Claude Code

Claude Code workflow tips from Boris Cherny (creator of Claude Code) and the Claude Code team. Use when: setting up Claude Code, optimizing workflows, running parallel sessions, configuring CLAUDE.md, using skills/commands, subagents, hooks, MCP integrations, or learning best practices. Covers: git worktrees, plan mode, verification, permissions, Slack MCP, BigQuery, prompting tips, plugins, custom agents, sandboxing, keybindings, status lines, output styles, and customization.

Execute semantic git commits with individual file staging, prefix selection, and split-commit enforcement. Use when committing code, managing git history, or when user mentions git/commit/push.

Intelligently select and use the most appropriate search tool based on search intent. Use when searching for information, whether web content, local files, locations, or specific data. Automatically chooses between WebSearch, Brave Search, Firecrawl, Desktop Commander, or other search MCPs.

Claude Codeの最新CHANGELOGを取得し、変更内容を日本語で解説する。ユーザーがClaude Codeの更新内容、最新バージョン、リリースノートについて聞いたときに使う。

Execute a complete feature development workflow from research to PR creation. Use when starting new feature development, implementing tasks, or when the user mentions "機能開発ワークフロー", "feature workflow", or "開発プロセス実行".

Run external Ralph Loop (Geoffrey Huntley method) with clean context per iteration. Supports Simple mode (single PROMPT.md) and Full Ecosystem mode (specs/, fix_plan.md, AGENT.md, plan/build prompts). Unlike the official ralph-loop plugin which uses Stop hooks (same session, context pollution), this spawns fresh `claude -p` sessions each iteration. Use when user mentions "camone-ralph-loop", "external ralph", "clean ralph loop", "外部ラルフ", "ラルフループ実行", or wants to run iterative AI development with isolated context windows.

Perform comprehensive web page quality audits using Chrome DevTools MCP including responsive layout verification, interactive element testing, console/network error detection, and accessibility checks. Use when user mentions "quality check", "UI check", "page audit", "responsive check", "deploy check", or asks to verify a web page before deployment. Also triggers on Japanese terms like "品質チェック", "UIチェック", "表示確認", "デプロイ前確認", "レスポンシブ確認", "アクセシビリティ確認".

Detect project tech stack and generate a comprehensive, production-grade .gitignore. Covers 15+ languages, 20+ frameworks, security patterns, modern tooling, and monorepo support.

Manage implementation logs in _docs/templates/ with consistent format. Use when starting project work, completing implementations, or when user mentions 実装ログ/implementation log.

Generate detailed, agent-executable feature specifications by interviewing the user with AskUserQuestionTool. Transforms rough ideas into comprehensive SPEC.md files through phased deep interviews (5 phases) covering technical architecture, data design, API design, UI/UX, edge cases, security, performance, and tradeoffs. Produces hybrid specs with Acceptance Criteria and phased implementation tasks with dependencies. Use when user mentions "spec", "仕様書作成", "仕様駆動", "インタビューして", "SPEC.md", "feature spec", "仕様を書いて", "大きな機能を計画", or wants to plan a feature before implementation.

Guide Test-Driven Development with task splitting, Red-Green-Refactor cycle, and framework auto-detection. Use when developing features with TDD approach, fixing bugs test-first, or when user mentions "TDD", "テスト駆動開発", "test-first", "/tdd".

Install MCP servers into the current project scope using claude mcp add. Use when setting up a new project, when user mentions MCP setup, project MCP, MCPインストール, MCPセットアップ, or /installing-project-mcps.

プロジェクトの .claude/settings.json にPostToolUseフック（prettier, eslint等）を設定する。Use when user mentions hooks設定/フック設定/formatter hooks/PostToolUse/setup-hooks/setup-post-tool-use-hooks.

Orchestrate a comprehensive TDD workflow with multi-agent Red-Green-Refactor discipline, phase gates, and coverage validation. Use when user mentions "tdd-cycle", "TDDサイクル", "厳密なTDD", "TDDオーケストレーション", or needs strict test-first development with automated quality checks.

Create a git worktree via gtr (git-worktree-runner) for a GitHub issue and generate a CLAUDE.local.md with issue context so that Claude Code launched in that worktree knows what to work on. Issue-specific context is written to CLAUDE.local.md (not .claude/CLAUDE.md) to avoid Git conflicts when merging PRs from multiple worktrees. Use when user mentions "gtr issue", "issue worktree", "issueでworktree", "issueに着手", "gtr-issue", or wants to set up an isolated worktree for a specific GitHub issue. Requires: gtr (git-worktree-runner) and gh CLI installed.

Create distinctive, production-grade frontend interfaces with high design quality that avoid generic AI aesthetics. Adapt to ANY aesthetic direction the user provides. Use when building web components, pages, or applications (websites, landing pages, dashboards, components, HTML/CSS layouts, or when styling/beautifying any web UI). Use when the user mentions UI/UX design, beautiful UI, frontend design, component creation, cool UI, impressive design, or Japanese equivalents like UI/UXデザイン/美しいUI/フロントエンドデザイン/ コンポーネント作成/かっこいいUI/印象的なデザイン.

Translates English technical articles (engineering blogs, documentation) to Japanese while preserving layout and structure. Use when the user asks to translate an article, convert English content to Japanese, or mentions translating a URL or technical blog post.

Execute a structured AI-driven development workflow with research, planning, implementation, optional multi-layer review (4 Sub-agents + /review + CodeRabbit CLI), priority-based fixes, and PR creation. Supports Light mode (fast, default) and Full mode (quality-focused with reviews). Use when implementing new features, performing large refactorings, starting feature development, or when the user mentions "AI development workflow", "AI開発ワークフロー", "feature workflow", "機能開発ワークフロー", "計画的に実装", "開発プロセス実行", "品質重視で実装", or "多層レビューで開発".