uiautomator2-mcp-server: Skill for Claude Code

.skills/android-ui-test/SKILL.md

android-ui-test is a skill for Claude Code, Codex from tanbro/uiautomator2-mcp-server. It costs 41 tokens per session (1,165 once invoked), scanned A, original, Apache-2.0.

A demonstration and automated testing skill for Android user interfaces. It uses uiautomator2 to interact with and validate a connected Android device.

In plain words
What is it for?
Use it to test Android UI actions, validate uiautomator2-mcp-server behavior, run the project’s device test suite, or study an example of Android automation.
Why use it?
It provides an organized way to check Android interactions and report which tests pass or fail. It also shows developers how to build similar testing skills.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is tanbro/uiautomator2-mcp-server's own configuration. It tells Claude Code and Codex how to work on uiautomator2-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything uiautomator2-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tanbro/uiautomator2-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tanbro/uiautomator2-mcp-server/main/.skills/android-ui-test/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tanbro/uiautomator2-mcp-server

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for android-ui-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/tanbro/uiautomator2-mcp-server/android-ui-test/github.svg)](https://agentmods.dev/skills/tanbro/uiautomator2-mcp-server/android-ui-test)
Your own site
<a href="https://agentmods.dev/skills/tanbro/uiautomator2-mcp-server/android-ui-test"><img src="https://agentmods.dev/badge/skills/tanbro/uiautomator2-mcp-server/android-ui-test/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for android-ui-test

Your own site · 80×15
<a href="https://agentmods.dev/skills/tanbro/uiautomator2-mcp-server/android-ui-test"><img src="https://agentmods.dev/badge/skills/tanbro/uiautomator2-mcp-server/android-ui-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,165 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.01165
Opus 5 $0.00020 $0.00583
Sonnet 5 $0.00008 $0.00233
Haiku 4.5 $0.00004 $0.00117

Measured 10d ago against content hash d95a87b20a99, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

android-ui-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.skills/android-ui-test/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Android UI Test Automation (Demo & Production)

This skill serves a dual purpose:

  1. Demonstration: Shows how to build AI-driven Android UI testing skills
  2. Production Testing: Acts as the project's own automated UI test suite

Goals

  • Demonstrate best practices for Android UI automation skills
  • Provide comprehensive testing for uiautomator2-mcp-server functionality
  • Enable AI agents to validate Android device interactions
  • Serve as a reference implementation for similar skills

Prerequisites

  • Connected Android device with USB debugging enabled
  • ADB server running (adb start-server)
  • uiautomator2-mcp-server properly configured

Usage Scenarios

Scenario 1: Learning Example

When developers want to understand how to create Android UI testing skills:

  • Study the structured approach in this skill
  • Learn proper YAML metadata formatting
  • Understand test case organization and execution flow
  • See how to handle device-specific considerations

Scenario 2: Production Testing

When validating uiautomator2-mcp-server functionality:

  • Execute complete test suite automatically
  • Generate detailed pass/fail reports
  • Validate all core device interaction capabilities
  • Ensure consistent performance across device variations

Test Execution Flow

Phase 1: Device Setup and Validation

  1. List connected devices via device_list
  2. Select first available device
  3. Initialize device via init tool
  4. Verify device connectivity and basic info

Phase 2: Comprehensive Functionality Tests

  1. Device Operations: Info, screenshot, UI hierarchy dump
  2. Touch Actions: Click, long press, double click at various positions
  3. Gesture Operations: Swipe, drag, system key presses
  4. Application Management: List apps, launch apps, get app info
  5. Element Interactions: Wait for elements, get bounds, text extraction, element clicks
  6. Input Operations: Text input, keyboard management
  7. Clipboard Operations: Read/write clipboard content

Read the full file on GitHub · 146 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 146 lines · 41 tokens per session scan A d95a87b20a99

Subscribe to this mod's changes

android-ui-test is a skill published in the GitHub repository tanbro/uiautomator2-mcp-server (41 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,165 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

android-ui-journey-testing

XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.

sickn33/agentic-awesome-skills · 27 tokens

solopi-ai

A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.

alipay/SoloPi · 127 tokens

android-qa

Test an Android app on a real phone or an emulator using adb. Use when the user wants to install an APK they just compiled, walk through the app's screens, check the on-screen text, reproduce a bug, capture screenshots, read crash logs, or set up an Android testing environment from scratch. Covers both a physical…

willbytee-sudo/android-qa-kit · 80 tokens

playwright-for-android

End-to-end Android debug loop on an emulator. Builds the APK with a Gradle task, boots a named AVD, installs and launches the target package, then drives a single feature via adb-injected UI actions while capturing a unified logcat-and-actions timeline plus a developer-facing test report. Use when the user wants to…

fclab-skku/playwright_for_android · 97 tokens

mobile-tester

You are the Mobile Tester Specialist. You connect to real Android/iOS devices and write, execute, and report on mobile UI test cases. You master THREE testing modalities.

buiphucminhtam/forgewright · 81 tokens

android-ui-journey-testing

XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.

iradoweck/antigravity-awesome-skills · 27 tokens