review

Review code changes for quality, security, performance, and accessibility issues.

3.0k|300|Updated Dec 12, 2025
One-click install
npx skills add https://github.com/Chachamaru127/claude-code-harness --skill review-chachamaru127
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/Chachamaru127/claude-code-harness/tree/main/skills/review
Command: npx skills add https://github.com/Chachamaru127/claude-code-harness --skill review-chachamaru127

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates thorough code reviews across multiple critical dimensions—security, performance, quality, and accessibility—providing comprehensive feedback faster than manual review.

Core Features & Use Cases

  • Parallelized Review Agents: Can launch specialized sub-agents to simultaneously review code for security vulnerabilities, performance bottlenecks, code smells, and accessibility issues.
  • Structured Feedback & Scoring: Delivers actionable findings with severity ratings and concrete improvement suggestions, not just generic comments.
  • Use Case: Before merging a major feature, run /harness-review to trigger this Skill. It will spawn parallel reviews, aggregating results into a single report that highlights security risks, slow queries, and WCAG compliance issues you might have missed.

Quick Start

Say "review my changes for security" to perform a focused security audit on your latest code modifications.

Frequently Asked Questions about review

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

FAQPage Schema
How do I automate code reviews across security, performance, and accessibility?

Automate code reviews by running parallel specialized agents that simultaneously assess security vulnerabilities, performance bottlenecks, code quality issues, and accessibility compliance. This Skill aggregates findings from multiple dimensions into a single structured report with severity ratings and actionable recommendations.

Can I review code changes and pull requests across different programming languages and frameworks?

Yes, this Skill applies multi-criteria code review to code changes, diffs, and pull requests across front-end and back-end stacks in diverse languages and frameworks, delivering consistent assessment regardless of tech stack.

What does a structured code review output include?

Structured outputs include markdown reports and JSON summaries with actionable findings, severity ratings, and concrete improvement suggestions organized by review dimension—security, performance, quality, and accessibility.

How can I gate code merges using automated multi-perspective review?

Trigger parallel reviews before merging to spawn specialized sub-agents that assess security risks, performance bottlenecks, and compliance issues simultaneously, producing aggregated results that inform merge decisions.

Does this Skill support focused audits on specific code concerns?

Yes, you can perform focused reviews—such as security-only audits or accessibility checks—on your latest code modifications by specifying the review dimension you want to prioritize.