Token导航 LogoToken导航TokenDH.com
研究检索external-serviceunknown未标认证来源可访问许可证需确认审计未展示

claude-mobile-ios-testingClaude mobile iOS 测试

Agent Skill

用于辅助测试设计、自动化测试、用例整理和回归验证。它适合让 Agent 编写单元测试、端到端测试、测试计划或根据失败日志定位问题。使用时需要确认项目测试框架、运行命令和夹具数据,避免为了通过测试而改坏真实逻辑;涉及浏览器或外部服务时,应区分本地模拟、测试环境和生产环境。

总安装

371

周安装

15

下载量

116
Local Agent

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:claude-mobile-ios-testing(Claude mobile iOS 测试)
来源仓库:https://smithery.ai
仓库路径:claude-mobile-ios-testing
安装命令:
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。当前暂无明确安装命令,请以来源页面说明为准。

简介

claude-mobile-ios-testing 实现 iOS 应用的自回归测试与视觉验证。

  • 适用于 Local Agent 中自动化移动端 UI 测试需求。
  • 通过 smithery.ai 平台获取,整合 expo-mcp 与 xc-mcp 技术栈。
  • 使用前需确认 React Native 组件配备 testID 属性。
  • 注意该方案依赖模拟器环境,真机测试需额外配置。

SKILL.md

iOS Testing Automation - expo-mcp + xc-mcp Hybrid

Overview

Autonomous iOS testing combining expo-mcp (React Native component testing) with xc-mcp (simulator management).

Core principle: expo-mcp for UI testing (testID-based). xc-mcp for simulator lifecycle. AI validates visually.

Announce at start: "I'm using the claude-mobile-ios-testing skill for autonomous iOS testing."

When to Use

  • Testing iOS app with visual verification (Gates 4A, 6A-E)
  • Capturing screenshots with AI analysis
  • Automating UI interactions by testID
  • Multi-device testing (iPhone SE, 14, Pro Max)
  • Verifying React Native components work correctly

Tool Selection Matrix

OperationToolWhy
Install packagesexpo-mcpCorrect Expo SDK versioning + usage docs
Search docsexpo-mcpNatural language Expo documentation search
Screenshotexpo-mcpautomation_take_screenshot (React Native level)
Find elementexpo-mcpautomation_find_view_by_testid (by testID prop)
Tap elementexpo-mcpautomation_tap_by_testid (by testID, React Native level)
Boot simulatorxc-mcpsimctl-boot (iOS simulator management)
Install.appxc-mcpsimctl-install (after xcodebuild)
Launch appxc-mcpsimctl-launch (iOS app lifecycle)
Low-level tapxc-mcpidb-ui-tap (when testID not available, use coordinates)
Accessibility treexc-mcpidb-ui-describe (iOS accessibility API)

Hybrid Workflow

1. Simulator Setup (xc-mcp)

// Boot iPhone simulator
mcp__xc-mcp__simctl-boot({
  deviceId: "iPhone 14",
  waitForBoot: true,
  openGui: true
});

2. Install and Launch (xc-mcp)

// Install .app bundle (after xcodebuild or expo run:ios)
mcp__xc-mcp__simctl-install({
  udid: "booted",
  appPath: "/Users/nick/Desktop/claude-mobile-expo/claude-code-mobile/ios/build/Build/Products/Debug-iphonesimulator/claudecodemobile.app"
});

// Launch app
mcp__xc-mcp__simctl-launch({
  udid: "booted",
  bundleId: "com.yourcompany.claudecodemobile"
});

3. Autonomous Testing (expo-mcp)

Requires: Metro running with EXPO_UNSTABLE_MCP_SERVER=1

Visual Verification:

"Take screenshot of Chat screen empty state"

AI analyzes screenshot:

  • ✅ Purple gradient background (#0f0c29→#302b63→#24243e)?
  • ✅ Input field visible?
  • ✅ Send button visible?
  • ✅ Colors match spec?

Element Verification:

"Find view with testID 'message-input' and verify it's accessible"

expo-mcp returns: {found: true, accessible: true, enabled: true}

Interaction Testing:

"Tap button with testID 'send-button'"

expo-mcp: Taps element successfully

Outcome Verification:

"Take screenshot and verify message appeared in chat"

AI analyzes: Message bubble visible ✅, correct styling ✅

4. Complete Test Cycle

// Test workflow for Chat screen
const tests = [
  "Take screenshot of Chat screen empty state, verify gradient background",
  "Find view with testID 'message-input'",
  "Tap view with testID 'message-input'",
  "Take screenshot and verify keyboard appeared",
  "Find view with testID 'settings-button'",
  "Tap button with testID 'settings-button'",
  "Take screenshot and verify Settings screen loaded",
];

for (const test of tests) {
  // AI executes test via expo-mcp prompt
  // AI analyzes result
  // AI determines pass/fail
}

testID Requirements

ALL interactive elements MUST have testID:

// ✅ CORRECT
<TouchableOpacity testID="send-button" onPress={handleSend}>
<TextInput testID="message-input" />
<Pressable testID="settings-button" onPress={openSettings}>
<FlatList testID="message-list" />

Why: expo-mcp automation_tap_by_testid and automation_find_view_by_testid require testID props

Multi-Device Testing

const devices = ["iPhone SE (3rd generation)", "iPhone 14", "iPhone 14 Pro Max"];

for (const device of devices) {
  // 1. Boot (xc-mcp)
  mcp__xc-mcp__simctl-boot({deviceId: device});

  // 2. Install and launch (xc-mcp)
  // ... (same as above)

  // 3. Test with expo-mcp
  "Take screenshot of Chat screen on ${device} and verify layout correct"

  // 4. AI verifies responsive layout

  // 5. Shutdown
  mcp__xc-mcp__simctl-shutdown({deviceId: "booted"});
}

Common Mistakes

MistakeReality
"Use npm install"WRONG. Use expo-mcp "Add package-name".
"Use xc-mcp screenshot"WRONG for RN testing. Use expo-mcp automation_take_screenshot.
"Tap by coordinates always"WRONG. Use expo-mcp automation_tap_by_testid with testID.
"Skip testID props"WRONG. Required for expo-mcp automation.
"Manual visual verification"WRONG. AI verifies screenshots autonomously.

Red Flags

  • "npm install is faster" → WRONG. expo-mcp provides correct versioning.
  • "xc-mcp screenshot is fine" → WRONG. expo-mcp works at React Native level.
  • "testIDs are optional" → WRONG. Required for autonomous testing.
  • "I'll verify manually" → WRONG. AI verifies via screenshot analysis.

All mean: Use expo-mcp for RN testing. Add testIDs. Let AI verify.

Integration

  • Use WITH: @claude-mobile-metro-manager (start Metro with MCP flag)
  • Use WITH: @claude-mobile-validation-gate (complete gate execution)
  • Provides to: Gate 4A, Gates 6A-E (visual validation)

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Local Agent

92.2%
按下载量换算107

安全审计

暂无安全审计结果可展示。

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills