What problem does it solve? Testing SwiftUI apps on a real device normally requires manual tapping or heavyweight UI test frameworks. This Skill connects to a physical iPhone over a USB CoreDevice tunnel and lets an AI agent autonomously explore screens, tap elements, and find bugs through a screenshot-analyze-act-verify loop. ## Core Features & Use Cases - Live-device agent loop: Connects via CoreDevice IPv6 tunnel, reads Swift source to understand screens, then iterates screenshot → analyze → decide → act → verify against the running app. - Embedded HTTP StateServer: Ships Swift/Objective-C templates (StateServer, DebugBridge, touch synthesis) that expose screenshots, accessibility elements, and tap/swipe/type mutations over authenticated loopback HTTP. - Remote QA over Tailscale: Optionally exposes the device so remote HTTP-capable agents can run iOS QA without physical access to the hardware. - Use Case: Ask the agent to "qa the iOS app" after a feature change; it drives the real device, exercises each screen, and reports bugs with screenshot evidence. ## Quick Start Ask the agent to run iOS QA on my iPhone app and find bugs on the connected device.