What problem does it solve?
This Skill removes the friction of manually operating an Android device for screenshots, taps, typing, and basic media actions by providing a unified, automation-friendly control layer.
Core Features & Use Cases
- Universal Android control across backends: Operates via Termux, ADB-only devices, or Android emulators.
- Vision feedback loop for UI automation: Take a screenshot, analyze it to get precise coordinates, then act (tap/swipe/type) and verify with a follow-up screenshot.
- Device interaction primitives for mobile workflows: Wake/unlock, capture camera (when supported), record/play audio, and launch apps to support mobile app testing or AI companionship.
What problem does it solve?
You want reliable mobile device automation (for testing, assistance, or delegated tasks) without needing to hard-code screen coordinates yourself.
Quick Start
Tell your agent to: take a screenshot, run vision to find the Settings button coordinates, then tap those coordinates and confirm the result with a second screenshot.