開發

This skill should be used when the user asks to "create terraform configuration", "deploy static site", "set up cloudfront", "configure route53", "create lambda function", "ssl certificate", or mentions S3 website hosting, CDN, serverless, JAMstack, or static site infrastructure.

Coordinate multiple agents by routing tasks to appropriate specialists. EXCLUSIVE to project-manager agent.

Validates code quality before commits in the MigraineTracker React Native project. Use this skill when preparing to commit code, before pushing changes, or when the user asks to run pre-commit checks. Ensures TypeScript type safety, test coverage (80%+), passing tests, and proper branch strategy compliance.

Create distinctive, memorable UI for landing pages, portfolios, marketing sites, and one-off creative work. Use when the user explicitly wants something "distinctive", "creative", "memorable", or "unique" - NOT for standard app components where consistency matters.

Write tests following 3-layer pyramid (unit 95%, integration 85%, E2E critical paths) with 1:1 file mapping for unit tests. Covers test organization, coverage requirements, fixtures, and best practices. Use when writing tests, checking coverage, or validating test structure.

Testing StickerNest widgets and components. Use when the user asks to test widgets, write tests, add tests, create test cases, run tests, debug tests, or verify widget functionality. Covers Playwright E2E tests, Vitest unit tests, widget integration testing, and pipeline testing.

Expert photography composition critic grounded in graduate-level visual aesthetics education, computational aesthetics research (AVA, NIMA, LAION-Aesthetics, VisualQuality-R1), and professional image analysis with custom tooling. Use for image quality assessment, composition analysis, aesthetic scoring, photo critique. Activate on "photo critique", "composition analysis", "image aesthetics", "NIMA", "AVA dataset", "visual quality". NOT for photo editing/retouching (use native-app-designer), generating images (use Stability AI directly), or basic image processing (use clip-aware-embeddings).

Structured code debugging through hypothesis formation and falsification planning. Use when diagnosing bugs, unexpected behaviour, or system failures where the root cause is unclear. Produces a hypothesis document for execution by another agent rather than performing the investigation directly. Triggers on requests to debug issues, diagnose problems, investigate failures, or create debugging plans.

Vite SPA deployment to various platforms. Use when deploying React SPAs.

Build responsive layouts that adapt seamlessly across devices using mobile-first design, fluid layouts, and standard breakpoints. Use this skill when implementing responsive designs, creating mobile-first layouts, defining breakpoint styles, working with responsive components and pages, using relative units (rem, em) instead of fixed pixels, implementing media queries, ensuring touch-friendly tap targets, optimizing images and assets for different screen sizes, maintaining readable typography across breakpoints, prioritizing content for smaller screens, testing UI across mobile, tablet, and desktop devices, or building fluid container layouts. Apply this skill when building responsive UI components, optimizing layouts for different screen sizes, or reviewing mobile and tablet user experiences.

Build Gemini Deep Research agents using the Interactions API. Use when creating autonomous research agents, implementing multi-step information gathering, building research report generators, or integrating Gemini's Deep Research capabilities into applications. Handles polling, streaming, file integration, and report synthesis.

Copies an existing landing page (from URL or image) into a specified page in the codebase using Playwright MCP. Iteratively refines the implementation until it matches the reference design and interactions as closely as possible. Use when the user wants to copy/reference/steal an existing landing page/url to replicate in their app

Create and use iOS simulator development builds with EAS for Expo/React Native apps. Use when setting up simulator-only profiles, building, installing, and running dev clients on iOS simulators.

Enterprise systematic code review orchestrator with TRUST 5 principles, multi-language support, Context7 integration, AI-powered quality checks, SOLID principle validation, security vulnerability detection, and maintainability analysis across 25+ programming languages; activates for code reviews, quality standard validation, TRUST 5 enforcement, architectural audits, and automated review automation

Polibaseのデータ処理ワークフローとパイプラインを説明します。議事録処理、Web scraping、政治家データ収集、話者マッチングなどの処理フロー、依存関係、実行順序を理解する際にアクティベートされます。

Plan and implement CDN deployment of built WebF app assets (Vercel/Netlify/S3+CloudFront/GitHub Pages), including cache headers and verification. Use when the user mentions CDN, cache headers, S3/CloudFront, Vercel, Netlify, GitHub Pages, or deploying build output.

Enterprise Mermaid diagramming skill for Claude Code using MCP Playwright. Use when creating architecture diagrams, flowcharts, sequence diagrams, or visual documentation.

Expert system for reviewing utility patent applications against USPTO MPEP guidelines.

Suite of tools for creating Practice Hub UI components and artifacts using the project's design system (React, Tailwind CSS, shadcn/ui, glass-card patterns). Use for building UI components that match Practice Hub's established design patterns and conventions.

Azure Key Vault + CSI Driver integration for Kubernetes secrets management. Use when creating SecretProviderClass resources, mounting secrets from Key Vault, troubleshooting 403 errors, syncing secrets to K8s, or configuring applications to use Key Vault secrets.