refactor

[UDS] Guide refactoring decisions and strategy selection, including the refactor-versus-rewrite call. Use when: code has become hard to change, choosing between tactical and architectural refactoring, working safely inside legacy code. Not for: moving to a different framework or major version — use /migrate; clearing debug artifacts and dead code — use /sweep. Keywords: refactor, rewrite, strangler, legacy code, technical debt, code smell, 重構, 重寫, 技術債.

Jump to install Review files

Repository: AsiaOstrich/universal-dev-standards
Last source activity: August 17, 2026 at 06:20
Detected SKILL.md language: English
Stars: 76
Forks: 13

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/AsiaOstrich/universal-dev-standards/tree/main/skills/refactoring-assistant.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/AsiaOstrich/universal-dev-standards --skill refactor

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

2 files

SKILL.md

Source instructions · Read-only preview

name: refactor
scope: universal
description: [UDS] Guide refactoring decisions and strategy selection, including the refactor-versus-rewrite call. Use when: code has become hard to change, choosing between tactical and architectural refactoring, working safely inside legacy code. Not for: moving to a different framework or major version — use /migrate; clearing debug artifacts and dead code — use /sweep. Keywords: refactor, rewrite, strangler, legacy code, technical debt, code smell, 重構, 重寫, 技術債.
allowed-tools: Read, Write, Grep, Glob, Bash(npm test:*), Bash(npx:*)
argument-hint: [file or module | 檔案或模組]

# Refactoring Assistant | 重構助手 Guide refactoring decisions, recommend strategies, and provide step-by-step execution workflows. 引導重構決策、推薦策略，並提供逐步執行工作流程。 ## Usage | 使用方式 | Command | Purpose | 用途 | |---------|---------|------| | `/refactor` | Start interactive refactoring guide | 啟動互動式重構引導 | | `/refactor decide` | Run refactor vs. rewrite decision tree | 執行重構 vs 重寫決策樹 | | `/refactor tactical` | Suggest tactical (daily) strategies | 建議戰術性（日常）策略 | | `/refactor strategic` | Guide strategic/architectural refactoring | 引導戰略性/架構重構 | | `/refactor legacy` | Legacy code safety strategies | 遺留程式碼安全策略 | | `/refactor debt` | Technical debt assessment | 技術債評估 | ## Strategy Quick Reference | 策略快速參考 ### Tactical Strategies (Daily) | 戰術性策略 | Strategy | When to Use | 使用時機 | |----------|-------------|---------| | **Preparatory Refactoring** | Before adding a blocked feature | 新增被阻擋的功能之前 | | **Boy Scout Rule** | During any maintenance work | 任何維護工作中 | | **Red-Green-Refactor** | TDD development cycle | TDD 開發循環 | ### Strategic Strategies (Architectural) | 戰略性策略 | Strategy | When to Use | 使用時機 | |----------|-------------|---------| | **Strangler Fig** | Replacing entire system gradually | 逐步替換整個系統 | | **Anti-Corruption Layer** | Integrating with legacy system | 與遺留系統整合 | | **Branch by Abstraction** | Shared code refactoring on trunk | 在主幹上重構共享程式碼 | ### Safety Strategies (Legacy) | 安全防護策略 | Strategy | When to Use | 使用時機 | |----------|-------------|---------| | **Characterization Tests** | Before any legacy refactoring | 任何遺留程式碼重構之前 | | **Scratch Refactoring** | Understanding black-box code | 理解黑盒程式碼 | | **Finding Seams** | Injecting test doubles into legacy | 在遺留程式碼中注入測試替身 | ## Workflow | 工作流程 1. **Assess** - Identify code to refactor, evaluate test coverage 2. **Decide** - Run decision tree (refactor vs. rewrite) if needed 3. **Select strategy** - Choose appropriate strategy based on scope and risk 4. **Execute** - Follow step-by-step workflow with safety checks 5. **Verify** - Run tests to confirm behavior is preserved ## Usage Examples | 使用範例 ``` User: /refactor src/legacy-auth/ AI: Analyzing src/legacy-auth/... Test coverage: 23% — recommending safety-first approach. Suggested strategy: Characterization Tests + Preparatory Refactoring ``` ``` User: /refactor decide AI: Let me help you decide whether to refactor or rewrite. Question 1: Is the code currently working in production? [Y/N] ``` ## Next Steps Guidance | 下一步引導 After `/refactor` completes, the AI assistant should suggest: > **重構完成。建議下一步 / Refactoring complete. Suggested next steps:** > - 執行 `/checkin` 通過品質關卡 ⭐ **Recommended / 推薦** — Pass quality gates > - 執行 `/coverage` 確認重構後覆蓋率不下降 — Verify coverage not decreased > - 執行 `/commit` 提交重構變更 — Commit the refactoring changes ## Reference | 參考 - Detailed guide: [guide.md](./guide.md) - Core standard: [refactoring-standards.md](../../core/refactoring-standards.md) ## AI Agent Behavior | AI 代理行為 > 完整的 AI 行為定義請參閱對應的命令文件：[`/refactor`](../commands/refactor.md#ai-agent-behavior--ai-代理行為) > > For complete AI agent behavior definition, see the corresponding command file: [`/refactor`](../commands/refactor.md#ai-agent-behavior--ai-代理行為)

