What problem does it solve? Testing SwiftUI apps on real iPhones normally requires manual tapping or simulator-only automation that misses device-specific bugs. This Skill connects to a physical iPhone over a USB CoreDevice tunnel and drives an autonomous screenshot-analyze-act-verify loop against the running app, so bugs surface on real hardware without a human holding the phone. ## Core Features & Use Cases - Live-device agent loop: Connects via CoreDevice IPv6 tunnel, reads Swift source to map every screen, then iterates screenshot, analyze, decide, act, verify against an embedded HTTP StateServer in the app under test. - DebugBridge instrumentation: Ships Swift and Objective-C templates (StateServer, touch synthesis, accessibility tree snapshot, debug overlay) that are compiled into DEBUG builds only, with bearer-token auth, session locking, and snapshot/restore of app state. - 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 your iPhone app before a release; it walks every screen on the connected device, taps through flows, and reports concrete bugs with file and line references. ## Quick Start Ask the agent to run iOS QA on your iPhone app with the device connected over USB.