PluginBench
Skill
Pass
Audit score 90

repo-intake-and-plan

lllllllama/rigorpilot-skills

README-first repository scanner for deep learning reproduction planning.

What is repo-intake-and-plan?

Scans a repository structure, extracts documented commands from README and project files, and classifies them into inference, evaluation, and training candidates. Use this at the start of reproduction work to build a trustworthy plan without executing commands or setting up environments.

  • Scan repository structure and identify key project files
  • Extract documented commands from README and configuration files
  • Classify commands into inference, evaluation, training, and other categories
  • Generate a minimum trustworthy reproduction recommendation
  • Flag ambiguities and risks in the reproduction plan
  • Provide concise inventory of available documented commands

How to install repo-intake-and-plan

npx skills add https://github.com/lllllllama/rigorpilot-skills --skill repo-intake-and-plan
Claude Code
Cursor
Windsurf
Cline

How to use repo-intake-and-plan

  1. 1.Provide the target repository path to the skill
  2. 2.Optionally specify priority (e.g., inference-first, evaluation-first)
  3. 3.The skill scans README, setup files, and common project configuration files
  4. 4.Review the generated repo structure summary and command inventory
  5. 5.Examine the classified candidates and reproduction recommendation
  6. 6.Check the ambiguity and risk list before proceeding to execution

Use cases

Good for
  • Starting a deep learning paper reproduction by mapping the repository structure and available commands
  • Identifying which inference or evaluation commands are documented before attempting execution
  • Planning a reproduction strategy by classifying available commands by type
  • Assessing reproduction feasibility by detecting missing documentation or conflicting instructions
  • Handing off a structured plan to an orchestrator or execution skill
Who it's for
  • ML researchers reproducing published work
  • Automation orchestrators managing multi-step reproduction workflows
  • Engineers auditing repository documentation quality
  • Teams planning reproducibility workflows before execution

repo-intake-and-plan FAQ

What files does this skill read?

It reads README files and common project files like setup.py, requirements.txt, Makefile, config files, and documentation. It does not execute anything.

Does this skill install dependencies or download assets?

No. It only scans and plans. Environment setup and asset download are separate concerns.

What should I do with the output?

Pass the structured plan to an orchestrator or execution skill. The output is a map, not a runnable workflow.

Can I use this mid-reproduction after commands have already run?

This skill is designed for the intake phase. Once execution has started, use it only to re-plan if the repository structure changes.

What if the README is incomplete or missing?

The skill will flag ambiguities and risks. It will still scan available files and note what documentation is absent.

Full instructions (SKILL.md)

Source of truth, from lllllllama/rigorpilot-skills.


name: repo-intake-and-plan description: 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.

repo-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/.