dev-tools

Test and document the real behavior of external APIs from: $ARGUMENTS

Create comprehensive API tests for: $ARGUMENTS

Generate both developer and user documentation for the feature: $ARGUMENTS

Create comprehensive documentation for MySQL database: $ARGUMENTS

Implement internal backend API based on spec: $ARGUMENTS

Implement frontend integration for the backend API using docs at: $ARGUMENTS

Use this agent when you need to review recently written code and identify only the most critical issues that must be addressed. This agent should be called after completing a logical chunk of code (e.g., implementing a new feature, refactoring a module, or fixing a bug) to ensure code quality without overwhelming the developer with minor suggestions. Examples: **Example 1: After implementing a new feature** user: "I've just implemented the payment processing module with transaction validation and error handling" assistant: "Let me review the payment processing code using the critical-code-reviewer agent to identify the top 3 most critical issues." <uses Task tool to launch critical-code-reviewer agent> **Example 2: After refactoring** user: "I've refactored the authentication system to use JWT tokens instead of sessions" assistant: "I'll use the critical-code-reviewer agent to check for any critical issues in the refactored authentication code." <uses Task tool to launch critical-code-reviewer agent> **Example 3: Proactive review after code generation** user: "Please create a function to handle user registration with email verification" assistant: "Here's the registration function with email verification:" <function implementation> assistant: "Now let me use the critical-code-reviewer agent to identify any critical issues before we proceed." <uses Task tool to launch critical-code-reviewer agent> **Example 4: After bug fix** user: "I've fixed the race condition in the order processing service" assistant: "Let me review the fix using the critical-code-reviewer agent to ensure there are no critical issues introduced." <uses Task tool to launch critical-code-reviewer agent>

This skill should be used when users want to create, configure, or debug Claude Code hooks. Hooks are shell commands that execute at various points in Claude Code's lifecycle (PreToolUse, PostToolUse, Stop, SessionStart, etc.). Use this skill when users ask to create custom automation, file protection, code formatting hooks, notifications, or any lifecycle-based triggers for Claude Code.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.