View on GitHub

Back to search Back to installation

comprehend

[UDS] 把一段難懂的 AI 輸出換成較好懂的形式：受控文字、Mermaid 圖、單檔 HTML 解說頁。所有形式都來自同一份大綱，所以形式會變，事實不會變。 Use when: AI 的說明、規格或程式碼解說太密、讀的人看不出該不該核准；非專業的人必須靠它做核准；想要它的圖或離線解說頁。 Not for: 寫新內容或加新分析——本技能只把既有的文字換形式；從原始碼產生文件——請用 /docgen；為專家讀者縮短文字——直接改寫即可。 Keywords: comprehension ladder, explainer, controlled language, Mermaid, HTML explainer, outline, plain language, understand AI output, 理解階梯, 受控語言, 流程圖, 解說頁, 換形式不換事實.

2026-10-05

comprehend

[UDS] 把一段难懂的 AI 输出换成较好懂的形式：受控文字、Mermaid 图、单文件 HTML 解说页。所有形式都来自同一份大纲，所以形式会变，事实不会变。 Use when: AI 的说明、规格或代码解说太密、读的人看不出该不该核准；非专业的人必须靠它做核准；想要它的图或离线解说页。 Not for: 写新内容或加新分析——本技能只把既有的文字换形式；从源代码产生文档——请用 /docgen；为专家读者缩短文字——直接改写即可。 Keywords: comprehension ladder, explainer, controlled language, Mermaid, HTML explainer, outline, plain language, understand AI output, 理解阶梯, 受控语言, 流程图, 解说页, 换形式不换事实.

2026-10-05

comprehend

[UDS] Turn one hard-to-follow AI output into easier forms: controlled text, a Mermaid diagram, a single-file HTML explainer. All forms come from one shared outline, so the form changes and the facts do not. Use when: an AI explanation, spec or code walk-through is too dense to judge, a non-specialist must approve something from it, you want a diagram or an offline explainer page of it. Not for: writing new content or adding analysis — this skill only re-forms a text that exists; generating docs from source code — use /docgen; shortening a text for an expert reader — edit it directly. Keywords: comprehension ladder, explainer, controlled language, Mermaid, HTML explainer, outline, plain language, understand AI output, 理解階梯, 受控語言, 流程圖, 解說頁, 換形式不換事實.

2026-10-05

View all from this repository

refactor

Source facts

Install options

Install with an AI assistant

Review the source files

More from this repository

Install with an AI assistant

More from this repository