jpskill.com
🛠️ 開発・MCP コミュニティ 🔴 エンジニア向け 👤 エンジニア・AI開発者

🛠️ MultiプラットフォームアプリMultiプラットフォーム

multi-platform-apps-multi-platform

APIファーストと並行開発で、ウェブ・モバイル・デスクトップ向けに同じ機能を一貫して構築・展開するSkill。

⏱ 障害ポストモーテム 1日 → 1時間

📺 まず動画で見る(YouTube)

▶ 【衝撃】最強のAIエージェント「Claude Code」の最新機能・使い方・プログラミングをAIで効率化する超実践術を解説! ↗

※ jpskill.com 編集部が参考用に選んだ動画です。動画の内容と Skill の挙動は厳密には一致しないことがあります。

📜 元の英語説明(参考)

Build and deploy the same feature consistently across web, mobile, and desktop platforms using API-first architecture and parallel implementation strategies.

🇯🇵 日本人クリエイター向け解説

一言でいうと

APIファーストと並行開発で、ウェブ・モバイル・デスクトップ向けに同じ機能を一貫して構築・展開するSkill。

※ jpskill.com 編集部が日本のビジネス現場向けに補足した解説です。Skill本体の挙動とは独立した参考情報です。

⚡ おすすめ: コマンド1行でインストール(60秒)

下記のコマンドをコピーしてターミナル(Mac/Linux)または PowerShell(Windows)に貼り付けてください。 ダウンロード → 解凍 → 配置まで全自動。

🍎 Mac / 🐧 Linux
mkdir -p ~/.claude/skills && cd ~/.claude/skills && curl -L -o multi-platform-apps-multi-platform.zip https://jpskill.com/download/3189.zip && unzip -o multi-platform-apps-multi-platform.zip && rm multi-platform-apps-multi-platform.zip
🪟 Windows (PowerShell)
$d = "$env:USERPROFILE\.claude\skills"; ni -Force -ItemType Directory $d | Out-Null; iwr https://jpskill.com/download/3189.zip -OutFile "$d\multi-platform-apps-multi-platform.zip"; Expand-Archive "$d\multi-platform-apps-multi-platform.zip" -DestinationPath $d -Force; ri "$d\multi-platform-apps-multi-platform.zip"

完了後、Claude Code を再起動 → 普通に「動画プロンプト作って」のように話しかけるだけで自動発動します。

💾 手動でダウンロードしたい(コマンドが難しい人向け)
  1. 1. 下の青いボタンを押して multi-platform-apps-multi-platform.zip をダウンロード
  2. 2. ZIPファイルをダブルクリックで解凍 → multi-platform-apps-multi-platform フォルダができる
  3. 3. そのフォルダを C:\Users\あなたの名前\.claude\skills\(Win)または ~/.claude/skills/(Mac)へ移動
  4. 4. Claude Code を再起動

⚠️ ダウンロード・利用は自己責任でお願いします。当サイトは内容・動作・安全性について責任を負いません。

🎯 このSkillでできること

下記の説明文を読むと、このSkillがあなたに何をしてくれるかが分かります。Claudeにこの分野の依頼をすると、自動で発動します。

📦 インストール方法 (3ステップ)

  1. 1. 上の「ダウンロード」ボタンを押して .skill ファイルを取得
  2. 2. ファイル名の拡張子を .skill から .zip に変えて展開(macは自動展開可)
  3. 3. 展開してできたフォルダを、ホームフォルダの .claude/skills/ に置く
    • · macOS / Linux: ~/.claude/skills/
    • · Windows: %USERPROFILE%\.claude\skills\

Claude Code を再起動すれば完了。「このSkillを使って…」と話しかけなくても、関連する依頼で自動的に呼び出されます。

詳しい使い方ガイドを見る →
最終更新
2026-05-17
取得日時
2026-05-17
同梱ファイル
1

💬 こう話しかけるだけ — サンプルプロンプト

  • Multi Platform Apps Multi Plat を使って、最小構成のサンプルコードを示して
  • Multi Platform Apps Multi Plat の主な使い方と注意点を教えて
  • Multi Platform Apps Multi Plat を既存プロジェクトに組み込む方法を教えて

これをClaude Code に貼るだけで、このSkillが自動発動します。

📖 Claude が読む原文 SKILL.md(中身を展開)

この本文は AI(Claude)が読むための原文(英語または中国語)です。日本語訳は順次追加中。

Multi-Platform Feature Development Workflow

Build and deploy the same feature consistently across web, mobile, and desktop platforms using API-first architecture and parallel implementation strategies.

