agent-mobile — for Claude Code agent-mobile, community, for Claude Code, ide skills, mobile, through, binary, should, follow, Confirm

v1.0.0
GitHub

Acerca de este Skill

Perfecto para Agentes de Pruebas Automatizadas que necesitan capacidades de prueba de aplicaciones móviles avanzadas a través de archivos binarios locales. Resumen localizado: Mobile automation skill for the local agent-mobile CLI. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Características

Use this skill to drive a mobile app through the local agent-mobile binary.
Every agent-mobile task should follow this loop:
Confirm the environment and target device.
Launch the app and capture a fresh snapshot.
Interact with @eN refs or semantic locators.

# Core Topics

for Claude Code mobile through binary should follow
r0227n r0227n
[1]
[0]
Updated: 3/10/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 8/11

This page remains useful for teams, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution
Review Score
8/11
Quality Score
42
Canonical Locale
en
Detected Body Locale
en

Perfecto para Agentes de Pruebas Automatizadas que necesitan capacidades de prueba de aplicaciones móviles avanzadas a través de archivos binarios locales. Resumen localizado: Mobile automation skill for the local agent-mobile CLI. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

¿Por qué usar esta habilidad?

Habilita a los agentes a controlar aplicaciones móviles a través de un archivo binario local utilizando localizadores semánticos y capturar instantáneas para análisis, aprovechando listas de dispositivos con formato JSON y arrancando dispositivos específicos como el iPhone 15 Pro.

Mejor para

Perfecto para Agentes de Pruebas Automatizadas que necesitan capacidades de prueba de aplicaciones móviles avanzadas a través de archivos binarios locales.

↓ Casos de uso accionables for agent-mobile

Automatizar pruebas de aplicaciones móviles en varios dispositivos
Depurar fallos de aplicaciones y capturar pruebas
Interactuar con aplicaciones móviles utilizando referencias @eN para un análisis exhaustivo

! Seguridad y limitaciones

  • Requiere instalación de binario de agente-móvil local
  • Limitado a pruebas de aplicaciones móviles en dispositivos especificados
  • Necesita confirmación del entorno y del dispositivo objetivo antes de la prueba

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

After The Review

Decide The Next Action Before You Keep Reading Repository Material

Killer-Skills should not stop at opening repository instructions. It should help you decide whether to install this skill, when to cross-check against trusted collections, and when to move into workflow rollout.

Install Path

Start With Installation And Validation

If this skill is worth continuing with, the next step is to confirm the install command, CLI write path, and environment validation.
Trusted Recheck

Cross-Check Against Trusted Picks

If you are still comparing multiple skills or vendors, go back to the trusted collection before amplifying repository noise.
Workflow

Move To Workflow Collections For Team Rollout

When the goal shifts from a single skill to team workflows, approvals, and repeatable execution, move into workflow collections.
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is agent-mobile?

Perfecto para Agentes de Pruebas Automatizadas que necesitan capacidades de prueba de aplicaciones móviles avanzadas a través de archivos binarios locales. Resumen localizado: Mobile automation skill for the local agent-mobile CLI. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

How do I install agent-mobile?

Run the command: npx killer-skills add r0227n/agent-mobile/agent-mobile. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for agent-mobile?

Key use cases include: Automatizar pruebas de aplicaciones móviles en varios dispositivos, Depurar fallos de aplicaciones y capturar pruebas, Interactuar con aplicaciones móviles utilizando referencias @eN para un análisis exhaustivo.

Which IDEs are compatible with agent-mobile?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for agent-mobile?

Requiere instalación de binario de agente-móvil local. Limitado a pruebas de aplicaciones móviles en dispositivos especificados. Necesita confirmación del entorno y del dispositivo objetivo antes de la prueba.

↓ How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add r0227n/agent-mobile/agent-mobile. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use agent-mobile immediately in the current project.

! Reference-Only Mode

This page remains useful for installation and reference, but Killer-Skills no longer treats it as a primary indexable landing page. Read the review above before relying on the upstream repository instructions.

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

agent-mobile

Resumen localizado: Mobile automation skill for the local agent-mobile CLI. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

agent-mobile

Use this skill to drive a mobile app through the local agent-mobile binary.

Core Workflow

Every agent-mobile task should follow this loop:

  1. Confirm the environment and target device.
  2. Launch the app and capture a fresh snapshot.
  3. Interact with @eN refs or semantic locators.
  4. Wait for the next stable state.
  5. Capture another snapshot or save evidence.
bash
1agent-mobile doctor
2agent-mobile device list -f json
3agent-mobile device boot "iPhone 15 Pro"
4agent-mobile session create ios-dev --udid <UDID>
5export AGENT_MOBILE_SESSION=ios-dev
6
7agent-mobile app launch com.example.app
8agent-mobile snapshot -i
9
10agent-mobile fill @e2 "user@example.com"
11agent-mobile tap @e3
12
13agent-mobile wait text "Home" --timeout 10s
14agent-mobile snapshot -i
15agent-mobile screenshot -o artifacts/home.png

Operating Rules

  • Re-run snapshot after navigation, modal transitions, scrolling, picker changes, or any action that can invalidate @eN refs.
  • Prefer snapshot -i for tight agent loops. Use snapshot -f json, find ... -f json, get ... -f json, or other JSON-capable commands when another tool must parse the result.
  • Prefer --session or AGENT_MOBILE_SESSION once a device is selected. Fall back to --udid only for one-off commands.
  • Prefer find when refs are not known yet, the screen is dynamic, or you want a single command with an inline action such as tap, long-press, fill, or clear.
  • Use wait before asserting on UI changes. Use is when exit-code based branching is enough.
  • Save proof with screenshot or record when the user asks for verification or when a flow can fail visually.

Common Patterns

Login Flow

bash
1agent-mobile app launch com.example.app
2agent-mobile snapshot -i
3agent-mobile find placeholder "Email" fill "user@example.com"
4agent-mobile find placeholder "Password" fill "password123"
5agent-mobile find text "Sign in" tap
6agent-mobile wait text "Dashboard" --timeout 10s
7agent-mobile screenshot -o artifacts/dashboard.png

Query Before Acting

bash
1agent-mobile snapshot -f json
2agent-mobile find type Button --all -f json
3agent-mobile get text @e4 -f json

Session-Based Reuse

bash
1agent-mobile session create smoke-ios --udid <UDID>
2agent-mobile --session smoke-ios app launch com.example.app
3agent-mobile --session smoke-ios snapshot -i
4agent-mobile session show --session smoke-ios -f json

Detailed Reference

Read references/command-playbook.md when you need:

  • exact subcommand shapes for app, device, and session management
  • platform caveats such as iOS clipboard usage or Android recording limits
  • heuristics for choosing between refs, semantic locators, JSON output, and evidence capture

Habilidades relacionadas

Looking for an alternative to agent-mobile or another community skill for your workflow? Explore these related open-source skills.

Ver todo

openclaw-release-maintainer

Logo of openclaw
openclaw

Resumen localizado: 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 333.8k
⑂ 0
Inteligencia Artificial

nextjs-turbopack

[ Destacado ]
Logo of affaan-m
affaan-m

Resumen localizado: Next.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack. It covers ai-agents, anthropic, claude workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 169.5k
⑂ 0
Productividad

widget-generator

Logo of f
f

Resumen localizado: Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat . It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code, Cursor, and

★ 149.6k
⑂ 0
Inteligencia Artificial

flags

Logo of vercel
vercel

Resumen localizado: The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 138.4k
⑂ 0
Navegador