Agent skill · operations · aaaaqwq
cua-driver-rs
Drive a native GUI app (macOS, Windows, Linux) via the cua-driver CLI (default) or MCP server — snapshot its accessibility tree, click/type/scroll by element_index or pixel coords, verify via re-snapshot, all without bringing the target to the foreground. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real application on the host.
Why this skill is useful
Adds executable automation scripts for cross-platform GUI application control that are not available in public documentation.
What it needs
Requires cua-driver installed locally. About 12k tokens when loaded. Last updated 2026-08-06. 83 stars on the source repository.
What this skill does
cua-driver-rs Orchestrates cross-platform app automation via cua-driver. Whenever a user asks to drive a native 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. Platform-specific reading — read this first This file is the cross-platform core: snapshot invariant, CLI vs MCP choice, tool surface naming, behavior matrix, canonical loop, pixel-click contract, common failure modes. The platform-specific material (forbidden-list, accessibility tree implementation, launch semantics, click dispatch) lives in companion files in this same directory: macOS — read MACOS.md (no-foreground contract, forbidden open/osascript/cliclick invocations, AXMenuBar navigation, SkyLight pixel-click dispatch, Apple-Events JS bridge). Windows — read WINDOWS.md (UIA tree vs AX, UWP / ApplicationFrameHost hosting, layered UIA+PostMessage click chain, Session 0 isolation, Windows-specific focus-steal vectors). Linux — read LINUX.md (X11/Wayland status, AT-SPI, BETA-level support). Cross-cutting topics also have their own files: WEBAPPS.md — browser / Electron / Tauri specifics (sparse AX trees, omnibox navigation, the setvalue workaround for minimized windows, tabs-vs-windows guidance). RECORDING.md — session recording + replaytrajectory. TESTS.md — internal test surface. Use whichever combination matches the host. When in doubt, run cua-driver doctor — it reports the platform and the right entry point. The no-foreground principle (cross-platform) The user's frontmost app MUST NOT change. Every platform has its own list of forbidden commands; the principle is universal: macOS: any open invocation, any osascript that mutates GUI state, cliclick, cghidEventTap writes targeting another app's window. Full list in MACOS.md. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aaaaqwq/cua-driver