plan-interview
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChinesePlan Interview Skill
Plan Interview Skill
Transform rough plans into comprehensive, implementation-ready specifications through adaptive, structured interviews.
通过自适应的结构化访谈,将粗略计划转化为全面、可直接用于实施的规格文档。
When to Use
适用场景
- Converting a plan or idea into a detailed specification
- Gathering requirements through structured questioning
- Transforming rough documentation into implementation-ready specs
- Ensuring all edge cases, risks, and stakeholders are considered before implementation
- 将计划或想法转化为详细的规格文档
- 通过结构化提问收集需求
- 将粗略文档转化为可直接用于实施的规格
- 在实施前确保考虑到所有边缘情况、风险和相关利益方
Available Components
可用组件
Command: /plan-interview:interview [plan-file]
/plan-interview:interview [plan-file]命令:/plan-interview:interview [plan-file]
/plan-interview:interview [plan-file]Adaptive interview that calibrates depth based on plan complexity:
| Complexity | Signals | Questions |
|---|---|---|
| Simple | Single feature, clear scope | 10-15 |
| Moderate | Multi-component, some integrations | 18-23 |
| Complex | Cross-system, many stakeholders | 22-28 |
Usage:
bash
/plan-interview:interview docs/feature-plan.md根据计划复杂度调整深度的自适应访谈:
| 复杂度 | 判定信号 | 问题数量 |
|---|---|---|
| 简单 | 单一功能、范围明确 | 10-15 |
| 中等 | 多组件、存在部分集成 | 18-23 |
| 复杂 | 跨系统、涉及众多利益相关方 | 22-28 |
使用示例:
bash
/plan-interview:interview docs/feature-plan.mdOutput: docs/feature-plan-spec.md
输出:docs/feature-plan-spec.md
undefinedundefinedAgent: spec-reviewer
spec-reviewerAgent: spec-reviewer
spec-reviewerAutonomous quality analysis of specifications across 4 dimensions:
- Completeness (25 pts) - All sections populated?
- Consistency (25 pts) - No contradictions?
- Clarity (25 pts) - No ambiguous language?
- Edge Cases (25 pts) - Error handling defined?
Triggers when you say "review my spec" or "check specification quality".
从4个维度对规格文档进行自主质量分析:
- 完整性(25分)- 所有章节是否已填充?
- 一致性(25分)- 是否存在矛盾?
- 清晰度(25分)- 是否存在模糊表述?
- 边缘情况(25分)- 是否定义了错误处理机制?
当你说出“review my spec”或“check specification quality”时触发该Agent。
Interview Phases
访谈阶段
- Foundations & Scope - Stakeholders, success criteria, constraints, MVP scope
- Technical Deep-Dive - Architecture, data models, scalability, security
- User Experience - Personas, flows, cognitive load, error recovery
- Risks & Tradeoffs - Risk categorization, blast radius, contingency plans
- Operationalization - Testing, deployment, monitoring
- Wrap-Up (optional) - Only for complex plans with remaining gaps
- 基础与范围 - 利益相关方、成功标准、约束条件、MVP范围
- 技术深入探讨 - 架构、数据模型、可扩展性、安全性
- 用户体验 - 用户角色、流程、认知负荷、错误恢复
- 风险与权衡 - 风险分类、影响范围、应急计划
- 落地实施 - 测试、部署、监控
- 收尾阶段(可选)- 仅适用于仍存在空白的复杂计划
Interview Philosophy
访谈理念
Core Principle: Depth over breadth. Better to deeply understand critical aspects than superficially cover everything.
Key Techniques:
- Non-obvious questions - Skip what the plan already answers
- Edge probing - What happens in unusual cases?
- Assumption surfacing - Make implicit beliefs explicit
- Contradiction detection - Flag when answers don't align
- Adaptive depth - Probe deeper on complex areas, move faster on clear ones
核心原则:深度优先于广度。与其表面涵盖所有内容,不如深入理解关键环节。
关键技巧:
- 非显而易见的问题 - 跳过计划中已明确的内容
- 边缘情况探查 - 异常情况下会发生什么?
- 假设显性化 - 将隐含的假设明确表达出来
- 矛盾检测 - 当回答不一致时进行标记
- 自适应深度 - 对复杂领域进行深入探查,对清晰内容快速推进
Spec Output Structure
规格文档输出结构
Generated specs include:
- Overview (problem, solution, success criteria, stakeholders)
- Functional and non-functional requirements
- Technical design (architecture, data models, APIs, security)
- User experience (personas, flows, states, edge cases)
- Risks and mitigations (risk register, tradeoffs, contingency plans)
- Implementation notes (key decisions, dependencies, migration)
- Operationalization (testing, deployment, monitoring)
- Open questions and out-of-scope items
- Phasing (MVP vs future)
生成的规格文档包含:
- 概述(问题、解决方案、成功标准、利益相关方)
- 功能性与非功能性需求
- 技术设计(架构、数据模型、API、安全性)
- 用户体验(用户角色、流程、状态、边缘情况)
- 风险与缓解措施(风险登记册、权衡方案、应急计划)
- 实施说明(关键决策、依赖项、迁移方案)
- 落地实施(测试、部署、监控)
- 待解决问题与超出范围的内容
- 阶段划分(MVP vs 未来规划)
References
参考资料
Load these for deeper guidance during interviews:
- - Foundations questions and pitfalls
references/phase-1-clarifications.md - - Architecture discussion patterns
references/phase-2-technical.md - - Persona development, UX patterns
references/phase-3-ux.md - - Risk assessment frameworks
references/phase-4-risks.md - - Cross-cutting interview skills
references/interview-techniques.md - - Annotated high-quality spec example
references/example-spec.md
在访谈过程中加载以下资料以获取更深入的指导:
- - 基础阶段问题与常见陷阱
references/phase-1-clarifications.md - - 架构讨论模式
references/phase-2-technical.md - - 用户角色开发、UX模式
references/phase-3-ux.md - - 风险评估框架
references/phase-4-risks.md - - 跨阶段访谈技巧
references/interview-techniques.md - - 带注释的高质量规格文档示例
references/example-spec.md