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's README and project files to extract documented commands and classify reproduction candidates (inference, evaluation, training). Use at the start of reproduction work to build a trustworthy plan without executing commands or setting up environments.
- Scans repository structure and reads README and common project files
- Extracts and inventories documented commands from documentation
- Classifies commands into inference, evaluation, training, and other categories
- Generates a minimum trustworthy reproduction recommendation
- Identifies ambiguities and risks in the reproduction plan
How to install repo-intake-and-plan
npx skills add https://github.com/lllllllama/rigorpilot-skills --skill repo-intake-and-planHow to use repo-intake-and-plan
- 1.Provide the target repository path to the skill
- 2.Optionally specify priority (e.g., inference-first, evaluation-first)
- 3.The skill scans the README and common project files (requirements.txt, setup.py, Makefile, etc.)
- 4.Review the returned repo structure summary and command inventory
- 5.Examine the classified candidates and minimum reproduction recommendation
- 6.Check the ambiguity and risk list before proceeding to execution
Use cases
- Starting a deep learning paper reproduction by mapping available commands before execution
- Planning which reproduction step (inference, evaluation, or training) to attempt first based on documented procedures
- Assessing repository readiness and identifying missing documentation before committing to reproduction
- Comparing multiple candidate commands for the same task to select the most reliable option
- Documenting reproduction prerequisites and dependencies from README without running setup
- ML researchers planning paper reproductions
- Reproducibility engineers auditing deep learning repositories
- AI agents orchestrating multi-step reproduction workflows
- Teams evaluating repository quality before reproduction investment
repo-intake-and-plan FAQ
No. This skill only scans, extracts, and plans. Use a separate execution skill for running commands.
No. It identifies what setup and assets are needed based on documentation, but does not perform those tasks.
The skill will scan available project files (setup.py, Makefile, config files) and flag ambiguities and risks in its output.
No. This skill is designed specifically for README-first deep learning repository reproduction planning.
It classifies commands based on keywords and context in the documentation, then flags ambiguous cases in the risk list for human review.
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/.
Related skills
More from lllllllama/rigorpilot-skills and the wider catalog.
run-train
Execute and document deep learning training runs with standardized evidence capture for reproducibility.
safe-debug
Conservative diagnosis and minimal patching for deep learning training failures and errors.
ai-paper-reproduction
Agent skill from lllllllama/rigorpilot-skills.
ai-research-explore
Structured exploration of deep learning research candidates with scientific rigor, fair comparison, and auditable experiments.
drizzle
Drizzle ORM schema and query patterns for PostgreSQL databases in LobeChat.
hotkey
Add or edit LobeHub keyboard shortcuts with proper scoping, conflict detection, and i18n support.