review-branch

Review feature branch code differences against base branches for bugs and security issues.

2|Updated Apr 28, 2025
One-click install
npx skills add https://github.com/gunubin/dotfiles --skill review-branch-gunubin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review-branch
Source: https://github.com/gunubin/dotfiles/tree/main/claude/.claude/skills/review-branch
Command: npx skills add https://github.com/gunubin/dotfiles --skill review-branch-gunubin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of reviewing code changes on a branch before creating a Pull Request, ensuring higher code quality and catching potential issues early.

Core Features & Use Cases

  • Parallel Agent Review: Utilizes five specialized AI agents to analyze code changes from different perspectives (rules, bugs, security, etc.).
  • Confidence Scoring: Assigns a score to each identified issue, allowing for filtering of false positives and prioritization of critical findings.
  • Use Case: Before submitting a feature branch for review, run this Skill to get a comprehensive AI-driven code quality report, reducing the burden on human reviewers and improving the overall codebase.

Quick Start

Run a parallel AI code review on the current branch against the main branch.

Frequently Asked Questions about review-branch

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

FAQPage Schema
How do I automate code review on a Git branch before creating a pull request?

Identify bugs and security vulnerabilities in uncommitted code by running a comprehensive AI branch review that analyzes code differences against the main branch using specialized agents for security, bugs, and rule violations.

How does confidence scoring work for AI-generated code review findings?

Deploy specialized AI agents in parallel to analyze feature branch code differences, with each agent focusing on specific quality dimensions like security, bugs, and regressions to ensure high-quality code before submission.

Do I need specific tools to run an AI-powered branch review?

Compare feature branch code against a base branch by utilizing AI agents that analyze git diffs to detect regressions, rule violations, and security vulnerabilities, reducing the burden on human reviewers before pull request creation.

What's the best way to reduce false positives in automated code analysis?

Run this Skill before submitting a feature branch for review to get a comprehensive AI-driven code quality report, reducing the burden on human reviewers and improving the overall codebase through early issue detection.