Skills lllllllama/rigorpilot-skills RigorPilot
minimal-run-and-audit
- Use it when
- setup is done and you want a short documented run, such as a smoke test, inference or evaluation, with its evidence on record
- It does
- runs that one command, or takes output already captured, and writes standard report files about it
- You get
- a repro_outputs folder: summary, commands, log and status, plus notes on what changed and how comparable the result is
- Not for
- training runs, choosing what to reproduce, or setting up the environment
- Usually called by
- RigorPilot's main skill, which reproduces a research repo from its README, which picks the command to run
Skill 4 of 5 in the RigorPilot bundle · Before it: env-and-assets-bootstrap · After it: ai-research-explore
Only works inside its bundle: Its run and report scripts load a shared runtime that ships inside ai-research-reproduction, the repo's main skill, and stop with an error without it. Install RigorPilot instead.
TLDR
The evidence step in RigorPilot, a set of skills that reproduces deep-learning research code by following its README. A run that passes shows the chosen command works, not that the paper's numbers were reproduced, and the reports keep that distinction. Each one states whether the run was full, partial, only a quick check, or blocked, names the documented command, separates facts from inferences and puts the main blocker up front. Two files guard what the result means: a scientific changelog lists anything that changed it, such as a different preprocessing step or checkpoint, and a comparability report says how far it can be compared with the README, the paper or a baseline. If repo files were edited to make the run work, PATCHES.md lists them, and no change to evaluation, preprocessing, checkpoints or metrics may be hidden.
Summarizes the skill at fb3ccdf.
npx skills add https://github.com/lllllllama/rigorpilot-skills --skill minimal-run-and-auditskills.sh page · Source on GitHub · All skills from lllllllama/rigorpilot-skills
- Installs
- 450,051 on skills.sh, Sep 21, 2026
- Repo stars
- 492 lllllllama/rigorpilot-skills
- First seen
- Mar 30, 2026 on skills.sh
Weekly values
| Week to | Installs |
|---|---|
| Aug 3 | 11,172 |
| Aug 10 | 32,229 |
| Aug 17 | 50,250 |
| Aug 24 | 41,213 |
| Aug 31 | 41 |
| Sep 7 | 41 |
| Sep 14 | 32 |
| Sep 21 | 30 |
| Category |
Research reproduction, financial data, charts and diagrams. |
|---|---|
| Type |
A multi-step process the agent follows: interview, debug, run a TDD loop, review. |
| Effect |
Its own steps create or change files, git state or local tools. |
| Needs |
Instructions only. Works in any agent that supports skills. |
| Publisher |
Everyone else. Unverified vendor claims default to community. |
| Topics | |
| Stack |
SKILL.md
From lllllllama/rigorpilot-skills at fb3ccdf. Checked daily, last changed Oct 20, 2026.
Frontmatter
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.mdfor changed scientific meaning and evidence statusCOMPARABILITY_REPORT.mdfor README/paper/baseline comparability- clear distinction between verified, partial, and blocked states
PATCHES.mdwhen 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.