thkt/claude-config

Access Google Sheets and Docs via gcloud CLI. Use when user shares a Google Sheets/Docs URL or mentions スプレッドシート, Sheets, Docs, Google ドキュメント.

Root cause analysis with 5 Whys methodology. Use when investigating bugs, analyzing failures, or when user mentions root cause, 5 Whys, なぜなぜ分析, 根本原因, 原因分析, symptom fix, 対症療法.

Fundamental software principles - SOLID, DRY, Occam's Razor, Miller's Law, YAGNI, Readable Code. Use when applying design principles, refactoring code, or when user mentions 原則, シンプル, 複雑, リファクタリング, 保守性, clean code, best practice.

Framework-agnostic frontend component design patterns. Use when designing React/Vue/Angular components, applying Container/Presentational pattern, or when user mentions component patterns, フロントエンドパターン, コンポーネント設計.

Browser automation using agent-browser CLI. Best for E2E testing, demos, screenshots. Use when automating browser interactions, creating E2E tests, or when user mentions browser automation, E2E test, ブラウザ操作, スクリーンショット, demo, manual testing.

Consult Google Gemini CLI for plan review, implementation check, and research. Use when needing second opinion on plans, verifying implementation approach, or when user mentions 計画レビュー, 実装確認, 調査依頼, Geminiに相談.

Structured ADR creation in MADR format. Use when creating architecture decision records, documenting technology choices, or when user mentions ADR, Architecture Decision, 決定記録, 技術選定, アーキテクチャ決定, deprecation, 非推奨化.

Generate API specification from codebase - endpoints, types, schemas. Use when generating API documentation, documenting endpoints, or when user mentions API docs, API仕様, OpenAPI, Swagger, REST API, endpoint documentation.

Generate architecture overview documentation from codebase analysis. Uses tree-sitter-analyzer for precise code structure extraction. Use when documenting project structure, creating architecture diagrams, or when user mentions architecture overview, project structure, アーキテクチャ, 構成図.

Generate domain documentation from codebase analysis - entities, glossary, relationships. Use when analyzing domain models, creating glossaries, or when user mentions domain model, entity diagram, ドメインモデル, 用語集, glossary, ubiquitous language.

Generate environment setup guide documentation from codebase analysis. Detects package managers, required tools, environment variables, and startup commands. Use when creating setup guides, documenting environments, or when user mentions setup guide, environment setup, 環境構築, 開発環境.

CSS-first approach - use CSS before JavaScript. Use when implementing layouts, animations, or toggles, or when user mentions レイアウト, スタイル, 位置, アニメーション, 表示/非表示, トグル, レスポンシブ, CSS Grid, Flexbox, transforms, transitions, CSSのみ, JavaScript不要, シンプル

Design document review format with 100-point scoring system for SOW/Spec. Use when reviewing SOW or Spec documents, scoring design quality, or when user mentions SOW review, Spec review, 設計書レビュー, 品質スコア, document scoring.

TDD with RGRC cycle and Baby Steps methodology. Use when implementing features with test-driven development, following RGRC cycle, or when user mentions TDD, テスト駆動, Red-Green-Refactor, Baby Steps.

Storybook integration with spec.md. Auto-generates Stories from Component API. Use when creating Storybook stories, defining component APIs, or when user mentions storybook, stories, props, argTypes, variants, CSF3.

Frontend performance optimization with data-driven approach. Use when optimizing page load times, improving Web Vitals, or when user mentions performance, Web Vitals, LCP, FID, CLS, パフォーマンス最適化, 速度改善, bundle size.

Command workflow orchestration patterns for /code, /fix, /audit, and other implementation commands. Use when implementing features with /code, /fix, /audit commands, or when user mentions workflow, ワークフロー, RGRC, quality gates, 品質ゲート, completion criteria.

Silent failure detection patterns for frontend code. Use when reviewing error handling, detecting swallowed errors, or when user mentions silent failure, empty catch, エラーハンドリング, 握りつぶし, swallowed error.

Testable code design patterns for TypeScript/React applications. Use when reviewing code for testability, implementing dependency injection, or when user mentions テスト容易性, モック, mock-friendly, DI.

TypeScript type safety patterns and best practices for maximum type coverage. Use when reviewing TypeScript code for type issues, eliminating `any` types, or when user mentions type safety, 型安全, 型カバレッジ, strict mode.

Plugin and skill security scanner for detecting malicious code and instructions. Supports local paths and GitHub repositories. Use when scanning plugins before installation, auditing external skills, or when user mentions plugin scan, security scan, GitHub repo scan, プラグインスキャン, 安全性チェック.

CLI tools guide for git, gh, npm, and other development tools. Use when executing git commands, managing branches, or when user mentions CLI, コマンドライン, バージョン管理, ブランチ, コミット.

LLM-optimized documentation fetching using llms.txt standard. Use when fetching external documentation, API references, library docs, or when user mentions ドキュメント参照, 公式ドキュメント, API docs, library documentation.

Git worktree management via wt CLI (claude-worktree). Use when user mentions worktree, ワークツリー, 並行開発, parallel branch, or wants to create/switch/list/remove worktrees.

React and Next.js performance optimization guidelines from Vercel Engineering. Use when writing, reviewing, or refactoring React/Next.js code, improving Web Vitals, or when user mentions React performance, Next.js optimization, bundle size, data fetching.

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".