repo-intake-and-plan
๐ฏSkillfrom lllllllama/rigorpilot-skills
|A RigorPilot helper skill that scans deep learning repositories and extracts README commands to build an initial reproduction plan, typically invoked by the main reproduction orchestrator.
Overview
repo-intake-and-plan is a RigorPilot helper skill that scans deep learning repositories to extract README commands and build an initial reproduction plan. It serves as the intake step in the RigorPilot workflow, typically invoked by the main ai-research-reproduction orchestrator rather than used as a standalone entry point.
Key Features
- Repository scanning: Automatically parses the target repository structure, identifying README files, setup instructions, training commands, and evaluation scripts.
- Command extraction: Pulls documented commands from README and related documentation files, organizing them into a structured reproduction plan.
- Plan generation: Creates an ordered execution plan that covers environment setup, data preparation, training, and evaluation steps as documented in the repository.
- Orchestrator integration: Designed to be called by the ai-research-reproduction orchestrator, feeding its output into subsequent trusted-lane skills like env-and-assets-bootstrap and minimal-run-and-audit.
- Cross-platform support: Works on both Windows PowerShell and Linux shells, using shell-neutral command formatting.
Who is this for?
- Researchers starting a reproduction workflow who need an automated first pass at understanding a deep learning repository's setup and execution steps.
- Teams using the full RigorPilot skill suite who rely on structured intake before executing reproduction pipelines.
- AI agents operating within the RigorPilot framework that need a systematic way to parse repository documentation into actionable plans.
Same repository
lllllllama/rigorpilot-skills(14 items)
Installation
npx vibeindex add lllllllama/rigorpilot-skills --skill repo-intake-and-plannpx skills add lllllllama/rigorpilot-skills --skill repo-intake-and-plan~/.claude/skills/repo-intake-and-plan/SKILL.mdSKILL.md
More from this repository10
The primary explore-lane orchestrator in the RigorPilot suite that enables meaningful and potentially novel exploration on top of current deep learning research, with idea gating, bounded experiments, and candidate ranking.
The primary end-to-end orchestrator in the RigorPilot suite that guides AI agents through README-first reproduction of deep learning repositories, ensuring scientific rigor, comparability, and auditable outputs.
A RigorPilot explore-lane skill for candidate implementation, code transplanting, and stitching on isolated branches when the researcher has explicitly authorized exploratory work on top of current research.
A helper skill in the RigorPilot suite that resolves gaps between a deep learning repository's README and its associated research paper, helping agents understand the paper context needed for faithful reproduction.
A RigorPilot trusted-lane skill for research-safe debugging of deep learning experiments that analyzes failures first and applies patches only after explicit approval, preserving scientific comparability.
A RigorPilot trusted-lane skill that performs read-only project analysis on deep learning repositories, including model mapping, structure inspection, and risk surfacing, without making any edits.
A RigorPilot trusted-lane skill for conservatively starting or verifying deep learning training runs, including resume handling, bounded monitoring, and generating durable training records.
A RigorPilot trusted-lane skill for conservatively setting up deep learning environments, including datasets, pretrained weights, checkpoints, and cache assumptions required for research reproduction.
A RigorPilot explore-lane skill for running small-subset probes, short-cycle trials, and ranked exploratory experiments when the researcher explicitly authorizes candidate-only exploration.
A RigorPilot trusted-lane skill for conservatively running documented evaluation, inference, smoke tests, and sanity checks in deep learning repositories without introducing unaudited changes.