Claude Skill
win4r/agent-skills-code-review-router
A Claude Skill that routes code review tasks to specialized agents for automated analysis. Streamline code quality checks and developer workflows with intelligent task distribution.
Overview
Repository
Install this Skill
git clone https://github.com/win4r/agent-skills-code-review-router.gitRegistry
Summary
A Claude Skill for routing code review tasks to specialized agents, enabling automated and efficient code analysis workflows.
Key features
- Code review task routing
- Specialized agent coordination
- Automated workflow management
- GitHub repository integration
Use cases
- Automated code quality checks
- Multi-agent review systems
- Developer workflow automation
- Pull request analysis
README excerpt
[English](#english) | [中文](#中文) --- <a name="english"></a> ### 🚀项目所对应的视频： https://youtu.be/Qydk2wlh4YI https://www.bilibili.com/video/BV1KErQB4Esx/ # Code Review Router [](https://opensource.org/licenses/MIT) An **Agent Skill** that intelligently routes code reviews between Gemini CLI and Codex CLI based on tech stack, complexity, and change characteristics. ## What is an Agent Skill? Agent Skills are reusable packages of knowledge that extend what AI agents can do. A Skill is a markdown file (SKILL.md) containing instructions that the agent follows when working on specific tasks. Skills follow a **progressive disclosure** pattern: 1. **Discovery**: The agent sees available Skills with their names and descriptions 2. **Activation**: When your task matches a Skill's description, the agent loads the full instructions 3. **Execution**: The agent follows the Skill's instructions automatically This Skill works with both **Claude Code** and **Google Antigravity**. ## Why Use a Decision Tree Skill? ### Advantages of Decision Tree-Based Routing | Advantage | Description | |-----------|-------------| | **Deterministic & Predictable** | Unlike free-form prompts, decision trees follow explicit rules, ensuring consistent routing every time | | **Transparent Logic** | Every routing decision can be traced back to specific criteria—no black-box behavior | | **Optimized Tool Selection** | Automatically selects the best tool (Gemini vs Codex) based on change characteristics | | **Reduced Token Usage** | Pre-defined decision paths eliminate the need for lengthy reasoning chains | | **Extensible** | Easy to add new routing rules or modify existing ones without rewriting the entire logic | | **Fallback Handl
Topics
No topics yet.