jaw-drop-audit

Audit software repositories with evidence-based scoring across architecture, testing, and git discipline.

1|Updated Jan 13, 2026
One-click install
npx skills add https://github.com/jongensutrecht/demo-ai-stack --skill jaw-drop-audit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: jaw-drop-audit
Source: https://github.com/jongensutrecht/demo-ai-stack/tree/main/lars%20skills/jaw-drop-audit
Command: npx skills add https://github.com/jongensutrecht/demo-ai-stack --skill jaw-drop-audit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill delivers a brutally honest, evidence-based code and repository audit for engineers who need a top-tier craft judgment instead of a polite checklist.

Core Features & Use Cases

  • Deep Repository Critique: Evaluates architecture, structure, naming, error handling, testing, performance, security, DX, git discipline, and consistency.
  • AI Fingerprint Detection: Spots signs of boilerplate repetition, over-commenting, inconsistent abstraction levels, and other patterns that suggest generated or low-craft code.
  • Actionable Transformation Plan: Ends with a non-lazy route to 10/10 that explains what to change, why it matters, what not to do, and how to prove the work is done.
  • Use Case: Use it when you have a repo that looks functional but you want an expert-level verdict on whether it is genuinely impressive, maintainable, and worth showing to strong engineers.

Quick Start

Ask the skill to audit the repository you want reviewed and return the full Jaw Drop Audit with evidence, scores, AI fingerprint findings, and a 10/10 transformation plan.

Frequently Asked Questions about jaw-drop-audit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit a repository for code quality and architecture craftsmanship?

An evidence-based repository audit analyzes architecture, naming, resilience, testing, and git discipline. It scores each facet individually with path-specific proof to produce an expert-level verdict on maintainability and overall code craft.

What are AI fingerprints in generated code and how do I spot them?

AI fingerprints are patterns in generated code such as boilerplate repetition, over-commenting, and inconsistent abstraction levels. Spotting these low-craft patterns during a repository review helps identify sections lacking genuine engineering maintainability.

How do I review a codebase to see if it is maintainable for strong engineers?

Reviewing a codebase for strong engineers requires evaluating developer experience, consistency, and error handling. A deep craft analysis looks past functional code to judge whether the repository architecture is genuinely impressive and maintainable.

How do I create an actionable transformation plan for improving code quality?

Create an actionable transformation plan by defining what to change, why it matters, and what not to do. A non-lazy route to 10/10 quality requires specific moves with path-specific proof to verify the work is done.

Does a code audit evaluate git discipline and developer experience?

Yes, a comprehensive code audit evaluates git discipline and developer experience alongside architecture and testing. Scoring these facets ensures the repository meets top-tier craft standards for long-term maintainability and consistency.