ui-detector

Detect UI elements in images using a YOLO-based detector.

2|Updated Mar 21, 2026
One-click install
npx skills add https://github.com/Throokie/claude-code-skills --skill ui-detector
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ui-detector
Source: https://github.com/Throokie/claude-code-skills/tree/main/skills/ui-detector
Command: npx skills add https://github.com/Throokie/claude-code-skills --skill ui-detector

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

在 UI 自动化场景下,提供一个基于 YOLO 的界面元素检测工具,帮助快速识别按钮、输入框、二维码等元素,减少手动标注与脚本开发成本。

Core Features & Use Cases

  • 多项目隔离管理:为不同 UI 自动化任务创建独立工作区,防止数据混淆。
  • 训练与推理一体化:从数据标注、模型训练到在线检测的一站式流程,支持自定义类别。
  • Use Case:在桌面或移动端截图中自动定位按钮并触发点击,从而实现端到端的自动化测试与执行。

Quick Start

Create a new project with ui-detector new <project>, then start annotation with ui-detector annotate <project> to train and detect UI elements.

Frequently Asked Questions about ui-detector

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

FAQPage Schema
How do I detect UI elements in screenshots for automated testing?

To detect UI elements in screenshots for automated testing, use a YOLO-based detector to identify buttons, inputs, and QR codes. This approach streamlines semi-automated interface interactions by automatically locating elements in desktop or mobile images.

How do I train a custom YOLO model to recognize specific GUI components?

To train a custom YOLO model for GUI components, use an integrated annotation and training workflow. Create an isolated project, annotate your specific UI element data, and execute the training process to build a detector tailored to your automation needs.

Can I use computer vision to automate mobile and desktop interface interactions?

Yes, you can use computer vision to automate mobile and desktop interface interactions. A YOLO-based detector supports on-demand inference across both platforms, enabling automated clicking and interaction with detected elements like buttons and inputs.

What is the best way to manage multiple UI automation training datasets?

The best way to manage multiple UI automation datasets is using multi-project isolation. Creating independent workspaces for different automation tasks prevents data混淆, ensuring your training workflows and annotations remain cleanly separated.

Do I need Python 3.11 to run YOLO-based GUI testing scripts?

Yes, you need Python 3.11 to run these YOLO-based GUI testing scripts. The detector fulfills explicit dependencies on this specific Python version and requires a portable project structure with a dedicated scripts directory to function properly.