create-work-breakdown-structure
About
This Claude Skill creates a Work Breakdown Structure (WBS) and WBS Dictionary by decomposing project deliverables into a hierarchy of manageable work packages. It handles WBS coding, effort estimation, dependency identification, and highlights critical path candidates. Use it after project charter approval for waterfall-style planning to establish a basis for estimation, resource allocation, and scheduling.
Quick Install
Claude Code
Recommendednpx skills add pjt222/agent-almanac -a claude-code/plugin add https://github.com/pjt222/agent-almanacgit clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/create-work-breakdown-structureCopy and paste this command in Claude Code to install this skill
Documentation
造工作分解結構
分項目範圍為階層之工作包,可估、可派、可追。WBS 為估工、資源計畫、排程開發之基,將複雜交付物分為可管之組件。
適用時機
- 項目章程核准且範圍已定後
- 計畫含既定交付物之古典/瀑布項目
- 將大倡議分為可管之工作包
- 立估工與資源計畫之基
- 造所有所需工作之共識
輸入
- 必要:核准之項目章程(尤範圍與交付物段)
- 必要:項目方法論(古典/瀑布、或含 WBS 之混合計畫)
- 選擇性:類似項目之歷史工作資料
- 選擇性:團隊組成與可用技能
- 選擇性:組織之 WBS 範本或標準
步驟
步驟一:自章程萃交付物
讀項目章程。列所有交付物與接受標準。組之為 3-7 頂層類(此為 WBS Level 1 元素)。
預期: Level 1 WBS 元素清單合章程交付物。
失敗時: 若章程泛,返 draft-project-charter 以精修範圍。
步驟二:分為工作包
各 Level 1 元素,分為子元素(Level 2、Level 3)。施 100% 規則:子元素須代表父範圍之 100%。分停於工作包為:
- 可估(可以人日派工)
- 可派(一人或一團隊有之)
- 可量(明完/未完標準)
造 WBS 大綱:
# Work Breakdown Structure: [Project Name]
## Document ID: WBS-[PROJECT]-[YYYY]-[NNN]
### WBS Hierarchy
1. [Level 1: Deliverable Category A]
1.1 [Level 2: Sub-deliverable]
1.1.1 [Level 3: Work Package]
1.1.2 [Level 3: Work Package]
1.2 [Level 2: Sub-deliverable]
2. [Level 1: Deliverable Category B]
2.1 [Level 2: Sub-deliverable]
3. [Level 1: Project Management]
3.1 Planning
3.2 Monitoring & Control
3.3 Closure
施 WBS 編碼(1.1.1 格式)。確保最深 3-5 層。恒含「Project Management」分支。
預期: 全 WBS,含 15-50 工作包,各有唯一 WBS 編碼。
失敗時: 若分超 5 層,範圍過大——考慮分為子項目。
步驟三:寫 WBS 字典
各工作包(葉節點),寫字典項:
# WBS Dictionary: [Project Name]
## Document ID: WBS-DICT-[PROJECT]-[YYYY]-[NNN]
### WBS 1.1.1: [Work Package Name]
- **Description**: What this work package produces
- **Acceptance Criteria**: How to verify it's done
- **Responsible**: Person or role
- **Estimated Effort**: [T-shirt size or person-days]
- **Dependencies**: WBS codes this depends on
- **Assumptions**: Key assumptions for this work package
### WBS 1.1.2: [Work Package Name]
...
預期: 各葉節點工作包皆有字典項。
失敗時: 缺之字典項指分解不全——返步驟二。
步驟四:估工
各工作包施一估法:
- T-shirt 尺碼(XS/S/M/L/XL)供早期計畫
- 人日供細計畫
- 三點估(樂觀/最可能/悲觀)供高不確之工
造摘要表:
## Effort Summary
| WBS Code | Work Package | Estimate | Method | Confidence |
|----------|-------------|----------|--------|------------|
| 1.1.1 | [Name] | 5 pd | person-days | High |
| 1.1.2 | [Name] | M | t-shirt | Medium |
總工 = 所有工作包之和。
預期: 各工作包皆有估工含所述信心度。
失敗時: 若 >30% 之包信心為 Low,與 SME 排精修會。
步驟五:辨依賴與關鍵路徑候選
映工作包間之依賴:
## Dependencies
| WBS Code | Depends On | Type | Notes |
|----------|-----------|------|-------|
| 1.2.1 | 1.1.1 | Finish-to-Start | Output of 1.1.1 is input to 1.2.1 |
| 2.1.1 | 1.1.2 | Finish-to-Start | |
辨依賴工作包之最長鏈——此為關鍵路徑候選。
預期: 依賴表含至少 finish-to-start 關係。
失敗時: 若依賴成環,分解有誤——返步驟二。
步驟六:審與基線
合 WBS 與字典為終檔。各層驗 100% 規則。得相關者簽。
預期: WBS.md 與 WBS-DICTIONARY.md 檔已造並審。
失敗時: 若相關者辨缺範圍,加工作包並重估。
驗證
- WBS 檔已造,含文件 ID 與 WBS 編碼
- 100% 規則於各層皆滿:子完整代表父範圍
- 各葉節點有 WBS 字典項
- 所有工作包皆有估工
- 依賴已辨,無循環引用
- 含 Project Management 分支
- 關鍵路徑候選已辨
- WBS 深度不超 5 層
常見陷阱
- 混交付物與活動:WBS 元素當為名詞(交付物),非動詞(活動)。「User Authentication Module」非「Implement Authentication」
- 違 100% 規則:若子不合父範圍之 100%,工作將被漏
- 過淺或過深:2 層於計畫過泛;6+ 層為微管理。目標 3-5 層
- 跳 Project Management 分支:PM 工作(計畫、會議、報告)為耗工之實工
- 分解前估:估工作包,非類。Level 1 之估不可靠
- 無字典:無字典之 WBS 為標籤之樹——字典提供完成之定義
相關技能
draft-project-charter—— 提供餵 WBS 分解之範圍與交付物manage-backlog—— 將 WBS 工作包轉為追之積壓項generate-status-report—— 對 WBS 完成率報告進度plan-sprint—— 若用混合法,自 WBS 工作包計畫衝刺conduct-retrospective—— 審估之準度與分解之品質
GitHub Repository
Related Skills
content-collections
MetaThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
polymarket
MetaThis skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.
creating-opencode-plugins
MetaThis skill helps developers create OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It provides the plugin structure, event API specifications, and implementation patterns for JavaScript/TypeScript modules. Use it when you need to intercept, monitor, or extend the OpenCode AI assistant's lifecycle with custom event-driven logic.
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