[Extended thinking: This workflow orchestrates multiple specialized agents to ensure feature parity across platforms while maintaining platform-specific optimizations. The coordination strategy emphasizes shared contracts and parallel development with regular synchronization points. By establishing API contracts and data models upfront, teams can work independently while ensuring consistency. The workflow benefits include faster time-to-market, reduced integration issues, and maintainable cross-platform codebases.]

Use this skill when

  • Working on multi-platform feature development workflow tasks or workflows
  • Needing guidance, best practices, or checklists for multi-platform feature development workflow

Do not use this skill when

  • The task is unrelated to multi-platform feature development workflow
  • You need a different domain or tool outside this scope

Instructions

  • Clarify goals, constraints, and required inputs.
  • Apply relevant best practices and validate outcomes.
  • Provide actionable steps and verification.
  • If detailed examples are required, open resources/implementation-playbook.md.

Phase 1: Architecture and API Design (Sequential)

1. Define Feature Requirements and API Contracts

  • Use Task tool with subagent_type="backend-architect"
  • Prompt: "Design the API contract for feature: $ARGUMENTS. Create OpenAPI 3.1 specification with:
    • RESTful endpoints with proper HTTP methods and status codes
    • GraphQL schema if applicable for complex data queries
    • WebSocket events for real-time features
    • Request/response schemas with validation rules
    • Authentication and authorization requirements
    • Rate limiting and caching strategies
    • Error response formats and codes Define shared data models that all platforms will consume."
  • Expected output: Complete API specification, data models, and integration guidelines

2. Design System and UI/UX Consistency

  • Use Task tool with subagent_type="ui-ux-designer"
  • Prompt: "Create cross-platform design system for feature using API spec: [previous output]. Include:
    • Component specifications for each platform (Material Design, iOS HIG, Fluent)
    • Responsive layouts for web (mobile-first approach)
    • Native patterns for iOS (SwiftUI) and Android (Material You)
    • Desktop-specific considerations (keyboard shortcuts, window management)
    • Accessibility requirements (WCAG 2.2 Level AA)
    • Dark/light theme specifications
    • Animation and transition guidelines"
  • Context from previous: API endpoints, data structures, authentication flows
  • Expected output: Design system documentation, component library specs, platform guidelines

3. Shared Business Logic Architecture

  • Use Task tool with subagent_type="comprehensive-review::architect-review"
  • Prompt: "Design shared business logic architecture for cross-platform feature. Define:
    • Core domain models and entities (platform-agnostic)
    • Business rules and validation logic
    • State management patterns (MVI/Redux/BLoC)
    • Caching and offline strategies
    • Error handling and retry policies
    • Platform-specific adapter patterns Consider Kotlin Multiplatform for mobile or TypeScript for web/desktop sharing."
  • Context from previous: API contracts, data models, UI requirements
  • Expected output: Shared code architecture, platform abstraction layers, implementation guide

Phase 2: Parallel Platform Implementation

4a. Web Implementation (React/Next.js)

  • Use Task tool with subagent_type="frontend-developer"
  • Prompt: "Implement web version of feature using:
    • React 18+ with Next.js 14+ App Router
    • TypeScript for type safety
    • TanStack Query for API integration: [API spec]
    • Zustand/Redux Toolkit for state management
    • Tailwind CSS with design system: [design specs]
    • Progressive Web App capabilities
    • SSR/SSG optimization where appropriate
    • Web vitals optimization (LCP < 2.5s, FID < 100ms) Follow shared business logic: [architecture doc]"
  • Context from previous: API contracts, design system, shared logic patterns
  • Expected output: Complete web implementation with tests

4b. iOS Implementation (SwiftUI)

  • Use Task tool with subagent_type="ios-developer"
  • Prompt: "Implement iOS version using:
    • SwiftUI with iOS 17+ features
    • Swift 5.9+ with async/await
    • URLSession with Combine for API: [API spec]
    • Core Data/SwiftData for persistence
    • Design system compliance: [iOS HIG specs]
    • Widget extensions if applicable
    • Platform-specific features (Face ID, Haptics, Live Activities)
    • Testable MVVM architecture Follow shared patterns: [architecture doc]"
  • Context from previous: API contracts, iOS design guidelines, shared models
  • Expected output: Native iOS implementation with unit/UI tests

