Overview
cua-driver is an open-source integrations skill for Claude Code and compatible agents, published by ThinkInAIXYZ. Its author describes it as: “Drive a native macOS app via the cua-driver MCP server or CLI — snapshot its AX tree, click/type/scroll by element_index, verify via re-snapshot. Use when the user asks you to operate, drive, automate, or perform a GU…”. The project has 6.2k stars on GitHub and is available under the Apache-2.0 license. Add it to your setup with `git clone https://github.com/ThinkInAIXYZ/deepchat ~/.claude/skills/cua-driver`.
What cua-driver does
Orchestrates macOS app automation via `cua-driver`. Whenever a user asks to drive a native macOS app, follow the loop in this skill rather than calling tools ad-hoc — the snapshot-before-action invariant is not optional and silently breaks if you skip it.
What’s inside
The SKILL.md for cua-driver is organised into these sections:
- DeepChat MCP mode
- Sparse visible UI fallback
- The no-foreground contract — read this first
- Defaults — always prefer cua-driver over shell shims
- The narrow carve-out
- Self-check pattern
- Prerequisites — check before starting
- Using cua-driver from the shell
- Agent cursor overlay
- The core invariant — snapshot before AND after every action
- Why window selection is the caller's job now
- Behavior matrix
Installation
Add cua-driver to your agent with:
git clone https://github.com/ThinkInAIXYZ/deepchat ~/.claude/skills/cua-driverReview a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.
Supported agents
Neither the skill nor its repository names a specific agent. It uses the SKILL.md format, which several agents can load — check the repository for any agent-specific requirements.
License
cua-driver is published under the Apache-2.0 license.
Strengths
- Clear Apache-2.0 license — safe to read and adapt within its terms
- Ships in ThinkInAIXYZ/deepchat, an established project with 6,228 GitHub stars
- Actively maintained — repository updated in the last 90 days
Author
Topics
Frequently asked questions
- What does cua-driver do?
- Drive a native macOS app via the cua-driver MCP server or CLI — snapshot its AX tree, click/type/scroll by element_index, verify via re-snapshot. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real macOS application on the host (e.g. "open a file in TextEdit", "navigate to /Applications in Finder", "click the Save button in Numbers").
- How do I install cua-driver?
- Run git clone https://github.com/ThinkInAIXYZ/deepchat ~/.claude/skills/cua-driver in your agent, then reload your skills. Review the source at https://github.com/ThinkInAIXYZ/deepchat before installing.
- Is cua-driver free to use?
- Yes. cua-driver is free and open source under the Apache-2.0 license, so you can read, run, and adapt it within that license's terms.
- Where does cua-driver come from?
- cua-driver ships inside ThinkInAIXYZ/deepchat, a repository that contains 25 catalogued skills in total. The repository's 6,228 GitHub stars apply to that whole collection, not to this skill on its own.