desktop-vision-pc

Community

See and control Windows desktop with vision.

Authormlamla123
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill enables seeing and interacting with the Windows desktop using screen capture and vision models, enabling automation for UI tasks, testing, and control of apps that lack CLI/API.

Core Features & Use Cases

  • Screen capture and analysis: take screenshots, analyze with a vision model to identify UI elements, dialogs, and states.
  • Interaction primitives: Click, Type, Key, Focus to operate on desktop apps.
  • Monitoring and automation: automate common desktop workflows, watch for dialogs, and perform scripted actions.

Quick Start

Watch and interact with your Windows desktop by taking screenshots, analyzing with vision models, and performing clicks or keystrokes.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: desktop-vision-pc
Download link: https://github.com/mlamla123/openclaw-starter-kit/archive/main.zip#desktop-vision-pc

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.