PluginBench
Skill
Review
Audit score 70

minimal-run-and-audit

lllllllama/rigorpilot-skills

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

SourceView on skills.sh

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 full audit trails and patch notes.

  • Execute selected smoke tests, inference runs, or evaluation commands with full evidence capture
  • Generate standardized repro_outputs/ files with execution results and normalized outputs
  • Create SCIENTIFIC_CHANGELOG.md documenting changes to evaluation, preprocessing, checkpoints, or metrics
  • Produce COMPARABILITY_REPORT.md assessing README/paper/baseline alignment
  • Track repository file changes in PATCHES.md with clear scientific impact distinction
  • Distinguish 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 setup plan already defined
  • Runnable commands or smoke commands identified
  • Environment and asset assumptions documented
Claude Code
Cursor
Windsurf
Cline

How to use minimal-run-and-audit

  1. 1.Provide the selected reproduction goal and the specific command to execute
  2. 2.Specify environment and asset assumptions for the run
  3. 3.Execute the command using the skill's execution framework
  4. 4.Review generated repro_outputs/ files and audit reports
  5. 5.Check SCIENTIFIC_CHANGELOG.md for any changes affecting evaluation or metrics
  6. 6.Verify COMPARABILITY_REPORT.md for alignment with README and paper claims
  7. 7.Review PATCHES.md if repository files were modified during execution

Use cases

Good for
  • Running a documented inference command on a pre-trained model and capturing outputs for reproducibility verification
  • Executing a smoke test suite after environment setup to validate repo functionality without full training
  • Auditing evaluation runs against baseline metrics and documenting any deviations or code changes
  • Normalizing execution evidence from multiple runs into standardized reports for comparison
  • Capturing inference outputs with patch notes when repository files were modified during execution
Who it's for
  • ML researchers validating deep learning repository reproducibility
  • Research engineers executing and auditing smoke tests and evaluation runs
  • Teams documenting evidence for paper reproducibility claims
  • Scientists needing standardized audit trails for computational experiments

minimal-run-and-audit FAQ

When should I use this skill vs. other reproduction skills?

Use minimal-run-and-audit after you have already selected a specific reproduction target and setup plan. It handles execution and evidence capture only—not target selection, environment setup, or training orchestration.

What happens if repository files change during execution?

The skill tracks all file changes in PATCHES.md and documents their scientific impact in SCIENTIFIC_CHANGELOG.md. Changes affecting evaluation, preprocessing, checkpoints, or metrics are flagged and not hidden.

Can this skill run training jobs?

No. This skill is designed for smoke tests, inference runs, and evaluation commands—not for training execution or long-running training state management.

What output files does this skill generate?

It generates standardized repro_outputs/ files, SCIENTIFIC_CHANGELOG.md (for scientific meaning changes), COMPARABILITY_REPORT.md (for README/paper alignment), and PATCHES.md (if files changed).

What if the command fails or produces partial results?

The skill clearly distinguishes between verified, partial, and blocked execution states in its reports, allowing you to assess what succeeded and what needs further investigation.

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 ../../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, ../../references/research-rigor-principles.md, scripts/run_command.py, and scripts/write_outputs.py.

Related skills

More from lllllllama/rigorpilot-skills and the wider catalog.

AN

analyze-project

lllllllama/rigorpilot-skills

Read-only analysis of deep learning repositories to understand structure, configs, and suspicious patterns.

84k installsAudited
AI

ai-research-explore

lllllllama/rigorpilot-skills

Auditable deep learning research exploration with idea gating, fair comparison, and governed experiments.

84k installs
EX

explore-code

lllllllama/rigorpilot-skills

Auditable exploratory code modifications for deep learning research on isolated branches with rollback tracking.

84k installs
AI

ai-research-reproduction

lllllllama/rigorpilot-skills

README-first deep learning repository reproduction with auditable evidence and standardized outputs.

84k installsAudited
PA

paper-context-resolver

lllllllama/rigorpilot-skills

Resolve reproduction-critical paper details when README and repo files leave gaps.

84k installs
SA

safe-debug

lllllllama/rigorpilot-skills

Conservative diagnosis and minimal patching for deep learning training failures without automatic code mutation.

84k installsAudited