.
- When inference, evaluation, and training candidates must be classified conservatively.
- When the user explicitly wants to inspect the repo first and not run anything yet.

## When not to apply

- When execution has already started and the task is now about running commands or writing outputs.
- When the target is not a repository-backed reproduction task.
- When the user only wants paper interpretation without repo inspection.
- When the user already has a selected documented command and only needs setup or execution.

## Clear boundaries

- This skill scans and plans.
- This skill is helper-tier and should usually be orchestrator-invoked.
- It does not install environments.
- It does not prepare large assets.
- It does not execute substantive reproduction commands.
- It does not decide high-risk patching.

## Input expectations

- Target repository path.
- Access to README and common project files if present.
- Optional user hints about desired priority, such as inference-first.

## Output expectations

- concise repo structure summary
- documented command inventory
- inferred candidate categories: inference, evaluation, training, other
- minimum trustworthy reproduction recommendation
- notable ambiguity or risk list

## Notes

Use `references/repo-scan-rules.md` and helper scripts under `scripts/`.

---

Skills Agentes — https://skillsagentes.com/skills/lllllllama/rigorpilot-skills/repo-intake-and-plan