analyze-project
๐ฏSkillfrom lllllllama/rigorpilot-skills
|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.
Overview
Analyze Project is a trusted-lane skill in the RigorPilot suite designed for read-only project analysis of deep learning repositories. It performs model mapping, structure inspection, and risk surfacing without making any edits to the codebase. This skill operates within RigorPilot's "trusted lane," meaning ambiguous requests default to safe, non-destructive operations that preserve scientific comparability.
Key Features
- Read-only analysis - Inspects the project structure, model architecture, and data pipeline without modifying any files, ensuring the research state remains untouched
- Model mapping - Maps out the neural network architectures, training configurations, and data flow within the repository
- Risk surfacing - Identifies potential issues such as missing dependencies, inconsistent configurations, or reproducibility gaps before you start running experiments
- Durable evidence bundles - Outputs structured results to
analysis_outputs/for later reference and comparison - Trusted-lane safety - Follows RigorPilot's principle that all actions stay in the safe, non-exploratory lane unless the researcher explicitly requests otherwise
Who is this for?
- Deep learning researchers who want to understand an unfamiliar repository's structure before attempting to reproduce or extend its results
- ML engineers onboarding onto a new research codebase who need a structured overview of models, training loops, and data pipelines
- Teams practicing rigorous AI research who need auditable, non-destructive analysis as part of their reproduction workflow
Same repository
lllllllama/rigorpilot-skills(14 items)
Installation
npx vibeindex add lllllllama/rigorpilot-skills --skill analyze-projectnpx skills add lllllllama/rigorpilot-skills --skill analyze-project~/.claude/skills/analyze-project/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 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 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.