agent-device
Automates mobile and simulator device interactions, including navigation, screenshots, and UI data extraction.
Install
mkdir -p .claude/skills/agent-device && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/4942" && unzip -o skill.zip -d .claude/skills/agent-device && rm skill.zipInstalls to .claude/skills/agent-device
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Automates Apple-platform apps (iOS, tvOS, macOS) and Android devices. Use when navigating apps, taking snapshots/screenshots, tapping, typing, scrolling, extracting UI info, collecting logs/network/perf evidence, or planning agent-device CLI commands.Key capabilities
- →Navigate mobile application UI screens
- →Interact with elements via tap, type, scroll, and pinch
- →Extract UI element data for verification
- →Capture system snapshots and performance metrics
- →Route interaction commands to specific platform versions
How it works
Provides a CLI routing layer that interfaces with platform-native accessibility APIs to mirror user inputs and extract layout data from mobile apps.
Inputs & outputs
When to use agent-device
- →Automating mobile app navigation flows
- →Taking screenshots for UI regression testing
- →Extracting UI elements for verification
- →Collecting performance logs from simulators
About this skill
agent-device
For a normal app-driving task, start immediately. Do not probe first with --help, --version, devices, appstate, snapshot, or screenshot:
agent-device open <app> --foreground
That starts the session and returns the initial interactive snapshot with @refs.
Loop: act with press|click|fill|longpress <target> ... --settle, scroll <direction> --settle, or back --settle; continue from the printed diff, verify the named expectation (wait text "...", is, get, or find), then run agent-device close.
Copy refs byte-for-byte: @e12, @e12~s4 — keep the @ and any ~sN. Prefer current refs, then id/label/role selectors; coordinates are a last resort. If snapshot reports sparse/AX-unavailable, its refs and selectors are invalid: run agent-device screenshot, inspect the image, use coordinates, then retry snapshot -i after navigating. Otherwise run snapshot -i only when the diff lacks the next target.
Error output includes corrective hints; follow them instead of re-planning. Only when the task is specialized (for example gestures, scripting, TV, macOS, remote, or debugging) or a command shape is unclear, run agent-device help <topic>. agent-device --help lists topics, but is not a startup step.
When not to use it
- →Performing non-UI related backend testing
- →Automating flows that change too quickly for snapshotting
Prerequisites
Limitations
- →Highly dependent on correct CLI version and environment settings
- →Does not support all complex guest-OS gestures
How it compares
It uses version-matched native accessibility hooks to interact with apps, unlike pixel-based automation which is brittle.
Compared to similar skills
agent-device side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| agent-device (this skill) | 2 | 3mo | Review | Advanced |
| build-iphone-apps | 14 | 8mo | Review | Advanced |
| run-device-tests | 3 | 2mo | Review | Advanced |
| mobile-use-setup | 1 | 6mo | Caution | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by callstackincubator
View all by callstackincubator →You might also like
build-iphone-apps
glittercowboy
Build professional native iPhone apps in Swift with SwiftUI and UIKit. Full lifecycle - build, debug, test, optimize, ship. CLI-only, no Xcode. Targets iOS 26 with iOS 18 compatibility.
run-device-tests
dotnet
Build and run .NET MAUI device tests locally with category filtering. Supports iOS, MacCatalyst, Android on macOS; Android, Windows on Windows. Use TestFilter to run specific test categories.
mobile-use-setup
minitap-ai
Interactive setup wizard for Minitap mobile-use SDK. USE WHEN user wants to set up mobile automation, configure mobile-use SDK, connect iOS or Android devices, or create a new mobile testing project.
android-emulator-skill
new-silvermoon
Production-ready scripts for Android app testing, building, and automation. Provides semantic UI navigation, build automation, log monitoring, and emulator lifecycle management. Optimized for AI agents with minimal token output.
webapp-testing
anthropics
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
dev-browser
SawyerHood
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.