4c. Android Implementation (Kotlin/Compose)

  • Use Task tool with subagent_type="mobile-developer"
  • Prompt: "Implement Android version using:
    • Jetpack Compose with Material 3
    • Kotlin coroutines and Flow
    • Retrofit/Ktor for API: [API spec]
    • Room database for local storage
    • Hilt for dependency injection
    • Material You dynamic theming: [design specs]
    • Platform features (biometric auth, widgets)
    • Clean architecture with MVI pattern Follow shared logic: [architecture doc]"
  • Context from previous: API contracts, Material Design specs, shared patterns
  • Expected output: Native Android implementation with tests

4d. Desktop Implementation (Optional - Electron/Tauri)

  • Use Task tool with subagent_type="frontend-mobile-development::frontend-developer"
  • Prompt: "Implement desktop version using Tauri 2.0 or Electron with:
    • Shared web codebase where possible
    • Native OS integration (system tray, notifications)
    • File system access if needed
    • Auto-updater functionality
    • Code signing and notarization setup
    • Keyboard shortcuts and menu bar
    • Multi-window support if applicable Reuse web components: [web implementation]"
  • Context from previous: Web implementation, desktop-specific requirements
  • Expected output: Desktop application with platform packages

Phase 3: Integration and Validation

5. API Documentation and Testing

  • Use Task tool with subagent_type="documentation-generation::api-documenter"
  • Prompt: "Create comprehensive API documentation including:
    • Interactive OpenAPI/Swagger documentation
    • Platform-specific integration guides
    • SDK examples for each platform
    • Authentication flow diagrams
    • Rate limiting and quota information
    • Postman/Insomnia collections
    • WebSocket connection examples
    • Error handling best practices
    • API versioning strategy Test all endpoints with platform implementations."
  • Context from previous: Implemented platforms, API usage patterns
  • Expected output: Complete API documentation portal, test results

6. Cross-Platform Testing and Feature Parity

  • Use Task tool with subagent_type="unit-testing::test-automator"
  • Prompt: "Validate feature parity across all platforms:
    • Functional testing matrix (features work identically)
    • UI consistency verification (follows design system)
    • Performance benchmarks per platform
    • Accessibility testing (platform-specific tools)
    • Network resilience testing (offline, slow connections)
    • Data synchronization validation
    • Platform-specific edge cases
    • End-to-end user journey tests Create test report with any platform discrepancies."
  • Context from previous: All platform implementations, API documentation
  • Expected output: Test report, parity matrix, performance metrics

7. Platform-Specific Optimizations

  • Use Task tool with subagent_type="application-performance::performance-engineer"
  • Prompt: "Optimize each platform implementation:
    • Web: Bundle size, lazy loading, CDN setup, SEO
    • iOS: App size, launch time, memory usage, battery
    • Android: APK size, startup time, frame rate, battery
    • Desktop: Binary size, resource usage, startup time
    • API: Response time, caching, compression Maintain feature parity while leveraging platform strengths. Document optimization techniques and trade-offs."
  • Context from previous: Test results, performance metrics
  • Expected output: Optimized implementations, performance improvements

Configuration Options

  • --platforms: Specify target platforms (web,ios,android,desktop)
  • --api-first: Generate API before UI implementation (default: true)
  • --shared-code: Use Kotlin Multiplatform or similar (default: evaluate)
  • --design-system: Use existing or create new (default: create)
  • --testing-strategy: Unit, integration, e2e (default: all)

Success Criteria

  • API contract defined and validated before implementation
  • All platforms achieve feature parity with <5% variance
  • Performance metrics meet platform-specific standards
  • Accessibility standards met (WCAG 2.2 AA minimum)
  • Cross-platform testing shows consistent behavior
  • Documentation complete for all platforms
  • Code reuse >40% between platforms where applicable
  • User experience optimized for each platform's conventions

Platform-Specific Considerations

Web: PWA capabilities, SEO optimization, browser compatibility iOS: App Store guidelines, TestFlight distribution, iOS-specific features Android: Play Store requirements, Android App Bundles, device fragmentation Desktop: Code signing, auto-updates, OS-specific installers

Initial feature specification: $ARGUMENTS

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.