Analyze Project

When you need to understand a deep learning repository before touching anything, this is your read-only audit pass. It maps model structure, training and inference entrypoints, config relationships, and flags suspicious patterns without patching code or running heavy jobs. Think of it as reconnaissance before reproduction. The boundaries are clear: it won't debug tracebacks, set up environments, or speculatively refactor. You get structured markdown summaries of what's where, what looks risky, and where you'd likely need to hook in changes. Good for the moment when you clone an unfamiliar repo and need to know what you're actually looking at before committing to a reproduction attempt.

skills.sh installs: 240
GitHub stars: 289
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add lllllllama/ai-paper-reproduction-skill --skill analyze-project --agent claude-code

Installs into .claude/skills of the current project.

Files

analyze-project

Use this as the Rigor Analyze / Rigor Audit read-only skill. The installed slug remains analyze-project for compatibility.

Use the shared operating principles in ../ai-research-reproduction/references/agent-operating-principles.md; this skill should guide read-only analysis without constraining the model's project-specific reasoning.

When to apply

The user wants to understand a deep learning repository before changing it.
The user needs a map of model structure, training entrypoints, inference entrypoints, and config relationships.
The user wants conservative suggestions about likely insertion points or suspicious implementation patterns.
The user explicitly wants read-only analysis and not heavy execution.