行動開發

Use this skill whenever the user wants to design, run, or refine Cloudflare D1 schema management, migrations, and data seeding for dev/staging/production environments, especially in conjunction with Hono/Workers apps.

Use when elements need to appear on screen - page loads, modals opening, items being added, content reveals, or any "coming into view" animation.

Robust error handling patterns for TypeScript applications

Use when saving notes to Obsidian vault, creating documentation, capturing knowledge, or logging any information. This skill determines the correct PARA location and applies the appropriate template from the vault.

Maintain living documentation with single source of truth approach, journal reconciliation, and worklog.db integration

QA engineer and test automation specialist with deep expertise in Flutter testing. Use for designing test strategies, writing unit/widget/integration tests, improving test coverage, and ensuring code reliability.

Routes to appropriate deep-RL skills based on problem type and algorithm family

Generate pytest tests with parametrization, shared fixtures, minimal mocking. Use for unit tests and test coverage. Follows 1-1 file mapping and real object testing.

Plan what to measure in AI agent systems using tiered approach

Create, update, and review code-map and spec documents for features. Use this skill to document code execution flows, trace function calls, and maintain architectural documentation in docs/2-current/.

Kotlin syntax, coroutines, scope functions, and functional programming. Use when working with Kotlin code.

iOSアプリのデザイン哲学とクリエイティブディレクション。Apple Human Interface Guidelinesに基づくClarity/Deference/Depthの原則、SwiftUIによる実装パターン、アクセシビリティ設計を包括的にガイド。使用タイミング: (1) 新規アプリのUI/UX設計時、(2) デザインシステム構築時、(3) SwiftUIコンポーネント設計時、(4) 「iOSらしいデザインにしたい」「HIGに準拠したい」、(5) アクセシビリティ対応時、(6) アニメーション・インタラクション設計時、(7) 複数プラットフォーム（iOS/iPadOS/watchOS/visionOS）対応時

スナップショットテスト支援。swift-snapshot-testing、UI変更検出。使用タイミング: (1) UIコンポーネントのリグレッションテスト、(2) デザインシステムの検証、(3) 複数デバイス・ダークモード対応の確認、(4) UIリファクタリング時の安全性確保

Use after proposal approval to break work into 2-5 minute tasks with exact file paths and code examples. Each task must be completable by an agent with zero context. Do NOT use before proposal is approved.

Single source of truth for MetaSaver agent selection and subagent_type mapping

Master ES6+ features including async/await, destructuring, spread operators, arrow functions, promises, modules, iterators, generators, and functional programming patterns for writing clean, efficient JavaScript code. Use when refactoring legacy code, implementing modern patterns, or optimizing JavaScript applications.

Manage Things 3 tasks, projects, and areas using the thangs CLI. Supports listing, adding, editing, completing, and canceling tasks with intelligent filtering and organization.

Control Chrome browser through MCP for testing, debugging, network analysis, and performance profiling. Use when testing web apps, measuring Core Web Vitals, analyzing network requests, debugging console errors, or when the user mentions Chrome DevTools, performance traces, or browser automation.

Enterprise Vercel Edge Platform with AI-powered modern deployment, Context7 integration, and intelligent edge orchestration for scalable web applications

Apply chronicle event effects to world state. Use when events need to modify entities (battles change force strength, treaties change relationships, deaths remove agents). This is the core simulation engine.