review

Review code changes and validate root cause analysis for pull requests.

4|Updated Feb 2, 2026
One-click install
npx skills add https://github.com/brave-experiments/brave-core-bot --skill review-brave-experiments
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/brave-experiments/brave-core-bot/tree/main/.claude/skills/review
Command: npx skills add https://github.com/brave-experiments/brave-core-bot --skill review-brave-experiments

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a comprehensive analysis of code changes, assessing quality, identifying root causes of issues, and evaluating the confidence in proposed fixes, whether for pull requests or local development.

Core Features & Use Cases

  • Code Quality Assessment: Evaluates code against best practices and identifies potential issues.
  • Root Cause Analysis Validation: Verifies the thoroughness and accuracy of explanations for bugs or test failures.
  • Fix Confidence Scoring: Rates the likelihood that a proposed solution will be effective and not introduce regressions.
  • Use Case: Before submitting a pull request, use this Skill to get an expert-level review of your changes, ensuring they meet quality standards and effectively address the underlying problem.

Quick Start

Run /review local to analyze your current uncommitted code changes.

Frequently Asked Questions about review

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

FAQPage Schema
How do I perform an automated code review on my local changes?

Automated code review on local changes is performed by running the review command, which analyzes uncommitted modifications to assess code quality, validate root cause analysis, and evaluate fix confidence before submission.

What is root cause analysis validation in a pull request review?

Root cause analysis validation verifies the thoroughness and accuracy of explanations for bugs or test failures during a pull request review, ensuring the underlying problem is correctly identified rather than just treating symptoms.

Do I need GitHub CLI and Git to analyze pull request quality and fix confidence?

Yes, GitHub CLI and Git are required dependencies to analyze pull request quality and fix confidence, as the review process uses specific scripting for data filtering and upstream flake analysis.

Can I evaluate fix confidence to prevent regressions before submitting a pull request?

Yes, you can evaluate fix confidence before submitting a pull request to rate the likelihood that a proposed solution will be effective and ensure it differentiates from previous fix attempts to prevent regressions.

What is the best way to assess code quality against best practices during development?

The best way to assess code quality against best practices is to use an expert-level review tool that evaluates changes, identifies potential issues, and scores fix confidence for both local development and pull requests.

Why does my code review need to differentiate from previous fix attempts?

Differentiating from previous fix attempts during code review ensures that the current solution actually addresses the root cause rather than repeating ineffective patches, which is critical for maintaining code quality and preventing regressions.