recca0120

cc-office project overview — current phase (Claude Code web client with protocol alignment to the VS Code extension) plus the long-term RPG roadmap (Code Quest). Use when asking what this project does, planning architecture, understanding which features are built vs planned, or framing new features.

Code Quest project-specific code review checks covering import order, zod schema placement, cross-package event-name alignment, server handler middleware, channel / emitter semantics, client handler organization, React Compiler compatibility, icon facade convention, and FakeSummoner test patterns. Pairs with generic `code-review` skill. Use when reviewing Code Quest code, discussing refactor, checking a PR for protocol/handler/zod alignment, or verifying that recent changes match project conventions.

Project-specific Vitest testing reference for the **server** package (apps/server). Use when writing or modifying server-side vitest tests, fixing failing tests, testing DB / socket.io server-side, choosing mocking strategies, or working with async patterns and fake timers. For frontend tests (apps/web) see `frontend-testing`.

Inversify dependency injection patterns for the server. Use when creating or modifying DI container bindings, adding injectable services, writing tests with dependency overrides, or managing TYPES symbols.

Tailwind CSS v4 styling with @theme, @utility, and @custom-variant directives. Use when styling components, configuring design tokens, adding custom utilities, migrating from v3, or converting hardcoded colors to theme tokens. Enforces token-first design flow: look up existing @theme tokens before reaching for arbitrary values, and extend @theme when a design exceeds the token range rather than sprinkling ad-hoc `[Npx]` / `[#hex]` values.

Explains Claude Code features, skills, subagents, hooks, MCP, and CLI usage. Use when the user asks questions like "How do I...", "Can Claude...", "What is...". Provides detailed guidance on Claude Code CLI functionality.

Collects real CLI (Claude, Gemini) stream-json output as .jsonl fixture files. Use when adding new fixture scenarios, updating after CLI version changes, or covering new protocol event types.

Drizzle ORM and drizzle-kit patterns for multi-dialect setup (SQLite + MySQL). Use when creating or modifying DB schemas, writing migrations, implementing repositories, adding tables or relations, or writing database tests.

Zod v4 schema validation 最佳實踐指南。當需要定義 schema、驗證/解析 JSON 資料、type inference、或處理 unknown data 時使用。

Svelte 5 + Astro 整合最佳實踐指南。當需要建立 Svelte 元件、使用 runes API、整合 Astro islands、或用 Testing Library 測試 Svelte 元件時使用。

GitHub GraphQL API 最佳實踐指南。當需要使用 GraphQL 查詢使用者資料、處理 cursor pagination、計算 rate limit、或除錯 GraphQL errors 時使用。

gayanvoice/top-github-users 架構參考指南。當需要了解 GitHub 使用者排行榜的資料抓取管線、國家設定、排行計算邏輯、已知問題、或社群需求時使用。

Commander.js v14 CLI 框架最佳實踐。當需要建立 CLI 工具、解析命令列參數、設計 subcommands 時使用。

GitHub Actions CI/CD 最佳實踐指南。當需要設定 workflow、cron 排程、GitHub Pages 部署、使用 Octokit API、或處理 rate limiting 時使用。

Globe.GL 3D 地球視覺化指南。當需要建立互動式 3D 地球、國家熱力圖、點擊導航、或整合 Astro 時使用。

MSW (Mock Service Worker) 2.x 最佳實踐指南。當需要在 Vitest 中攔截 HTTP 請求、測試 API 整合（含 Octokit）、模擬錯誤/rate limiting、或組織 mock handlers 時使用。

cubejs (Rubik's Cube solver, Kociemba two-phase) 使用指南。當需要實作魔術方塊自動解法、狀態字串序列化、或 scramble 產生時使用。

msw-fetch-mock 套件使用指南（搭配 MSW v2 + Vitest）。當需要 mock HTTP 請求、測試 fetch 呼叫、驗證 API 互動時使用。

React 19 最佳實踐指南。當需要撰寫 React 元件、使用 Hooks、處理狀態管理、或搭配 TypeScript/Vite 開發時使用。

React Three Fiber (R3F) + Three.js + drei 最佳實踐。當需要建立 3D 場景、處理相機/光照、互動事件、動畫、效能優化時使用。

TDD (Test-Driven Development) 最佳實踐指南，搭配 Vitest + React Testing Library。當需要撰寫測試、實踐 Red-Green-Refactor、設計測試結構時使用。應在開發新功能時主動套用。

Test Doubles 最佳實踐指南（Vitest + TypeScript）。當需要選擇 Mock/Stub/Fake/Spy/Dummy、或討論測試隔離策略時使用。

Vite 6/7 最佳實踐指南。當需要初始化 Vite 專案、設定 plugin、配置 build、除錯 HMR、path alias 或整合 React/TS/Vitest 時使用。

Zustand 5 最佳實踐指南。當需要建立 store、設計 selector、使用 middleware (persist/immer/devtools)、或處理 React 狀態管理時使用。

Analyzes Claude Code Skills for lint issues and duplicate content. Use when user asks to analyze skills, lint skills, check quality, or find duplicates.

Extracts duplicate content from Skills into shared modules. Use when user asks to refactor skills, extract common content, or merge duplicates.

Validates Skills after refactoring to ensure they work correctly. Use when user asks to validate skills, verify refactoring, or check skills still work.

Processes various document formats and extracts content. Use when user asks to process documents, extract text, or convert file formats.

Analyzes documents for insights and patterns. Use when user asks to analyze documents, find patterns, or generate reports.

I can help you with various tasks. You can use this tool for anything.

A generic helper for various tasks. Assists with common operations.

This skill uses tabs for indentation. Tabs should not be used in YAML.

Provides Hugo Stack theme configuration reference including sidebar, widgets, comments (Giscus), color scheme, article options, custom CSS, and Stack-specific shortcodes. Use when configuring or troubleshooting Stack theme settings.

Guides writing and editing technical blog posts for recca0120.github.io (Hugo + Stack theme, bilingual zh-hant-tw + en). Covers article structure, SEO, frontmatter conventions, cover image generation, internal links via Hugo ref shortcode, plain blockquote callouts (for cross-post compatibility), and humanized zh-hant writing style. Use this skill whenever the user writes, drafts, edits, translates, or restructures any article on this blog — even if they don't explicitly say "blog post" (e.g. "幫我整理成一篇", "改寫這段", "翻成英文版").

Detects and removes AI-generated writing patterns from Chinese text (both 繁體 and 简体), making it sound natural and human-written. Use this skill whenever editing, reviewing, translating, or drafting any Chinese prose longer than a short sentence — including blog posts, article sections pasted by the user, AI-drafted translations, or any text that smells "AI-ish" (exaggerated symbolism, promotional tone, formulaic三段式 structure, filler phrases like "此外/然而/總而言之"). Preserve the original script variant (繁體 → 繁體, 简体 → 简体) — never silently convert between them.

當使用者單純貼一個 URL 時，自動詳讀該網址的內容，整理成技術部落格文章。 觸發條件：訊息只有一個或多個 URL，沒有其他指示。 流程：讀內容 → 搜尋相關舊文章 → 問使用者確認方向 → 寫文章。

Provides Hugo static site generator reference for configuration, templates, content management, and multilingual setup. Use when modifying Hugo site config, creating templates or shortcodes, managing content structure, or debugging Hugo build issues.