android-emulator
Verify and debug native, React Native, Expo, or Flutter apps on an Android Emulator with agent-device. Use when an agent needs to…
@callstackincubatorInstall SkillTesting
Skill
/agent-device
Automates Apple-platform apps (iOS, tvOS, macOS), Android devices (including Android TV and Fire TV on Fire OS), and Amazon Vega OS TV apps in Vega Virtual Devices. Use when navigating apps, taking snapshots/screenshots where supported, driving TV remotes, tapping, typing,
Claude Code
$ npx -y skills add callstack/agent-device --skill agent-device --agent claude-code
Codex
$ npx skills add callstack/agent-device --skill agent-device -a codex -y
Cursor
$ npx skills add callstack/agent-device --skill agent-device -a cursor -y
Gemini CLI
$ npx skills add callstack/agent-device --skill agent-device -a gemini-cli -y
GitHub Copilot
$ npx skills add callstack/agent-device --skill agent-device -a github-copilot -y
OpenCode
$ npx skills add callstack/agent-device --skill agent-device -a opencode -y
Windsurf
$ npx skills add callstack/agent-device --skill agent-device -a windsurf -y
SKILL.md
agent-device.SKILL.mdname: agent-device
description: Automates Apple-platform apps (iOS, tvOS, macOS), Android devices (including Android TV and Fire TV on Fire OS), HarmonyOS devices, and Amazon Vega OS TV apps in Vega Virtual Devices. Use when navigating apps, taking snapshots/screenshots where supported, driving TV remotes, tapping, typing, scrolling, extracting UI info, installing or replacing an app binary, collecting evidence, or planning agent-device CLI commands. Install or reinstall an app binary (Android, Apple, HarmonyOS) and uninstall an app (Android, Apple) with the install, reinstall, and uninstall commands, not adb, hdc, or bm.
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`, or `agent-device close --shutdown` if your session booted a local simulator or emulator, unless the user asks to keep it running.
Reaching an off-screen target is one command, not a scroll-and-check loop: `scroll down --until <selector>` scrolls until that element is on screen, and `scroll bottom` runs to the end of the content. Repeated bare `scroll down` calls are the slow way to find something.
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.
To capture network traffic on a Limrun session, see `agent-device help remote` or the Limrun docs.
Read more
name: agent-device description: Automates Apple-platform apps (iOS, tvOS, macOS), Android devices (including Android TV and Fire TV on Fire OS), HarmonyOS devices, and Amazon Vega OS TV apps in Vega Virtual Devices. Use when navigating apps, taking snapshots/screenshots where supported, driving TV remotes, tapping, typing, scrolling, extracting UI info, installing or replacing an app binary, collecting evidence, or planning agent-device CLI commands. Install or reinstall an app binary (Android, Apple, HarmonyOS) and uninstall an app (Android, Apple) with the install, reinstall, and uninstall commands, not adb, hdc, or bm.
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`, or `agent-device close --shutdown` if your session booted a local simulator or emulator, unless the user asks to keep it running.
Reaching an off-screen target is one command, not a scroll-and-check loop: `scroll down --until <selector>` scrolls until that element is on screen, and `scroll bottom` runs to the end of the content. Repeated bare `scroll down` calls are the slow way to find something.
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.
To capture network traffic on a Limrun session, see `agent-device help remote` or the Limrun docs.
Stats
5,332
Stars
393
Forks
Active
Maintenance
TypeScript
Language
MIT
License
Last commit
Created
Ships withagent-device
Open source device layer for AI coding agents. Let coding agents control mobile, web, TV, and desktop apps on devices and simulators, locally or in the cloud, through a CLI, built-in MCP server, or typed Node.js API.
5.2k4 skills
Stars on GitHub
Momentum
- stars in total
- 5.2k
Other skills on agent-device.
@callstackincubatorInstall Skilldogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use…
@callstackincubatorInstall Skillios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to…
@callstackincubatorInstall SkillMore skills from other plugins.
api-review
Produce the "Playwright 1.xx API Review" artifact for a range of commits - the public API additions and the breaking or behavior…
@microsoftInstall Skill
promptfoo-evals
Write, refine, run, and QA promptfoo evaluation suites: promptfooconfig.yaml, prompts, providers, vars, tests, assertions,…
@promptfooInstall Skilldeepeval
DeepEval evaluation workflow for AI agents and LLM applications. TRIGGER when the user wants to evaluate or improve an AI agent,…
@confident-aiInstall SkillQuestions about agent-device.
- Which coding agents can use agent-device?
- agent-device installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.