bug-review

Audit codebases for AI-generated failure patterns and resilience gaps.

26|2|Updated Feb 12, 2026
One-click install
npx skills add https://github.com/sburl/CrossCheck --skill bug-review-sburl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bug-review
Source: https://github.com/sburl/CrossCheck/tree/main/codex/skills/bug-review
Command: npx skills add https://github.com/sburl/CrossCheck --skill bug-review-sburl

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Systematic auditing of code to surface AI-generated failure patterns, latent bugs, and maintainability gaps, enabling teams to ship reliable software.

Core Features & Use Cases

  • Comprehensive taxonomy covers AI-patterns, error handling, concurrency, state management, and testing gaps.
  • Reproduction-ready findings produce actionable remediation steps and optional reproduction workflows for critical issues.
  • Flexible auditing modes support full audits, quick audits, and focused deep-dives across diverse codebases and languages.

Quick Start

Run a full bug-review audit across your repository to surface AI-generated code issues.

Frequently Asked Questions about bug-review

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

FAQPage Schema
How do I audit AI-generated code for failure patterns and reliability gaps?

You can run a quick audit to rapidly scan your codebase for AI-patterns and error handling gaps, or execute a full audit to deeply analyze concurrency risks and state management issues across diverse languages.

What types of bugs does an AI code audit detect?

An AI code audit detects failure patterns using a comprehensive 10-category taxonomy that covers AI-patterns, error handling gaps, concurrency risks, state management issues, and testing gaps.

Can I reproduce critical bugs found during a code audit?

Yes, you can reproduce critical bugs found during a code audit by utilizing an optional reproduction workflow that generates actionable remediation steps and reproduction-ready findings.

Does the bug audit work with different programming languages and CI pipelines?

Yes, the bug audit works with different programming languages and CI pipelines, applying its structured taxonomy flexibly across diverse codebases to surface AI-patterns and maintainability debt.

When should I use a quick audit instead of a full code review?

Use a quick audit for rapid detection of AI-patterns and error handling gaps, and use a full audit when you need focused deep-dives into concurrency risks and state management across the entire repository.