code-reviewer

Analyze source code and produce severity-ranked review reports with metrics and auto-fix suggestions.

Updated Apr 10, 2026
One-click install
npx skills add https://github.com/Exia-thd/Digital-Nervous --skill code-reviewer-exia-thd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-reviewer
Source: https://github.com/Exia-thd/Digital-Nervous/tree/main/skills/code-reviewer
Command: npx skills add https://github.com/Exia-thd/Digital-Nervous --skill code-reviewer-exia-thd

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Code Reviewer skill provides a comprehensive, production‑grade quality gate that automatically evaluates a project's architecture, code quality, performance, and test coverage, identifying issues before deployment.

Core Features & Use Cases

  • Two‑stage review: verifies spec compliance before code quality analysis.
  • Parallel phases: architecture conformance, code quality, performance, and test quality reviews run concurrently.
  • Severity‑ranked findings: outputs critical, high, medium, and low issues with actionable recommendations.
  • Metrics & auto‑fixes: generates complexity, coverage, dependency metrics and suggested patch files.
  • Use case: run against any full‑stack repository to ensure it meets architectural decisions and release standards.

Quick Start

Invoke the code-reviewer skill to analyze the repository and generate a full review report.

Frequently Asked Questions about code-reviewer

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

FAQPage Schema
How do I automate code review for architecture and performance issues before deployment?

Automated code review analyzes source code to identify architectural, performance, quality, and testing issues before deployment. It runs parallel phases to evaluate conformance and generates severity-ranked findings with metrics without modifying source files.

What is a production release quality gate and how does it evaluate full-stack projects?

A production release quality gate automatically evaluates full-stack projects including backend services, libraries, and frontend components. It verifies spec compliance and runs concurrent reviews on architecture, code quality, performance, and test suites to produce structured reports.

Can I use automated code review to generate auto-fix suggestions without modifying source files?

Yes, automated code review generates suggested patch files and auto-fix recommendations without modifying source files. It outputs severity-ranked findings, complexity metrics, coverage metrics, and dependency metrics in a structured review report.

Does the code review process work with full-stack repositories containing frontend components and backend services?

The code review process applies to full-stack repositories with backend services, libraries, frontend components, and associated test suites. It evaluates the entire project against architectural decisions and release standards concurrently.

What is the best way to ensure a full-stack project meets architectural decisions and release standards?

The best way to ensure a project meets architectural decisions is running a two-stage review that verifies spec compliance before code quality analysis. Parallel phases evaluate architecture conformance, code quality, performance, and test quality concurrently.

How do I get severity-ranked findings and actionable recommendations from a code review?

To get severity-ranked findings, run an automated code review that outputs critical, high, medium, and low issues with actionable recommendations. The review also generates complexity, coverage, and dependency metrics alongside auto-fix suggestions.