repo-intake-and-plan
Assistant d'ingestion rigoureuse pour la reproduction de dépôts d'apprentissage profond en priorité README. À utiliser lorsque la tâche consiste spécifiquement à analyser un dépôt, lire le README et les fichiers de projet courants, extraire les commandes documentées, classer les candidats d'inférence, d'évaluation et d'entraînement, et renvoyer le plan de reproduction le plus fiable et minimal à l'orchestrateur principal. Ne pas utiliser pour la configuration d'environnement, le téléchargement de ressources, l'exécution de commandes, le rapport final, la recherche d'articles ou l'orchestration de bout en bout.
npx skills add https://github.com/lllllllama/rigorpilot-skills --skill repo-intake-and-planrepo-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/.