Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Imported from borghei/claude-skills
.claude/skills/borghei-senior-mobile/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -32% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 113% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 90% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -33% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 269% | 0% |
Expert mobile application development across iOS, Android, React Native, and Flutter — scaffolding production projects, building MVVM features (SwiftUI, Jetpack Compose, Expo Router), static performance analysis, and App Store / Play Store submission.
mobile, ios, android, react-native, flutter, swift, kotlin, swiftui, jetpack-compose, expo-router, zustand, app-store, performance, offline-first
@MainActor ViewModels, Compose sealed UiState + StateFlow, Zustand stores.Before scaffolding, confirm these inputs. If any is unknown or vague, ASK — do not assume:
--platform; an entirely different scaffold)--state; changes the generated architecture)mobile_scaffold / store_metadata_generator / app_performance_analyzer)Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
| Tool | Purpose | Command | |------|---------|---------| | mobile_scaffold.py | Scaffold a project for react-native, flutter, ios-native, or android-native | python scripts/mobile_scaffold.py MyApp --platform react-native --state zustand | | store_metadata_generator.py | Generate App Store / Play Store listing metadata | python scripts/store_metadata_generator.py --app-name FitTrack --category health --features "workout,tracking" | | app_performance_analyzer.py | Static performance analysis (score, issues, bundle estimate) | python scripts/app_performance_analyzer.py ./my-app --platform react-native |
Load the reference that matches the task — keep this file lean and pull detail on demand:
This skill covers:
This skill does NOT cover:
senior-backend and senior-fullstack skills).senior-devops and release-orchestrator skills).senior-frontend and design-auditor skills).| Skill | Integration | Data Flow | |-------|-------------|-----------| | senior-frontend | Shared component patterns, styling conventions, and responsive design principles for React Native web targets | Frontend design tokens and component APIs feed into mobile UI components | | senior-backend | API contract definitions, authentication flows, and data models consumed by mobile clients | Backend OpenAPI specs define mobile service layer interfaces | | senior-devops | Build pipelines, code signing automation, and deployment workflows for mobile releases | Mobile build artifacts flow into CI/CD pipelines for TestFlight / Play Console distribution | | senior-qa | Test strategy alignment, device matrix coverage, and E2E testing patterns for mobile screens | QA test plans drive device coverage; mobile scaffold includes test directory structure | | senior-security | Secure storage patterns (Keychain/Keystore), certificate pinning, and data encryption for mobile apps | Security requirements inform Keychain helper implementation and network client configuration | | release-orchestrator | Version bumping, changelog generation, and coordinated release across iOS and Android | Release metadata and version info flow from orchestrator into store submission workflow |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-10 | fail→fail | 15,721 | 14,141 | -10% | 1 | 1 | 0% | 2,892 | 3,985 | +38% | 0 | 0 | — |
case-01 | fail→fail | 3,523 | 25,613 | +627% | 1 | 1 | 0% | 384 | 5,743 | +1396% | 0 | 0 | — |
case-02 | fail→pass | 17,398 | 2,651 | -85% | 1 | 1 | 0% | 2,757 | 1,861 | -32% | 0 | 0 | — |
case-03 | fail→pass | 6,377 | 4,294 | -33% | 1 | 1 | 0% | 1,006 | 2,147 | +113% | 0 | 0 | — |
case-04 | fail→pass | 10,327 | 12,286 | +19% | 1 | 1 | 0% | 1,809 | 3,429 | +90% | 0 | 0 | — |
case-05 | pass→pass | 4,015 | 4,454 | +11% | 1 | 1 | 0% | 589 | 2,176 | +269% | 0 | 0 | — |
case-06 | pass→pass | 7,850 | 5,447 | -31% | 1 | 1 | 0% | 1,335 | 2,393 | +79% | 0 | 0 | — |
case-07 | pass→pass | 11,979 | 7,509 | -37% | 1 | 1 | 0% | 1,872 | 2,646 | +41% | 0 | 0 | — |
case-08 | fail→pass | 20,567 | 6,941 | -66% | 1 | 1 | 0% | 3,684 | 2,464 | -33% | 0 | 0 | — |
case-09 | pass→pass | 12,533 | 7,813 | -38% | 1 | 1 | 0% | 1,894 | 2,590 | +37% | 0 | 0 | — |
case-11 | fail→fail | 13,344 | 16,600 | +24% | 1 | 1 | 0% | 2,617 | 4,635 | +77% | 0 | 0 | — |
case-12 | fail→fail | 20,866 | 29,454 | +41% | 1 | 1 | 0% | 3,710 | 6,792 | +83% | 0 | 0 | — |
case-13 | pass→pass | 8,583 | 5,029 | -41% | 1 | 1 | 0% | 1,266 | 2,220 | +75% | 0 | 0 | — |
case-14 | pass→pass | 8,929 | 7,478 | -16% | 1 | 1 | 0% | 1,547 | 2,869 | +85% | 0 | 0 | — |
case-15 | pass→pass | 11,006 | 10,026 | -9% | 1 | 1 | 0% | 1,896 | 3,133 | +65% | 0 | 0 | — |
case-16 | pass→pass | 12,223 | 5,362 | -56% | 1 | 1 | 0% | 1,871 | 2,273 | +21% | 0 | 0 | — |
case-17 | pass→pass | 4,223 | 3,517 | -17% | 1 | 1 | 0% | 513 | 1,977 | +285% | 0 | 0 | — |
case-18 | pass→pass | 4,805 | 5,233 | +9% | 1 | 1 | 0% | 645 | 2,321 | +260% | 0 | 0 | — |
case-19 | pass→pass | 7,834 | 2,850 | -64% | 1 | 1 | 0% | 1,162 | 1,889 | +63% | 0 | 0 | — |
case-20 | pass→pass | 4,978 | 1,793 | -64% | 1 | 1 | 0% | 687 | 1,714 | +149% | 0 | 0 | — |
case-21 | pass→pass | 7,042 | 7,612 | +8% | 1 | 1 | 0% | 1,080 | 2,623 | +143% | 0 | 0 | — |
case-22 | pass→pass | 18,457 | 19,513 | +6% | 1 | 1 | 0% | 2,675 | 4,788 | +79% | 0 | 0 | — |
case-23 | pass→pass | 18,087 | 10,973 | -39% | 1 | 1 | 0% | 2,817 | 3,271 | +16% | 0 | 0 | — |
case-24 | pass→pass | 6,439 | 1,877 | -71% | 1 | 1 | 0% | 927 | 1,755 | +89% | 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. 24 cases were attempted. The headline lift of +17 percentage points is the difference between those two pass rates over the 24 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.