A comprehensive skill for controlling macOS applications and automating GUI interactions through the Accessibility API.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install mac-compute-use
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install mac-compute-use using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
Mac Compute Use is a powerful extension for Openclaw Skills that enables AI agents to interact directly with the macOS desktop environment. By utilizing the system's Accessibility API, this skill provides a way to programmatically navigate, inspect, and control any graphical application running on Mac. Whether it is managing files in Finder, sending messages, or interacting with specialized software, this tool bridges the gap between digital reasoning and physical UI interaction. For users of Openclaw Skills, this provides a computer use capability that allows for the automation of complex, manual desktop tasks that do not offer a traditional CLI or API interface.
First, install the MCP server via Homebrew:
brew tap reedburns/mcp-server-macos-use
brew install mcp-server-macos-use
Next, register the server with mcporter to enable it within your Openclaw Skills environment:
mcporter config add macos-use --transport stdio --command $(which mcp-server-macos-use)
Finally, you must manually grant Accessibility permissions by navigating to System Settings → Privacy & Security → Accessibility and adding the mcp-server-macos-use binary.
The skill manages its data through structured JSON responses and temporary files that define the UI tree.
| Property | Description |
|---|---|
| status | The outcome of the tool execution (success or error). |
| pid | The Process ID of the application currently being controlled. |
| file | The absolute path to a JSON file containing the full UI element tree. |
| visible_elements | A summary of interactive elements, including their coordinates (x, y) and dimensions. |
| diff | A report of what changed in the UI following the last interaction. |
Loading
A powerful bridge between your personal knowledge management system and your AI agent, enabling programmatic access to Readwise and Reader data.

A specialized utility for converting raw Telegram Desktop JSON exports into polished, long screenshot-style images using Openclaw Skills.

A precision material takeoff tool for calculating fencing components including posts, rails, pickets, and hardware for wood, vinyl, and aluminum projects.

An AI-powered script optimizer that converts narrative plots into structured 9-segment visual scripts specifically for Seedance video generation.

A high-efficiency utility to scrape and structure tech event data from lu.ma for any global city without requiring authentication.

Decentralized, AES-256 encrypted storage for AI agent memory backed by the Jackal Protocol.








































