Minimal Run And Audit

When you've already identified what command to run in an AI research repo and just need clean execution evidence, this handles the boring parts. It runs your smoke test or documented inference command, captures the output, and writes standardized files to repro_outputs/ with proper success/failure classification. Also generates PATCHES.md when files get modified during execution. The narrow scope is intentional - it won't help you pick targets or set up environments, but it's reliable for the "just run it and document what happened" phase of reproduction work.

skills.sh installs: 139.8K
GitHub stars: 506
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add lllllllama/ai-paper-reproduction-skill --skill minimal-run-and-audit --agent claude-code

Installs into .claude/skills of the current project.

Files

minimal-run-and-audit

Use this as the Rigor Run skill. The installed slug remains minimal-run-and-audit for compatibility.

Use the shared operating principles in ../ai-research-reproduction/references/agent-operating-principles.md; this skill should make run evidence auditable without turning every command into a rigid protocol.

When to apply

After a reproduction target and setup plan exist.
When the main skill needs execution evidence and normalized outputs.
When a smoke test, documented inference run, documented evaluation run, or other short non-training verification is appropriate.
When the user already knows what command should be attempted and wants execution plus reporting only.

When not to apply

During initial repo scanning.
When environment or assets are still undefined enough to make execution meaningless.
When the task is a literature lookup rather than repository execution.
When the user is still deciding which reproduction target should count as the main run.