mcpField
M
minimal-run-and-audit

minimal-run-and-audit

github.com/lllllllamaTesting & quality486139.8k installsUpdated 5w ago
Repository

About minimal-run-and-audit

minimal-run-and-audit is the Rigor Run skill that produces normalized reports for an attempted command. It is intended for cases where the reproduction goal and setup plan already exist, and it records execution evidence while separating verified, partial and blocked states. It does not choose the reproduction target or manage training startup and long-running training state.

Key features

  1. 01Execution result summary for an attempted command
  2. 02Standardized repro_outputs/ files
  3. 03SCIENTIFIC_CHANGELOG.md for changes in scientific meaning
  4. 04COMPARABILITY_REPORT.md for README, paper and baseline comparability
  5. 05Distinction between verified, partial and blocked states

Use cases

  1. 01Recording results of smoke tests or documented inference and evaluation runs
  2. 02Documenting repository file changes in PATCHES.md
  3. 03Checking comparability between README, paper and baseline results

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/lllllllama/ai-paper-reproduction-skill --skill minimal-run-and-audit

After installing, type/minimal-run-and-auditin Claude Code to confirm it loaded.

Details

From the project README

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.

Comments

Markdown supported