Code Review & Testing · IN-DEPTH PROFILE

minimal-run-and-audit

Minimal Run and Audit executes a selected smoke, inference, evaluation, or other short non-training verification for research code.

View listed source ↗Installation guide ↓
Best for

Researchers needing an auditable first run

What you get

Run a bounded verification + Capture audit artifacts

Main limitation

It does not choose the reproduction target, train a model, conduct broad paper analysis, or hide scientific-meaning changes.

First risk

Scientific changes hidden as setup fixes. Patches to data, checkpoints, precision, or evaluation can change the meaning of a result. Record every deviation, preserve the original command, and downgrade comparability when necessary.

EVIDENCE FRESHNESS

Three checks, kept separate

A recent source check is not a runtime test or security audit.

Upstream sourceChecked 2026-08-20

Pinned revision · 3ab50525

Open pinned commit ↗
SkillSignal profileSource-grounded

Updated 2026-08-20

Runtime & securityNot independently verified

Source review does not certify behavior or safety.

30-SECOND BRIEF

What it does—and when it fits

Minimal Run and Audit executes a selected smoke, inference, evaluation, or other short non-training verification for research code. It standardizes results under repro_outputs, records the execution outcome, scientific changes, comparability, and patches, and reports the run as verified, partial, or blocked rather than hiding deviations.

INSTALL BY AGENT

Choose your Agent

Paths come from official Agent docs or the universal installer behind skills.sh. Compatibility still follows this Skill's record.

Native

This Skill's current record explicitly names this Agent. Still inspect scripts, permissions, and external dependencies first.

Project scope.claude/skills/minimal-run-and-audit/
Personal scope~/.claude/skills/minimal-run-and-audit/

Use project scope for team sharing and personal scope across repositories. The installer defaults to project scope; add -g for personal scope.

Install command (project scope)npx skills add lllllllama/rigorpilot-skills --skill minimal-run-and-audit --agent claude-code
Official agent docs

Claude Code discovers custom Skill folders automatically at project or personal scope.

View path evidence ↗

TYPICAL WORKFLOW

A practical workflow

01

Run a bounded verification

Execute one already selected short command without expanding into training.

02

Capture audit artifacts

Persist results, commands, changes, comparability notes, and patches.

03

Report honest status

Distinguish verified evidence from partial or blocked execution.

THE TRADEOFFS

Advantages and tradeoffs

Notable strengths

  1. This profile is manually organized around the current upstream SKILL.md workflow.
  2. The capability boundary remains explicitly tied to lllllllama/rigorpilot-skills.
  3. Core uses, limitations, and risks are separated for pre-install review.

Limitations

  1. It does not choose the reproduction target, train a model, conduct broad paper analysis, or hide scientific-meaning changes.
  2. A successful short run does not establish full-paper reproduction, metric parity, or production reliability.

COMPARE THE TRADEOFF

Consider these close alternatives

These are deterministic nearby candidates, not paid placements or a universal ranking. Open the full profile before choosing.

01

Same job family · native to Claude Code + Codex

frontend-design

Design constraints that push generated interfaces beyond generic AI UI.
Tradeoff to check
Aesthetic judgments remain subjective and still need stakeholder review.
First risk
Style over function · Medium
Source state
Pinned · 0a64e398
Open profile ↗
02

Same job family · native to Codex + Claude Code

web-design-guidelines

Review interfaces against practical web design and accessibility rules.
Tradeoff to check
It depends on network access and a live guideline document whose contents can change over time.
First risk
Rule drift or context-free findings · Medium
Source state
Pinned · b8caa260
Open profile ↗
03

Same job family · native to Codex + Claude Code

grill-me

Relentless decision interviews for sharper plans and designs.
Tradeoff to check
A relentless interview can be tiring and disproportionate for small, reversible decisions.
First risk
Decision fatigue · Low
Source state
Pinned · 885e2ca4
Open profile ↗
Compare more in the directory →

BEST FIT

Who it is for

→

Researchers needing an auditable first run

→

Reviewers checking reproducibility evidence

BEFORE YOU USE IT

Risks to review before use

High

Scientific changes hidden as setup fixes

Patches to data, checkpoints, precision, or evaluation can change the meaning of a result. Record every deviation, preserve the original command, and downgrade comparability when necessary.

Medium

Upstream instruction drift

Behavior can change with upstream updates. Record the commit used for important workflows and review updates before adoption.

SECURITY

What the permission profile means

  • Declared access remains governed by the current upstream SKILL.md and runtime requests.
  • Treat repository files, web content, and tool output as untrusted input.
  • SkillSignal has not independently executed or security-audited this package; external skills.sh labels are not SkillSignal certification.

Not a security certification. External ratings are attributed references. SkillSignal has not independently executed or security-reviewed this Skill.

INSIDE THE PACKAGE

Indexed files

SKILL.mdUpstream Skill instructionsSource-linked

TAGS

experiment-runaudit-trailreproducibility

Manually expanded from the current upstream SKILL.md and linked source at lllllllama/rigorpilot-skills, checked 2026-08-20. This is an original summary, not an execution result or security certification.