Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

minimal-run-and-audit — Claude Code skill: how to install

Captures and normalizes execution evidence from deep learning smoke tests and inference commands into standardized repro_outputs/ files.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add lllllllama/RigorPilot-Skills --skill minimal-run-and-audit -a claude-code
Open on GitHub

What minimal-run-and-audit does

The skill targets README-first deep learning reproduction. It runs documented inference, evaluation commands, or short smoke tests, then standardizes run evidence. Under the hood, execution relies on scripts/run_command.py and scripts/write_outputs.py along with predefined reporting policies.

Outputs land in the repro_outputs/ directory. The skill creates COMPARABILITY_REPORT.md to check consistency against paper baselines, SCIENTIFIC_CHANGELOG.md for methodology shifts, and PATCHES.md whenever repository code changes. Runs are explicitly tagged as verified, partial, or blocked.

Attempting execution before assets and environments are prepared produces worthless audit artifacts. The skill expects a chosen reproduction target upfront; it does not select benchmarks, scan papers, or manage training loops.

What it helps with

  • audit deep learning inference commands against README instructions
  • generate COMPARABILITY_REPORT.md to cross-check paper baselines
  • record repository code modifications in PATCHES.md
  • track changes in preprocessing or metrics inside SCIENTIFIC_CHANGELOG.md

Example prompts for the agent

  • Run the README inference command with minimal-run-and-audit and log outputs to repro_outputs/
  • Execute the evaluation smoke test and document repository diffs in PATCHES.md

How to install minimal-run-and-audit

1Skills CLI (Vercel)

npx skills add lllllllama/RigorPilot-Skills --skill minimal-run-and-audit -a claude-code

2Manually: put the files in place

~/.claude/skills/minimal-run-and-audit/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/minimal-run-and-audit/

From the same set9

The whole set →
repo-intake-and-plan lllllllama Scans a repository through its README and project files, then builds a small reproduction plan. Use it before running experiments. Claude Code CX Codex Cursor +1 474,500installs env-and-assets-bootstrap lllllllama Prepares environment and checkpoint/dataset paths before the first run of a README-documented repo. Claude Code CX Codex Cursor +1 474,300installs ai-research-explore lllllllama Governs deep learning research exploration on top of an existing baseline. It isolates candidate experiments and generates structured comparison reports. Claude Code CX Codex Cursor +1 335,600installs analyze-project lllllllama Reads a deep learning repository and maps its structure, entrypoints and suspicious spots. Changes nothing, runs no heavy jobs. Claude Code CX Codex Cursor +1 335,500installs ai-research-reproduction lllllllama This skill guides a repository-grounded reproduction run from its README to an evidence bundle. Use it to test a documented model run without quietly changing the experiment. Claude Code CX Codex Cursor +1 335,300installs explore-code lllllllama A skill for cautious code experiments in deep learning repositories: it transplants modules and adapts architectures on an isolated branch, with rollback-aware records. Claude Code CX Codex Cursor +1 335,000installs explore-run lllllllama Plans bounded exploratory machine learning runs with comparability caveats and saves summaries to explore_outputs. Claude Code CX Codex Cursor +1 334,700installs run-train lllllllama Runs a selected training command and organizes the resulting evidence. Use it for startup checks, short-run verification, full training kickoff, or resume handling. Claude Code CX Codex Cursor +1 334,700installs

Similar

prd official github Turns a feature idea into a structured PRD with user stories, technical requirements, and risks. Use it when planning a software feature or an AI-powered one. GitHub Copilot 24,035installs nature-shared Yuan1z0825 A support package for the Nature Skills set. It holds shared definitions and journal formats that other skills load on demand, and never runs on its own. Claude Code CX Codex Cursor +1 13,100installs video-editing affaan-m AI-assisted workflow for editing, trimming, and enriching real footage. Connects raw recordings with FFmpeg cuts, Remotion overlays, and ElevenLabs voiceovers. Claude Code CX Codex Cursor +1 6,500installs gemini-api official google Connects Gemini API from Google Cloud Agent Platform to the agent. Gives access to Gemini models, multimodal input, function calling, and context caching. Claude Code Gemini CLI CX Codex 17,116installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. Claude Code 466,719installs media-use heygen-com Finds or generates media for HyperFrames videos, including voiceovers, music, cutouts, and color grades. Stores files locally in assets. Claude Code CX Codex Cursor +1 1,100,000installs mcp-builder official anthropics This skill walks through building an MCP server in TypeScript or Python, from reading the protocol spec to writing tests and evaluation questions. Claude Code Claude.ai 130,949installs

Questions about minimal-run-and-audit

How to install minimal-run-and-audit in Claude Code?

Run npx skills add lllllllama/RigorPilot-Skills --skill minimal-run-and-audit -a claude-code.

What does minimal-run-and-audit do?

It executes selected smoke tests or inference commands in machine learning repositories. It then formats audit logs, patch notes, and comparability reports inside repro_outputs/.

Can minimal-run-and-audit manage model training?

No, it intentionally excludes training startup and long-running state management. It focuses strictly on short evaluation runs, inference tests, and verifiable reporting.

Source text

SKILL.md · MIT 
---
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`.

© lllllllama · MIT · lllllllama/RigorPilot-Skills

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor