Mobile Testing

What it does

When your agent uses it

• Testing native apps
• Ensuring quality across 1000+ device variants

Example prompts

• “/mobile-testing”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1DEFINE device coverage matrix (Tier 1: 60%, Tier 2: 30%, Tier 3: 10%)
2. 2TEST platform differences (iOS ≠ Android: back button, permissions, UI)
3. 3VALIDATE touch gestures (tap, swipe, pinch, long-press)
4. 4TEST mobile-specific scenarios (offline, low battery, interruptions)
5. 5USE real devices for critical paths, emulators for fast feedback

What it can do on your machine

Read from SKILL.md and the folder at commit 829d030. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/, which the agent can run.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Mobile Testing loads about 1.3k tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 272 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~65

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from proffesor-for-testing/agentic-qe at commit 829d030, republished under its MIT licence (© proffesor-for-testing). 272 words, ~1,319 tokens.

name

mobile-testing

description

Comprehensive mobile testing for iOS and Android platforms including gestures, sensors, permissions, device fragmentation, and performance. Use when testing native apps, hybrid apps, or mobile web, ensuring quality across 1000+ device variants.

category

specialized-testing

priority

high

tokenEstimate

1000

agents

qe-test-executor, qe-performance-tester, qe-visual-tester

implementation_status

optimized

optimization_version

1

last_optimized

2025-12-02

quick_reference_card

true

tags

mobile, ios, android, appium, gestures, device-fragmentation, sensors

trust_tier

3

// Offline mode testing
test('app works offline', async () => {
  await driver.toggleAirplaneMode();

  await driver.findElement('view-saved-items').click();
  const items = await driver.findElements('saved-item');
  expect(items.length).toBeGreaterThan(0);

  const banner = await driver.findElement('offline-banner');
  expect(banner.getText()).toContain('No internet');

  await driver.toggleAirplaneMode(); // Restore
});

// Location testing
test('location-based features', async () => {
  await driver.setGeoLocation({
    latitude: 37.7749,
    longitude: -122.4194,
    altitude: 0
  });

  const stores = await driver.findElement('stores-list');
  expect(stores.getText()).toContain('San Francisco');
});

// Permission testing (Android)
test('camera permission flow', async () => {
  await driver.findElement('take-photo').click();

  // Handle permission dialog
  await driver.findElement(
    'com.android.packageinstaller:id/permission_allow_button'
  ).click();

  expect(await driver.findElement('camera-view')).toBeDefined();
});

// Cross-platform mobile testing
await Task("Mobile Test Suite", {
  platforms: ['iOS', 'Android'],
  deviceTiers: [1, 2],
  tests: 'regression-suite',
  parallelDevices: 5,
  deviceFarm: 'browserstack'
}, "qe-test-executor");

// Device farm integration
await Task("Device Farm Execution", {
  service: 'browserstack',
  devices: [
    'iPhone 15 - iOS 17',
    'Samsung Galaxy S24 - Android 14'
  ],
  recordVideo: true,
  captureNetworkLogs: true
}, "qe-test-executor");

aqe/mobile-testing/
├── device-matrix/*      - Device coverage strategy
├── platform-tests/*     - iOS/Android specific tests
├── gesture-library/*    - Reusable gesture patterns
└── performance/*        - Mobile performance metrics

const mobileFleet = await FleetManager.coordinate({
  strategy: 'mobile-testing',
  agents: [
    'qe-test-executor',       // Cross-platform execution
    'qe-performance-tester',  // Mobile performance
    'qe-visual-tester'        // Screen size validation
  ],
  topology: 'parallel'
});

© proffesor-for-testing, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts) in assets/skills/mobile-testing of proffesor-for-testing/agentic-qe.

• SKILL.md
• evals/mobile-testing.yaml
• schemas/output.json
• scripts/validate-config.json

Open the folder on GitHubat commit 829d030