cua-desktop-automation-skills

General-purpose GUI debugging loop — use Cua Driver + Vision AI to automate any desktop GUI app with screenshot analysis and automated click/verify flow

Complete GitHub OAuth/Device Code Flow via Cua Driver browser automation — bypasses Chrome URL bar search issue when authenticating from headless agents

Use Cua Driver for macOS desktop automation — launching apps, clicking UI elements, and controlling web pages via Accessibility API and JavaScript injection.

Hybrid control loop using Cua Driver (Accessibility) + Vision AI (Screenshot Analysis) for macOS desktop apps. Full pipeline: screencapture → vision_analyze → Cua hotkey/click → screencapture verify.

Use Cua Driver to inspect and navigate WeChat DevTools simulator for Mini Program UI visual review. Covers AX tree quirks, pixel-click strategies, and NW.js limitations.

Use Cua Driver to automate desktop browsers (Chrome/Safari) — open pages, type text, click elements, execute JavaScript. Includes React/Draft.js workaround for X.com and similar SPA platforms.

Install, configure, and integrate Cua Driver (trycua/cua) on macOS for background desktop control via MCP, including permission granting and Hermes integration.