菜单
Intelligently update README.md to reflect code changes, new features, and API updates. Use when adding new features, changing APIs, or syncing documentation with code. Triggers: readme, 說明, 更新說明, update readme, 文檔同步, 更新文檔, documentation, docs.
Proactively detect and execute code refactoring to maintain DDD architecture and code quality. Use when code is too complex, violates DRY principle, or needs restructuring. Triggers: RF, refactor, 重構, 拆分, split, 模組化, modularize, 太長, cleanup, 簡化, simplify, 整理程式碼.
Systematic debugging workflow using hypothesis-test-verify cycle to find and fix issues efficiently. Use when encountering errors, bugs, unexpected behavior, or test failures. Triggers: DEBUG, 除錯, bug, 找問題, 為什麼不work, 出錯了, error, fix bug, 壞了, broken, 不動, 故障, exception, traceback, 報錯.
Pre-commit orchestration workflow ensuring Memory Bank sync, README/CHANGELOG/ROADMAP updates before git commit. Use when preparing to commit code changes or push to repository. Triggers: GIT, gc, push, commit, 提交, 準備 commit, 要提交了, git commit, pre-commit, 推送, 準備上程式碼.
Complete data analysis workflow including EDA, Table One, descriptive statistics, and correlation analysis using MCP AutoML tools. Use when analyzing CSV data, exploring datasets, generating summary statistics, or creating publication-ready Table One reports. Triggers: 分析資料, analyze data, EDA, 探索資料, 資料分析, describe data, 資料探索, 基本統計, summary statistics, Table One, 敘述統計, 看看資料, 快速分析, quick analysis, 分析一下, 幫我分析.
Data cleaning and preprocessing workflow including handling missing values, encoding categorical variables, filtering rows, removing columns, and checking multicollinearity (VIF). Use when preparing data for analysis, cleaning messy datasets, or transforming variables. Triggers: 資料清理, data cleaning, 缺失值, 處理資料, preprocess, missing values, 遺漏值, encoding, 編碼, VIF, multicollinearity, 共線性, filter, 過濾, rename columns.
Machine learning model training workflow using AutoML including data upload, model training, evaluation, and prediction. Use when training classification or regression models, comparing algorithms, or making predictions on new data. Triggers: 訓練模型, train model, ML, 機器學習, AutoML, prediction, 預測, classification, regression, 分類, 迴歸, XGBoost, random forest, neural network, 模型比較.
| name | readme-updater |
| description | Intelligently update README.md to reflect code changes, new features, and API updates. Use when adding new features, changing APIs, or syncing documentation with code. Triggers: readme, 說明, 更新說明, update readme, 文檔同步, 更新文檔, documentation, docs. |
智能更新 README.md，保持與程式碼同步，支援多語言版本維護。
| 區塊 | 條件 |
|---|---|
| 功能列表 | 新增/移除功能 |
| 安裝說明 | 依賴變更 |
| 使用範例 | API 變更 |
| 專案結構 | 目錄結構變更 |
| 配置說明 | 新增設定選項 |
以下區塊不自動修改：
README.md # 主 README（預設語言）
README.zh-TW.md # 繁體中文版本（可選）
README.en.md # 英文版本（可選）
如果使用者提供中文內容 → 同步到英文版（如存在）
如果使用者提供英文內容 → 同步到中文版（如存在）
如果主 README 變更 → 同步所有語言版本
| 中文 | English |
|---|---|
| 憲法 | Constitution |
| 子法 | Bylaws |
| 技能 | Skills |
| 記憶庫 | Memory Bank |
| 領域驅動設計 | Domain-Driven Design (DDD) |
| 資料存取層 | Data Access Layer (DAL) |
| 提交 | Commit |
| 工作流 | Workflow |
| 架構 | Architecture |
| 模組化 | Modular |
- [ ] 章節數量一致
- [ ] 程式碼區塊一致
- [ ] 連結有效性
- [ ] 術語一致性
📝 README 更新分析
變更偵測：
✅ 新增功能：用戶認證模組
✅ 新增依賴：bcrypt
建議更新：
[功能列表] 新增「🔐 用戶認證」
[安裝說明] 新增 bcrypt 安裝指令
預覽：
## 功能
- 🤖 Claude Skills
- 📝 Memory Bank
+ - 🔐 用戶認證（新增）
多語言同步：
⏭️ README.zh-TW.md - 不存在，跳過