reviewing-code

Name: reviewing-code
Availability: InStock
Author: ryugen04

Coordinate automated and human code reviews across PRs and uncommitted work.

Updated Aug 23, 2026

Search Tags:#code review #performance #security #agents #quality #report

Ready to run

npx skills add https://github.com/ryugen04/dotfiles --skill reviewing-code-ryugen04

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: reviewing-code
Source: https://github.com/ryugen04/dotfiles/tree/main/packages/claude/.claude/skills/code/reviewing-code
Command: npx skills add https://github.com/ryugen04/dotfiles --skill reviewing-code-ryugen04

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a structured framework for conducting code reviews using 12 specialized agents (6 pr-review-toolkit and 6 custom) to evaluate quality, security, performance, and consistency.

Core Features & Use Cases

12 agents: 12 agents are defined and activated conditionally, each with a specific focus.
Parallel execution: All necessary agents run in parallel to produce a comprehensive report.
Mandatory reports: All agents report their findings; no silent failures.

Quick Start

Trigger a code review (PR or changes) and let the 12 agents execute to produce a detailed, multi-section report.

Frequently Asked Questions about reviewing-code

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

FAQPage Schema

How do I run automated code reviews on pull requests and uncommitted changes?▼

Code reviews coordinate 12 parallel agents—six from pr-review-toolkit and six custom—to evaluate PRs, unpushed commits, or uncommitted work. Trigger via /code:review-pr, /code:review-unpushed, or /code:review-uncommited to deploy agents covering security, performance, quality, consistency, design, and governance in a single comprehensive report.

What does a parallel code review process cover?▼

Parallel code reviews evaluate security vulnerabilities, performance bottlenecks, code quality issues, consistency violations, design problems, and governance compliance. Each of the 12 agents reports findings with exact file paths and line numbers, ensuring no issues are missed and all results follow a standardized format.

Can I use code reviews for both PRs and uncommitted work?▼

Yes. The code review workflow supports three triggers: /code:review-pr for pull requests, /code:review-unpushed for commits not yet pushed, and /code:review-uncommited for local changes. All three activate the same 12-agent parallel execution to produce identical reporting standards.

What happens if an agent doesn't find issues in its area?▼

All 12 agents report findings regardless of outcome. The system implements startup rules that determine whether each agent runs or skips, then outputs pre-launch status and final results in a standardized format, ensuring transparency and no silent failures.

How are code review results structured and reported?▼

Results preserve per-agent issues with exact file paths and line numbers in a standardized format. Each of the 12 agents reports independently, allowing you to see which checks passed, which flagged problems, and where in your code changes those problems occur.

Is setup or configuration required before running code reviews?▼

No dependencies or components are required. The code review workflow is self-contained and runs immediately when triggered. Simply invoke /code:review-pr, /code:review-unpushed, or /code:review-uncommited to activate the 12-agent parallel review system.