skills.rest
Kasempiternal
KasempiternalCOMMUNITY
Explore all skills by this author →
GitHub

review

Orchestrate 7 AI agents to review code and report prioritized findings.

15|4|Updated Jul 4, 2025
Search Tags:#code quality#automation#code review#refactoring#bug detection#agent swarm
One-click install
npx skills add https://github.com/Kasempiternal/Claude-Agent-System --skill review-kasempiternal
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/Kasempiternal/Claude-Agent-System/tree/main/claude-agent-system-plugin/skills/review
Command: npx skills add https://github.com/Kasempiternal/Claude-Agent-System --skill review-kasempiternal

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the rigorous process of code review, identifying bugs, style issues, and potential failures before they reach production.

Core Features & Use Cases

  • Multi-Agent Analysis: Employs 7 specialized agents to scrutinize code from various angles (bugs, guidelines, types, tests, etc.).
  • Automated Fixes: Automatically resolves critical and major issues, with an option to simplify code post-fix.
  • Use Case: Before merging a new feature, run /review to have a swarm of AI agents thoroughly inspect the code, report findings, and even fix common issues automatically.

Quick Start

Run /review to analyze your uncommitted code changes.

Frequently Asked Questions about review

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

FAQPage Schema
How do I automate code review for uncommitted changes?▼

You can automate code review by running a command to analyze uncommitted changes. The system orchestrates a swarm of 7 specialized AI agents to detect bugs, style violations, and silent failures, synthesizing findings into a prioritized report.

What is an agent swarm and how does it help with bug detection?▼

An agent swarm is a group of 7 specialized AI agents that scrutinize code from various angles. It helps with bug detection by analyzing files for logic errors, type issues, and test coverage gaps, generating a comprehensive and prioritized findings report.

Can AI automatically fix code quality issues found during a review?▼

Yes, AI can automatically fix code quality issues. After the review identifies critical and major issues, the system optionally resolves them automatically and offers a code simplification pass to refactor and improve the overall structure.

Does automated code review work for detecting silent failures and test coverage gaps?▼

Automated code review works for detecting silent failures and test coverage gaps. The multi-agent analysis specifically scrutinizes code to identify these hidden issues alongside style violations and logic errors before code reaches production.

What is the best way to perform a comprehensive code review before merging a feature?▼

The best way to perform a comprehensive code review before merging is to run an automated analysis on your files. A swarm of AI agents will thoroughly inspect the code from multiple angles, report prioritized findings, and automatically fix common issues.

Are there limitations to using AI agents for code refactoring and bug detection?▼

A limitation of using AI agents for code refactoring and bug detection is that the automated fixes target only critical and major issues. Complex logic errors may still require manual intervention after the swarm synthesizes its prioritized findings report.

Related Skills

Explore More Software Engineering Skills→
shannonshellshannonshell
11

commit

Generate poetic git commit messages with staged file selection.

Official
Intermediate
chaitinchaitin
5

fix

Fix lint errors and formatting in JavaScript/TypeScript projects before commit.

Official
Intermediate
AlexCMartyAlexCMarty

act-on-test-audit

Convert test coverage audit findings into verified behavior-pinning test cases.

Community
Advanced
erichugyerichugy

address-pr-comments

Fetch unresolved GitHub review threads and implement fixes via multi-agent worktrees.

Community
Advanced