Advanced desktop automation with mouse, keyboard, and screen control
Data sourced from ClawHub. View on ClawSkills
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install desktop-controlOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install desktop-controlβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/desktop-control/π‘Extract and place the folder at the path above, then restart your agent.
Category
What Desktop Control can do for your AI workflow
Advanced desktop automation directly from your Claude conversation
Works across Claude, Cursor, OpenClaw β install once, use everywhere
Trusted by 47,974+ developers worldwide
One-command installation β no complex setup required
Combine with other skills to build powerful multi-step AI workflows
Try these prompts with your AI agent after installing Desktop Control
Help me get started with Desktop Control
Explains what Desktop Control does, walks through the setup, and runs a quick demo based on your current project
Use Desktop Control to advanced desktop automation with mouse, keyboard, and screen control
Invokes Desktop Control with the right parameters and returns the result directly in the conversation
What can I do with Desktop Control in my ai agent & automation workflow?
Lists the top use cases for Desktop Control, with example commands for each scenario
Guides & tutorials for AI skills
Desktop Control extends your AI assistant with the ability to advanced desktop automation with mouse, keyboard, and screen control. Rather than leaving your conversation to handle this manually, you can ask your Claude agent directly β and it will take care of the task end-to-end, using Desktop Control as its underlying capability.
Desktop Control works across Claude, Cursor, OpenClaw through the Model Context Protocol (MCP) β an open standard that lets AI clients share tools and skills without lock-in. Because MCP is platform-agnostic by design, you install Desktop Control once and it becomes available across all your AI clients. Whether you're working in Claude for focused sessions or Cursor for integrated workflows, the skill behaves consistently.
To install Desktop Control, copy the skill folder to `~/.claude/skills/desktop-control/` for use across all your projects, or `.claude/skills/desktop-control/` for a single project. Restart Claude and the skill is immediately active β invoke it with `/desktop-control` or just describe your goal and the AI will pick it up automatically.
With 47,974 installs, Desktop Control has built a substantial following in the AI Agent & Automation space. That install count reflects consistent demand from developers and teams who've found it genuinely useful. Like all skills on DiscoverAISkills, it is free to install and use. The broader AI skills ecosystem continues to expand as developers contribute new capabilities across categories like developer tools, data analysis, writing, automation, and more.
Place the skill folder at ~/.claude/skills/desktop-control/ for personal use (all projects), or .claude/skills/desktop-control/ for project-specific use. Restart your AI client, then invoke with /desktop-control or let the AI discover it automatically.
Desktop Control supports Claude, Cursor, OpenClaw. It integrates seamlessly with these AI platforms to extend their capabilities.
Desktop Control is free to install. Check the repository for licensing information.
Advanced desktop automation with mouse, keyboard, and screen control
Automate my ai agent & automation tasks using Desktop Control
Identifies repetitive steps in your workflow and sets up Desktop Control to handle them automatically
MCP vs traditional plugins: what's the difference?
Desktop Control is categorized under AI Agent & Automation. These skills help AI agents perform specialized tasks in this domain.