ai-research-reproduction
๐ฏSkillfrom lllllllama/rigorpilot-skills
|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.
Overview
AI Research Reproduction is the primary end-to-end orchestrator in the RigorPilot suite. It guides AI agents through README-first reproduction of deep learning repositories, ensuring that every step maintains scientific rigor, comparability, and auditable evidence. The skill follows a structured workflow: read the README, set up the environment, run the code, train models, and validate outputs against the paper's reported results.
Key Features
- README-first workflow - Starts by thoroughly reading the repository README and any associated paper to understand expected inputs, outputs, and reproduction steps before touching any code
- Environment setup automation - Handles dependency installation, dataset preparation, and configuration while documenting every step for reproducibility
- Training and validation pipeline - Runs training scripts and validates outputs against baseline metrics reported in the original paper
- Durable evidence bundles - Saves all reproduction outputs to
repro_outputs/with timestamps, configurations, and comparison data for audit trails - Trusted-lane defaults - Ambiguous instructions always resolve to the safe reproduction path, never silently drifting into exploratory modifications
Who is this for?
- Deep learning researchers reproducing published results who need a structured, auditable process from start to finish
- Graduate students and research assistants tasked with verifying paper claims through code reproduction
- ML teams establishing baselines for new projects by first reproducing the state-of-the-art results they plan to build upon
Same repository
lllllllama/rigorpilot-skills(14 items)
Installation
npx vibeindex add lllllllama/rigorpilot-skills --skill ai-research-reproductionnpx skills add lllllllama/rigorpilot-skills --skill ai-research-reproduction~/.claude/skills/ai-research-reproduction/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.
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 helper skill that scans deep learning repositories and extracts README commands to build an initial reproduction plan, typically invoked by the main reproduction orchestrator.
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.