minimal-run-and-audit
๐ฏSkillfrom lllllllama/rigorpilot-skills
|A RigorPilot trusted-lane skill for conservatively running documented evaluation, inference, smoke tests, and sanity checks in deep learning repositories without introducing unaudited changes.
Overview
minimal-run-and-audit is a RigorPilot trusted-lane skill for conservatively running documented evaluation, inference, smoke tests, and sanity checks in deep learning repositories. It executes only the commands explicitly documented in the repository and produces auditable output bundles without introducing any unverified changes to the codebase or configuration.
Key Features
- Conservative execution: Runs only evaluation and inference commands that are explicitly documented in the repository README or related documentation, refusing to improvise or modify scripts.
- Smoke test support: Performs sanity checks and quick validation runs to verify that the environment and model are functioning correctly before longer training or evaluation sessions.
- Auditable output bundles: Generates structured results in
repro_outputs/that include command logs, metric outputs, and configuration state for full reproducibility auditing. - No silent changes: Strictly avoids modifying any code, configuration, or data files during execution, ensuring that the repository state remains identical before and after the run.
- Blocker surfacing: When documentation is ambiguous or commands fail, surfaces these issues as explicit blockers for researcher review rather than attempting workarounds.
Who is this for?
- Researchers verifying that a reproduction setup works correctly before committing to full training runs.
- Teams conducting systematic evaluations of published models who need strict adherence to documented evaluation procedures.
- AI agents in the RigorPilot workflow that need to execute bounded evaluation steps within the trusted lane.
Same repository
lllllllama/rigorpilot-skills(14 items)
Installation
npx vibeindex add lllllllama/rigorpilot-skills --skill minimal-run-and-auditnpx skills add lllllllama/rigorpilot-skills --skill minimal-run-and-audit~/.claude/skills/minimal-run-and-audit/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 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.