create-work-breakdown-structure
关于
This Claude Skill creates a Work Breakdown Structure (WBS) and WBS Dictionary by decomposing project deliverables into a hierarchical structure of manageable work packages. It handles WBS coding, effort estimation, dependency identification, and critical path analysis for classic or waterfall projects. Use it after project charter approval to establish a basis for detailed planning, estimation, and resource allocation.
快速安装
Claude Code
推荐npx 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-structure在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
Create a Work Breakdown Structure
Decompose scope → hierarchical work packages → estimate + assign + track. Foundation for effort + resource + schedule.
Use When
- Charter approved + scope defined
- Classic/waterfall planning
- Large initiative → manageable pkgs
- Basis for estimation + resource
- Shared understanding of work
In
- Required: Approved charter (scope + deliverables)
- Required: Methodology (classic/waterfall / hybrid)
- Optional: Historical effort data
- Optional: Team composition + skills
- Optional: Org WBS templates
Do
Step 1: Extract Deliverables
Read charter. List deliverables + acceptance. Group → 3-7 top-level cats → WBS Level 1.
Got: L1 elements match charter deliverables.
If err: Charter vague → draft-project-charter to refine.
Step 2: Decompose → Work Packages
Each L1 → sub-elements (L2, L3). 100% rule: children = 100% parent scope. Stop when pkgs:
- Estimable (person-days)
- Assignable (1 owner)
- Measurable (done/not-done)
WBS outline:
# 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
Codes (1.1.1 fmt). Max 3-5 levels. Always include "Project Management" branch.
Got: Complete WBS, 15-50 pkgs, unique codes.
If err: >5 levels → scope too large → split sub-projects.
Step 3: WBS Dictionary
Each leaf → entry:
# 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]
...
Got: Entry per leaf pkg.
If err: Missing entries → incomplete decomp → Step 2.
Step 4: Estimate
Per pkg, 1 method:
- T-shirt (XS/S/M/L/XL) → early planning
- Person-days → detailed
- 3-pt (optimistic/ML/pessimistic) → high-uncertainty
Summary:
## 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 |
Total = sum of all pkgs.
Got: Every pkg estimated + confidence.
If err: Low confidence >30% pkgs → SME refinement session.
Step 5: Deps + Critical Path
Map deps:
## 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 | |
Longest chain = critical path candidate.
Got: Dep table w/ FS relationships.
If err: Cycles → decomp errs → Step 2.
Step 6: Review + Baseline
Combine WBS + dict → final docs. Verify 100% rule every level. Stakeholder sign-off.
Got: WBS.md + WBS-DICTIONARY.md created + reviewed.
If err: Missing scope found → add pkgs + re-estimate.
Check
- WBS file w/ doc ID + codes
- 100% rule every level
- Every leaf in dict
- All pkgs estimated
- Deps no cycles
- PM branch included
- Critical path ID'd
- Depth ≤5 levels
Traps
- Confuse deliverables vs activities: Elements = nouns (deliverables), not verbs. "User Auth Module" not "Implement Auth".
- Violate 100% rule: Children ≠ 100% parent → missed work.
- Too shallow / deep: 2 levels vague; 6+ micromgmt. Target 3-5.
- Skip PM branch: PM work (planning, mtgs, reports) = real effort.
- Estimate pre-decomp: Estimate pkgs, not cats. L1 estimate unreliable.
- No dict: WBS w/o dict = tree of labels. Dict = def of done.
→
draft-project-charter— scope + deliverables feed decompmanage-backlog— WBS pkgs → backlog itemsgenerate-status-report— report % completeplan-sprint— hybrid: sprint-plan from pkgsconduct-retrospective— review estimation + decomp quality
GitHub 仓库
相关推荐技能
content-collections
元Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
polymarket
元这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。
creating-opencode-plugins
元该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。
sglang
元SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
