# Computer Use

> Control desktop - take screenshots, click at coordinates, type text, move mouse, press keys, visual AI

- Skill: `chainlesschain/computer-use` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add chainlesschain/computer-use`
- Raw SKILL.md: https://api.skillmd.com/api/skills/chainlesschain/computer-use/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Web & Frontend
- Author: chainlesschain (https://skillmd.com/u/chainlesschain)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/chainlesschain/computer-use

---


# Computer Use Skill

Desktop-level automation with screenshot, mouse, keyboard, and Vision AI.

## Usage

```
/computer-use <action> [args]
```

## Actions

| Action         | Description                       | Example                                        |
| -------------- | --------------------------------- | ---------------------------------------------- |
| `screenshot`   | Capture full screen               | `/computer-use screenshot`                     |
| `click`        | Click at pixel coordinates        | `/computer-use click 500 300`                  |
| `type`         | Type text via keyboard            | `/computer-use type "Hello World"`             |
| `visual-click` | Click element found by Vision AI  | `/computer-use visual-click "Settings button"` |
| `analyze`      | Analyze screenshot with Vision AI | `/computer-use analyze "What's on screen?"`    |
| `key`          | Press keyboard shortcut           | `/computer-use key ctrl+c`                     |
| `move`         | Move mouse to coordinates         | `/computer-use move 400 200`                   |

## Vision AI Integration

The skill can use Vision AI (Claude/GPT-4V/LLaVA) to:

- Find UI elements by visual description
- Analyze screen content
- Identify clickable targets without knowing coordinates