find-bugs

Analyze code changes to identify bugs, security vulnerabilities, and quality issues.

1|Updated Jan 17, 2026
One-click install
npx skills add https://github.com/kurokeita/ai-agent --skill find-bugs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: find-bugs
Source: https://github.com/kurokeita/ai-agent/tree/main/skills/find-bugs
Command: npx skills add https://github.com/kurokeita/ai-agent --skill find-bugs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Review branch changes to surface bugs, security vulnerabilities, and code quality issues before merging.

Core Features & Use Cases

  • Phase-driven analysis to detect bugs, security gaps, and quality issues in code changes.
  • Applies to pull requests and feature branches by enumerating changed files, inputs/params, authentication checks, state changes, external calls, and potential edge cases.
  • Generates actionable findings and recommended fixes for developers and reviewers.

Quick Start

Run the Find Bugs skill on your feature branch to audit changes and surface issues.

Frequently Asked Questions about find-bugs

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

FAQPage Schema
How do I find security vulnerabilities in a git diff before merging a pull request?

Security review for pull requests works by enumerating changed files to map inputs, queries, auth checks, state changes, and external calls. It identifies potential logic errors and outputs a structured report detailing findings and recommended fixes.

What is attack surface mapping in code changes?

Attack surface mapping in code changes involves analyzing modified files to trace inputs, parameters, external calls, and state changes. This identifies potential entry points for security vulnerabilities and logic bugs during a branch review.

How do I run a security review on a feature branch?

Run a security review on a feature branch by applying a phase-driven analysis to the code changes. This audits the modifications to surface bugs, security gaps, and quality issues, generating actionable findings and recommended fixes for developers.

Can I detect code quality issues and bugs in pull requests automatically?

Yes, you can detect code quality issues and bugs in pull requests by applying a five-phase analysis process to the changed files. This verifies state changes and edge cases to generate actionable findings and recommended fixes.

What is the best way to audit code changes for edge cases and logic errors?

The best way to audit code changes for edge cases and logic errors is using a structured five-phase process including input gathering, attack surface mapping, security checklist verification, and pre-conclusion auditing to map state changes and external calls.