analyze-project Skill for Claude: Read-Only Review of ML Repos

analyze-project makes your agent read a deep learning repo without changing it, and map its model, entrypoints and configs.

Installs: 345.2K; on skills.sh
Stars: 486; on GitHub
Files: 3; besides SKILL.md
Updated: Sep 2026; last repo commit

analyze-project is the read-only analysis skill in the RigorPilot set. It maps model structure, training and inference entrypoints and config relationships, suggests conservative insertion points, and flags suspicious patterns as heuristics, not confirmed bugs. It writes analysis_outputs/SUMMARY.md, RISKS.md and status.json.

It does not patch code. SKILL.md calls it read-mostly, says it may run lightweight static inspection helpers, and says not to use it to execute a failing command or debug a traceback. The folder bundles scripts/analyze_project.py. It reads shared files from ai-research-reproduction, so install the whole set.

Good for

Researchers who need to understand a paper repo before touching it
ML engineers who want likely insertion points and suspicious patterns flagged
Reviewers who want analysis only, with no code edits or heavy jobs

Install analyze-project

Claude Code

Copy this prompt.

Install the analyze-project skill in Claude Code. Run this command:

npx skills add lllllllama/RigorPilot-Skills --all

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js.

This skill reads shared guideline files from the ai-research-reproduction skill, so install the whole set rather than this folder alone. The README says the main reproduction skill works alone and that "all skills" is the choice for the companion and leaf skills.

From the project README. Source.

What's in the skill

When it loads

Rigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrypoints, review configs and insertion points, or flag suspicious implementation patterns without modifying code or running heavy jobs. Do not use for active command execution, broad refactoring, speculative code adaptation, or automatic bug fixing.

Sections in SKILL.md

When to apply
When not to apply
Clear boundaries
Output expectations
Notes

Key facts

Author: lllllllama (owner of the lllllllama/rigorpilot-skills repo)
License: MIT
Installs on skills.sh: 345,245 as of 2026-11-02
GitHub stars: 486 for the whole lllllllama/rigorpilot-skills repo
skills.sh audits: Gen Agent Trust Hub pass, Socket pass, Snyk pass
What is inside: 3 files besides SKILL.md (1 in agents/, 1 in references/, 1 in scripts/)
Needs: The other RigorPilot skills for shared reference files; Python for the bundled helper
Last commit to the repo: 2026-09-23

What it includes

Model structure, train and inference entrypoints, configs
Gives you a picture of how the repository fits together before you change anything.
Try: “Use analyze-project on this repo. Where is the model defined, and what do the train and eval entrypoints use?”
Files · Map the repo
Conservative places where a change could go
Offers likely spots without editing them.
Read · Suggest insertion points
Marks them as heuristics, not confirmed bugs
Uses the shared research pitfall checklist from ai-research-reproduction.
Read · Flag suspicious patterns
May run scripts/analyze_project.py
SKILL.md allows light static inspection but no heavy jobs or active command execution.
Runs code · Lightweight static helpers
SUMMARY.md, RISKS.md, status.json
The three files SKILL.md lists as output expectations.
Write · Write analysis_outputs/

From the official docs

Permissions

Low risk

It reads your repo and writes a report, and can run a bundled static helper script. Use it on repos you trust.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

It runs a bundled Python helper
SKILL.md allows lightweight static inspection helpers, and scripts/analyze_project.py is in the folder. Run it on repos you trust.
Findings are heuristics
SKILL.md says suspicious patterns are not confirmed bugs. Check them before acting.

Technical details

Scopes	Reads the repository May run a lightweight static helper script Writes analysis_outputs/ files

Questions

What does analyze-project do?

It reads a deep learning repository and tells you how it is built: model structure, entrypoints, configs and likely insertion points. It stays read-only and marks suspicious code as a heuristic.

How do I install it?

Use the install box at the top of this page, which installs the whole RigorPilot set. The skill reads shared files from ai-research-reproduction, so installing it alone is not enough. The README says the installer needs Node.js/npm and that skills@1.5.26 requires Node 22.20.0 or newer.

Does it need an API key?

No key is named in SKILL.md. It works inside your agent and its Python helpers run on your machine.

Can it change my code?

No. SKILL.md says it does not patch repository code, calls itself read-mostly and rules out heavy jobs. The outputs it lists are three files in analysis_outputs/.

analyze-project or safe-debug?

Use analyze-project to understand a repo with no active failure. Use safe-debug when you have a traceback or training failure and want a diagnosis first.

Is it safe?

It is meant for reading, and SKILL.md says it does not patch code, but it may run a bundled Python helper (scripts/analyze_project.py) on your machine. The README says RigorPilot is local execution, not an OS sandbox, so use repos you trust.

Information

updated Nov 2, 2026

Repository: lllllllama/rigorpilot-skills
Folder: skills/analyze-project

lllllllama/rigorpilot-skills skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 3

RigorPilot Skills README · github.com
analyze-project SKILL.md · github.com
skills.sh listing and audits · skills.sh