Install any skill in seconds. Free to start, no credit card required.
Get Started Free →21 production-ready scripts for iOS app testing, building, and automation. Provides semantic UI navigation, build automation, accessibility testing, and simulator lifecycle management. Optimized for AI agents with minimal token output.
.claude/skills/microck-ios-simulator-skill/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 81% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 104% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 129% | 0% |
Build, test, and automate iOS applications using accessibility-driven navigation and structured data instead of pixel coordinates.
bash# 1. Check environment bash scripts/sim_health_check.sh # 2. Launch app python scripts/app_launcher.py --launch com.example.app # 3. Map screen to see elements python scripts/screen_mapper.py # 4. Tap button python scripts/navigator.py --find-text "Login" --tap # 5. Enter text python scripts/navigator.py --find-type TextField --enter-text "user@example.com"
All scripts support --help for detailed options and --json for machine-readable output.
--project, --scheme, --clean, --test, --verbose, --json--app, --severity, --follow, --duration, --output, --json--verbose, --hints, --json--find-text, --find-type, --find-id, --tap, --enter-text, --json--swipe, --scroll, --pinch, --long-press, --refresh, --json--type, --key, --button, --slow, --clear, --dismiss, --json--launch, --terminate, --install, --uninstall, --open-url, --list, --state, --json--verbose, --output, --json--threshold, --output, --details, --json--test-name, --output, --verbose, --json--app-bundle-id, --output, --log-lines, --json--copy, --test-name, --expected, --json--preset, --time, --data-network, --battery-level, --clear, --json--bundle-id, --title, --body, --badge, --payload, --json--bundle-id, --grant, --revoke, --reset, --list, --json--udid, --name, --wait-ready, --timeout, --all, --type, --json--udid, --name, --verify, --timeout, --all, --type, --json--device, --runtime, --name, --list-devices, --list-runtimes, --json--udid, --name, --yes, --all, --type, --old, --json--udid, --name, --verify, --timeout, --all, --type, --booted, --jsonAuto-UDID Detection: Most scripts auto-detect the booted simulator if --udid is not provided.
Device Name Resolution: Use device names (e.g., "iPhone 16 Pro") instead of UDIDs - scripts resolve automatically.
Batch Operations: Many scripts support --all for all simulators or --type iPhone for device type filtering.
Output Formats: Default is concise human-readable output. Use --json for machine-readable output in CI/CD.
Help: All scripts support --help for detailed options and examples.
bash scripts/sim_health_check.shpython scripts/app_launcher.py --launch com.example.apppython scripts/screen_mapper.pypython scripts/navigator.py --find-text "Button" --tappython scripts/accessibility_audit.pypython scripts/app_state_capture.py --app-bundle-id com.example.appSemantic Navigation: Find elements by meaning (text, type, ID) not pixel coordinates. Survives UI changes.
Token Efficiency: Concise default output (3-5 lines) with optional verbose and JSON modes for detailed results.
Accessibility-First: Built on standard accessibility APIs for reliability and compatibility.
Zero Configuration: Works immediately on any macOS with Xcode. No setup required.
Structured Data: Scripts output JSON or formatted text, not raw logs. Easy to parse and integrate.
Auto-Learning: Build system remembers your device preference. Configuration stored per-project.
Use these scripts directly or let Claude Code invoke them automatically when your request matches the skill description.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 5,021 | 6,933 | +38% | 1 | 1 | 0% | 902 | 2,537 | +181% | 0 | 0 | — |
case-02 | fail→fail | 6,234 | 4,849 | -22% | 1 | 1 | 0% | 1,003 | 2,489 | +148% | 0 | 0 | — |
case-03 | fail→fail | 7,412 | 7,903 | +7% | 1 | 1 | 0% | 1,310 | 2,637 | +101% | 0 | 0 | — |
case-04 | fail→pass | 9,336 | 3,423 | -63% | 1 | 1 | 0% | 1,566 | 2,840 | +81% | 0 | 0 | — |
case-05 | fail→pass | 7,896 | 3,472 | -56% | 1 | 1 | 0% | 1,338 | 2,726 | +104% | 0 | 0 | — |
case-06 | fail→pass | 15,080 | 3,400 | -77% | 1 | 1 | 0% | 2,602 | 2,713 | +4% | 0 | 0 | — |
case-07 | fail→pass | 10,669 | 2,623 | -75% | 1 | 1 | 0% | 1,880 | 2,656 | +41% | 0 | 0 | — |
case-08 | fail→pass | 7,073 | 3,372 | -52% | 1 | 1 | 0% | 1,264 | 2,895 | +129% | 0 | 0 | — |
case-09 | fail→fail | 23,192 | 6,182 | -73% | 1 | 1 | 0% | 4,445 | 2,465 | -45% | 0 | 0 | — |
case-10 | fail→fail | 15,612 | 6,676 | -57% | 1 | 1 | 0% | 2,275 | 2,476 | +9% | 0 | 0 | — |
case-11 | fail→fail | 19,138 | 5,990 | -69% | 1 | 1 | 0% | 3,011 | 2,479 | -18% | 0 | 0 | — |
case-12 | fail→pass | 19,880 | 5,171 | -74% | 1 | 1 | 0% | 3,882 | 2,525 | -35% | 0 | 0 | — |
case-13 | fail→fail | 14,320 | 5,261 | -63% | 1 | 1 | 0% | 2,718 | 2,487 | -8% | 0 | 0 | — |
case-18 | fail→fail | 16,945 | 5,506 | -68% | 1 | 1 | 0% | 2,948 | 2,466 | -16% | 0 | 0 | — |
case-14 | fail→fail | 5,496 | 4,694 | -15% | 1 | 1 | 0% | 797 | 2,478 | +211% | 0 | 0 | — |
case-15 | fail→fail | 9,828 | 5,711 | -42% | 1 | 1 | 0% | 984 | 2,558 | +160% | 0 | 0 | — |
case-16 | fail→fail | 7,528 | 5,689 | -24% | 1 | 1 | 0% | 1,351 | 2,417 | +79% | 0 | 0 | — |
case-17 | fail→fail | 4,239 | 5,652 | +33% | 1 | 1 | 0% | 779 | 2,511 | +222% | 0 | 0 | — |
case-19 | pass→pass | 10,512 | 6,024 | -43% | 1 | 1 | 0% | 1,885 | 3,201 | +70% | 0 | 0 | — |
case-20 | pass→pass | 10,798 | 7,312 | -32% | 1 | 1 | 0% | 1,865 | 3,579 | +92% | 0 | 0 | — |
case-21 | pass→pass | 8,638 | 5,780 | -33% | 1 | 1 | 0% | 1,346 | 3,087 | +129% | 0 | 0 | — |
case-22 | fail→fail | 3,317 | 5,278 | +59% | 1 | 1 | 0% | 477 | 2,459 | +416% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 10 counted toward the lift figure. The other 12 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +27 percentage points is the difference between those two pass rates over the 10 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.