review

Coordinate parallel code-review agents and output a combined Markdown report.

2|1|Updated Jan 27, 2026
One-click install
npx skills add https://github.com/lucidlabs-hq/lucidlabs-agent-kit --skill review-lucidlabs-hq
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/lucidlabs-hq/lucidlabs-agent-kit/tree/main/.claude/skills/review
Command: npx skills add https://github.com/lucidlabs-hq/lucidlabs-agent-kit --skill review-lucidlabs-hq

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinated code reviews are often slow when performed sequentially. This Skill orchestrates parallel review agents to examine a codebase for multiple concerns (security, performance, simplicity, and Next.js/React), delivering a single, structured report to speed up quality feedback.

Core Features & Use Cases

  • Parallel execution: runs four focused reviewers at the same time to accelerate feedback cycles.
  • Scoped and flexible: supports path-based reviews to focus on specific directories or files within a repository.
  • Consolidated reporting: merges findings from all reviewers into one report for triage and remediation planning.

Quick Start

Run a full code-review on the target repository to generate a consolidated report.

Frequently Asked Questions about review

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

FAQPage Schema
How do I run parallel code reviews for security and performance across a repository?

You can run parallel code reviews by orchestrating four focused agents that examine a codebase for security, performance, simplicity, and Next.js/React issues simultaneously, delivering a single consolidated Markdown report.

Can I target code reviews to specific directories or files instead of the entire codebase?

Yes, you can scope code reviews to specific directories or files using path-based targeting, allowing the parallel agents to focus their security, performance, and simplicity checks on targeted repository sections.

How does parallel code review work with multiple agents?

Parallel code review works by launching four distinct agent types configured via .claude/agents/ files at the same time, merging their individual security, performance, simplicity, and Next.js/React findings into one structured report.

Does this code review approach work with Next.js and React repositories?

Yes, the review process specifically applies to Next.js and React frontend repositories, with dedicated agents checking for framework-specific issues alongside general security, performance, and simplicity concerns.

What is the best way to consolidate code review findings for triage?

The best way to consolidate code review findings is to merge outputs from parallel security, performance, simplicity, and Next.js/React reviewers into a single structured Markdown report for efficient triage and remediation planning.