Minimal Run And Audit: Install, Source and Security | FunnelSlayer
FunnelSlayer
Book a call

Minimal Run And Audit

Published by lllllllama in rigorpilot-skills

Review recommended450k installsAutomation & Infrastructure

What this skill does

It helps an agent capture and normalize evidence from a short model smoke test, inference run, or evaluation command. It produces standardized reproduction reports that show results, changes, and whether they can be compared fairly. Best for Researchers and engineers documenting short verification runs in deep learning repository reproductions.

Add Minimal Run And Audit to your agent

Review the source and files first. When you are ready, copy the prompt instruction or use the CLI command supported by your environment.

Install with a prompt

Paste this into a compatible coding agent:

add this skill "minimal-run-and-audit" from https://github.com/lllllllama/rigorpilot-skills

Install with the CLI

Run this command in a controlled environment after reviewing the repository:

npx skills add https://github.com/lllllllama/rigorpilot-skills --skill minimal-run-and-audit

Skill instructions

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.

Clear boundaries

  • This skill owns normalized reporting for an attempted command.
  • It may receive execution evidence from the main skill or a thin helper.
  • It does not choose the overall target on its own.
  • It does not perform broad paper analysis.
  • It does not own training startup, resume, or long-running training state.
  • It should not normalize risky code edits into acceptable practice.
  • It must not hide changes that alter evaluation, preprocessing, checkpoints, metrics, or other scientific meaning.

Input expectations

  • selected reproduction goal
  • runnable commands or smoke commands
  • environment and asset assumptions
  • optional patch metadata

Output expectations

  • execution result summary
  • standardized repro_outputs/ files
  • SCIENTIFIC_CHANGELOG.md for changed scientific meaning and evidence status
  • COMPARABILITY_REPORT.md for README/paper/baseline comparability
  • clear distinction between verified, partial, and blocked states
  • PATCHES.md when repo files changed

Notes

Use references/reporting-policy.md, ../ai-research-reproduction/references/research-rigor-principles.md, scripts/run_command.py, and scripts/write_outputs.py.

Files included

  • agents/openai.yaml
  • references/reporting-policy.md
  • scripts/run_command.py
  • scripts/write_outputs.py
  • SKILL.md