mcpField
M
minimal-run-and-audit

minimal-run-and-audit

github.com/lllllllamaTesting & quality486478.9k installsUpdated 5w ago
Repository

About minimal-run-and-audit

Rigor Run is a skill for AI research reproduction that produces normalized reports for attempted commands so run evidence can be audited. It is intended for smoke tests, documented inference or evaluation runs, and other short non-training checks, and it separates verified, partial, and blocked states.

Key features

  1. 01Execution result summary
  2. 02Standardized repro_outputs/ files
  3. 03SCIENTIFIC_CHANGELOG.md for scientific changes
  4. 04COMPARABILITY_REPORT.md for baseline comparability
  5. 05Verified, partial, and blocked state distinction

Use cases

  1. 01Reporting a smoke test or documented inference run in normalized form
  2. 02Recording changes that affect evaluation or metric meaning with evidence status
  3. 03Comparing reproduction results against README and paper baselines

Install

Copy the command and run it in a terminal.

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

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

Bundled files

References and scripts installed along with SKILL.md.

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

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