code-reviewer

Review code changes, pull requests, and codebases for correctness, maintainability, security, and architecture issues.

12|Updated Feb 28, 2026
One-click install
npx skills add https://github.com/specd-sdd/SpecD --skill code-reviewer-specd-sdd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-reviewer
Source: https://github.com/specd-sdd/SpecD/tree/main/dev/ai-agents/skills/specd-code-reviewer
Command: npx skills add https://github.com/specd-sdd/SpecD --skill code-reviewer-specd-sdd

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Conduct exhaustive, professional reviews to identify correctness, maintainability, security, and architectural issues across code changes, PRs, and entire repositories.

Core Features & Use Cases

  • Phase-driven review workflow utilizing parallel subagents with the most capable model for each task
  • Supports local changes (staged/working tree), remote Pull Requests (by number or URL), and full codebase reviews across multiple languages
  • Generates a structured findings report with actionable items and configurable guardrails for spec compliance

Quick Start

Prepare your repository and invoke the review to generate a comprehensive findings report.

Frequently Asked Questions about code-reviewer

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

FAQPage Schema
How do I review a remote pull request for security and maintainability issues?

Review a remote pull request by providing its number or URL to initiate an exhaustive code review. The analysis identifies correctness, maintainability, security, and architecture issues using parallel subagents and generates a structured findings report.

Can I run static analysis on staged local changes before creating a commit?

Static analysis can be run on staged local changes or the working tree. The review workflow applies phase-driven analysis to identify architectural and correctness issues across multiple languages before you commit.

What's the best way to perform an exhaustive codebase review across multiple languages?

Exhaustive codebase reviews across multiple languages are performed using phase-driven workflows with parallel subagents. This approach applies static analysis and GitNexus-based impact analysis to generate a comprehensive findings report.

Does this code review tool support spec compliance checks for architectural standards?

Spec compliance checks are supported through configurable guardrails during the code review. The structured findings report verifies code changes against your architectural standards and specifications.

How does parallel subagent analysis improve the accuracy of a PR review?

Parallel subagents improve PR review accuracy by assigning the most capable model to each specific analysis phase. This phase-based approach ensures exhaustive coverage of correctness, security, and maintainability issues.

What languages are supported for full codebase static analysis and architectural review?

Full codebase static analysis and architectural review support multiple programming languages. The phase-driven workflow evaluates spec compliance and generates actionable findings regardless of the language used.