Repo Intake and Plan Skill: Scan Before You Reproduce

Scans a research repo and README, lists the documented commands, and returns the smallest trustworthy reproduction plan.

Installs: 484.2K; on skills.sh
Stars: 486; on GitHub
Files: 4; besides SKILL.md
Updated: Sep 2026; last repo commit

repo-intake-and-plan is the first step of README-first deep learning reproduction. It reads the README and common project files, lists the documented commands, sorts them into inference, evaluation, training and other candidates, and recommends the smallest trustworthy run.

Use it at the start of reproduction work, or when you want to inspect a repo before running anything. It scans and plans only: it does not install environments, download assets, run substantive commands or decide high-risk patches. It bundles two Python helper scripts and a scan-rules reference.

Good for

Researchers about to reproduce a paper from its GitHub repo
ML engineers who want a plan before running anything
Users of the RigorPilot main skill

Install repo-intake-and-plan

Claude Code

Copy this prompt.

Install the repo-intake-and-plan 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 22.20+.

The README says the main skill, ai-research-reproduction, works alone, and to choose all skills for the companion entrypoints. The README lists this skill as one of two helpers that support orchestration, so install the set. The README tested the installer with skills@1.5.26 and Node 22.20.0, which it says is the minimum.

From the project README. Source.

What's in the skill

When it loads

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.

Sections in SKILL.md

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

Key facts

Author: lllllllama (RigorPilot-Skills)
Installs on skills.sh: 484,199 (Nov 2, 2026)
GitHub stars: 486 on lllllllama/rigorpilot-skills (Nov 2, 2026)
License: MIT
Last repo commit: Sep 23, 2026
What installs: SKILL.md plus 4 bundled files: agents/openai.yaml, references/repo-scan-rules.md, scripts/extract_commands.py, scripts/scan_repo.py
skills.sh audits: Gen Agent Trust Hub: pass, Socket: pass, Snyk: pass
Part of: RigorPilot-Skills; a helper-tier skill usually called by the main skill
Runs: scripts/scan_repo.py and scripts/extract_commands.py
Does not: Install environments, prepare large assets or execute substantive reproduction commands

What it includes

Reads the README and common project files
Produces a concise repo structure summary.
Runs code · Scan the repo
Builds an inventory of commands the README documents
Uses scripts/extract_commands.py.
Runs code · Extract documented commands
Sorts commands into inference, evaluation, training or other
Conservative: it recommends the minimum trustworthy reproduction.
Classify candidates
Returns notable ambiguity and risks
Handed back to the main orchestrator.
Flag ambiguity

From the official docs

Permissions

Low risk

It runs two bundled Python scripts that read the target repo, and SKILL.md says it does not execute reproduction commands.

What it can do

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

Watch out for

It runs two bundled Python scripts
The scan and command-extraction scripts run on the repo you point at. Read them once before first use.

Technical details

Scopes	Reads the target repository

Questions

What does repo-intake-and-plan do?

It scans a repo and its README, lists the documented commands, classifies inference, evaluation and training candidates, and returns the smallest trustworthy reproduction plan.

How do I install it?

Follow the install box at the top of the page. The README says to choose all skills for the companion entrypoints, so install the whole RigorPilot set.

Does it run the repo's code?

SKILL.md says it does not execute substantive reproduction commands, install environments or prepare large assets. It runs its own two scan scripts.

What comes after intake?

Setup with env-and-assets-bootstrap, then a run with minimal-run-and-audit, in the RigorPilot flow. The main skill, ai-research-reproduction, coordinates these.

Can I use it on its own?

Yes, when you only want to inspect a repo before running anything. SKILL.md lists that as a use case.

Is it safe?

It reads the repo and runs bundled scripts and nothing else is named in SKILL.md. Its skills.sh audits show pass from all three auditors.

Information

updated Nov 2, 2026

Repository: lllllllama/rigorpilot-skills
Folder: skills/repo-intake-and-plan

lllllllama/rigorpilot-skills skills.sh

Sources

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

Show all 3

RigorPilot-Skills README · github.com
repo-intake-and-plan SKILL.md · github.com
skills.sh listing · skills.sh