rey-code-review for Openclaw

A comprehensive AI-driven code review agent providing multi-level analysis for quality, security, and architectural best practices.

sa9saq
v1.0.0
Feb 11, 2026
0
0
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install code-review-pro

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install code-review-pro using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is rey-code-review?

rey-code-review is a specialized AI agent skill designed to perform thorough code audits across multiple dimensions including security, maintainability, and correctness. It acts as an automated peer reviewer that can adapt its depth based on the size of the change, ranging from quick syntax checks to deep architectural deep-dives. As a key component of the Openclaw Skills ecosystem, it helps development teams maintain high standards and catch critical bugs before they reach production.

rey-code-review Use Cases

  • Performing rapid syntax and type-checking on small commits.
  • Conducting standard logic and error-handling reviews for feature pull requests.
  • Executing deep architectural and security audits for mission-critical system changes.
  • Automating the detection of performance bottlenecks like N+1 queries and memory leaks.
  • Ensuring consistent adherence to team-specific coding conventions and best practices.

How rey-code-review Works

  1. The user triggers the review by specifying the depth level: Quick, Standard, or Full.
  2. The skill analyzes the target files to identify immediate issues such as syntax errors or unused variables.
  3. It performs a semantic analysis of the code logic to ensure correctness and proper edge-case handling.
  4. The agent evaluates the code against specialized viewpoints including security vulnerabilities and performance impacts.
  5. A structured report is generated, categorizing findings by severity (Critical, Major, Minor, Nit) and providing specific code suggestions.
  6. The skill provides a final verdict (Approved, Needs Changes, or Blocked) to guide the development workflow.

rey-code-review Setup

To integrate this skill into your environment, use the following commands:

# Install the code review skill
openclaw install rey-code-review

# Run a standard review on your current changes
openclaw run rey-code-review "Review this code"

rey-code-review Data Schema & Taxonomy

The skill produces a structured JSON or Markdown report with the following data points:

Field Description
Summary A count of files reviewed and a breakdown of issues by severity level.
Verdict The final assessment: APPROVED, NEEDS_CHANGES, or BLOCKED.
Findings A detailed list including file path, line number, issue description, and suggested fix.
Positive A section highlighting well-implemented logic or clean code patterns.
Metadata Information on the review level used and time taken.

rey-code-review Advanced Features

  • Scalable Review Tiers: Choose between Quick (30s), Standard (2-5m), and Full (10-20m) review depths.
  • Cross-Skill Integration: Works seamlessly with other Openclaw Skills such as security-review and systematic-debug.
  • Severity-Based Filtering: Automatically prioritizes critical security risks and data loss vulnerabilities.
  • Context-Aware Suggestions: Provides actual code snippets for suggested improvements rather than just vague descriptions.
  • Architectural Fit Analysis: Evaluates how new code aligns with existing system patterns during Full Reviews.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*