burner-phone

Control Android device screens via ADB with vision-based coordinate detection.

5|Updated Feb 8, 2026
One-click install
npx skills add https://github.com/tiancaiamao/ai --skill burner-phone-tiancaiamao
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: burner-phone
Source: https://github.com/tiancaiamao/ai/tree/main/skills/burner-phone
Command: npx skills add https://github.com/tiancaiamao/ai --skill burner-phone-tiancaiamao

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires adb, ollama, python3, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

This Skill removes the friction of manually interacting with Android devices when you need precise taps, swipes, typing, or app launches from an AI-driven workflow.

Core Features & Use Cases

  • Vision-guided control: Captures the screen, analyzes UI elements, and finds exact coordinates before acting.
  • ADB automation: Sends taps, swipes, key events, text input, and app launch commands directly to the device.
  • Practical use cases: Automate burner phone workflows, test mobile apps, verify UI states, or complete repetitive on-device tasks with a screenshot-and-confirm loop.

Quick Start

Ask the skill to inspect your Android screen and then tap, swipe, type, or launch the needed app using ADB with vision-based coordinate detection.

Frequently Asked Questions about burner-phone

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate Android device screen interactions using ADB and vision analysis?

Android device automation via ADB uses vision analysis to capture screenshots, identify UI element coordinates, and execute taps, swipes, and text entry. This removes manual interaction by using a screenshot-and-confirm loop to verify actions.

What do I need to set up to control an Android phone with ADB and a vision model?

To control an Android phone with ADB and a vision model, you need python3, an accessible vision model endpoint for screenshot interpretation, and an Android device connected with USB debugging enabled.

Can I use vision-based screenshot inspection to find exact tap coordinates on Android?

Yes, vision-based screenshot inspection captures the current Android screen and analyzes UI elements to find exact coordinates before sending ADB tap commands, ensuring precise interaction with the target application.

How does ADB automation handle app launches and key events on Android devices?

ADB automation handles app launches and key events by sending direct commands to the connected Android device. It uses vision analysis to verify screen states before executing key events or initiating app launches.

What are the limitations of using ADB and vision models for mobile app testing?

Limitations of ADB and vision models for mobile app testing include the dependency on a connected device with USB debugging and the processing overhead of capturing and analyzing screenshots for every on-device action.

Is ADB vision control suitable for repetitive on-device tasks like burner phone workflows?

Yes, ADB vision control is suitable for repetitive on-device tasks like burner phone workflows because it automates screenshot inspection, coordinate tapping, swiping, and text entry through an AI-driven workflow.