minimal-run-and-audit

lllllllama/rigorpilot-skills

Execute and audit deep learning repo smoke tests with standardized evidence capture and scientific changelog tracking.

What is minimal-run-and-audit?

Minimal-run-and-audit is a Rigor Run skill for README-first deep learning repository reproduction. Use it after a reproduction target and setup plan exist to execute documented smoke tests, inference runs, or evaluation commands and generate standardized repro_outputs/ files with patch notes and scientific comparability reports.

Executes selected smoke tests, inference runs, or evaluation commands with full evidence capture
Generates standardized repro_outputs/ directory structure with normalized execution results
Creates SCIENTIFIC_CHANGELOG.md documenting any changes that alter evaluation, preprocessing, or metrics
Produces COMPARABILITY_REPORT.md comparing against README, paper, and baseline specifications
Tracks PATCHES.md when repository files are modified during execution
Distinguishes between verified, partial, and blocked execution states

How to install minimal-run-and-audit

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

Prerequisites

Selected reproduction target and documented command to execute
Environment and asset assumptions already defined
Repository already cloned and initial setup completed

Claude Code

Cursor

Windsurf

Cline

How to use minimal-run-and-audit

1.Provide the selected reproduction goal and the exact command to run (smoke test, inference, or evaluation)
2.Specify any environment variables, asset paths, or assumptions needed for execution
3.Execute the command via the skill and capture all stdout, stderr, and output artifacts
4.Review generated repro_outputs/ files, SCIENTIFIC_CHANGELOG.md, and COMPARABILITY_REPORT.md
5.Verify that any repository file changes are documented in PATCHES.md with scientific impact notes

Use cases

Good for

Capturing evidence from a documented inference command after environment setup is complete
Running a smoke test to verify model evaluation pipeline matches paper specifications
Normalizing outputs from multiple inference runs into standardized repro_outputs/ format
Documenting and auditing any code changes made during reproduction with scientific impact assessment
Generating comparability reports to confirm reproduced results align with baseline claims

Who it's for

ML researchers reproducing deep learning papers
Research engineers validating model inference and evaluation pipelines
Teams conducting systematic repository audits and reproducibility assessments
Scientists needing standardized evidence capture for research rigor documentation

minimal-run-and-audit FAQ

Should I use this skill for training execution?

No. This skill is for smoke tests, inference runs, and evaluation commands only. Do not use it for training startup, resume, or long-running training state management.

What happens if the repository files change during execution?

The skill generates PATCHES.md documenting all changes and flags any modifications that alter scientific meaning (evaluation logic, preprocessing, metrics, checkpoints) in SCIENTIFIC_CHANGELOG.md.

When should I apply this skill?

Apply it after a reproduction target and setup plan exist and the user knows what command should be attempted. Do not use during initial repo scanning or when the environment is still undefined.

What is the difference between SCIENTIFIC_CHANGELOG.md and COMPARABILITY_REPORT.md?

SCIENTIFIC_CHANGELOG.md tracks changes that alter evaluation or preprocessing meaning and evidence status. COMPARABILITY_REPORT.md compares the reproduced results against README, paper, and baseline specifications.

Can this skill choose the reproduction target on its own?

No. The skill receives the selected reproduction goal and runnable commands as input. It does not choose the overall target or perform broad paper analysis.

Full instructions (SKILL.md)

Source of truth, from lllllllama/rigorpilot-skills.

name: minimal-run-and-audit description: Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.

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.