Analyze Project

When you clone a deep learning repo and need to understand what you're looking at before you break something, this is your read-only audit pass. It maps model architectures, training and inference entry points, config files, and flags suspicious patterns without touching code or spinning up expensive jobs. The scope discipline is the real value here: it won't try to fix bugs, refactor speculatively, or run your failing command, so you get orientation without scope creep. Outputs land in analysis_outputs as markdown summaries and a status JSON. Think of it as the mandatory reconnaissance step before you start adapting someone else's research code.

Install to Claude Code

npx -y skills add lllllllama/rigorpilot-skills --skill analyze-project --agent claude-code