content/skills/development-workflows/interview-plan/SKILL.md
通过苏格拉底式访谈细化需求,优先使用 planning-with-files 文件计划模式生成持久化实施计划,不可用时降级为原生 Plan 模式。适用于需求细化、技术方案设计等场景。
npx skillsauth add bahayonghang/my-claude-code-settings interview-planInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
通过苏格拉底式访谈将模糊需求转化为清晰的工程规格,然后调用 Plan 模式生成可执行的实施计划。
读取 resources/BRAINSTORMING_INTEGRATION.md 了解头脑风暴协议。若用户说"跳过头脑风暴"或"skip brainstorming",则跳过步骤 3、7、8 中标记为 [可选] 的分支。
$ARGUMENTS 为空,提示用户提供需求文档路径(默认查找 plan.md)。若文件不存在,报错退出。resources/INTERVIEW_PRINCIPLES.md,按其提问原则进行苏格拉底式访谈。resources/INTERVIEW_DIMENSIONS.md,按 A-G 维度框架逐项向用户提问:
AskUserQuestion 工具呈现每轮问题,将 2-3 个收敛性选项映射为可点击的交互式选项卡(options),禁止以纯文本 A/B/C 形式输出。AskUserQuestion 调用包含 1-4 个问题(questions),每个问题 2-4 个选项(options),用户可通过 UI 直接点选。AskUserQuestion 调用中,减少交互轮次。resources/VISUAL_COMPANION.md 提议启用浏览器可视化伴侣。
127.0.0.1 / localhost;没有明确远程访问需求时,不要放宽监听范围。AskUserQuestion 让用户选择。resources/RISK_PROTECTION.md 并发出告警,等待用户明确授权。planning-with-files 是否存在。
b. 若 planning-with-files 可用(优先路径):
输出提示:📋 检测到 planning-with-files,使用文件计划模式
先将访谈结论以 notes.md 模板格式写入工作目录的 notes.md
调用 Skill(skill="planning-with-files:plan", args="基于访谈结论创建实施计划,访谈结论已写入 notes.md")
task_plan.md 按以下模板结构生成:
# Implementation Plan
## Goal
<从访谈提取的核心业务目标>
## Phases
- [ ] Phase 1: <阶段名> — <关键交付物>
- [ ] Phase 2: ...
## Key Questions Resolved
| 问题 | 决策 | 理由 |
|------|------|------|
| ... | ... | ... |
## Decisions Made
- **选定方案**: <方案名> — <一句话理由>
- **被拒方案**: <方案名> — <为什么不选>
## Risks
- [ ] <风险描述> → 缓解措施: <措施>
## Status
- 当前阶段: Phase 1
- 创建时间: YYYY-MM-DD
完成后告知用户计划文件位置,流程结束 c. 若 planning-with-files 不可用(降级路径):
输出提示:📋 planning-with-files 不可用,使用平台原生 Plan 模式
调用 EnterPlanMode 进入原生 Plan 模式
在计划文件中写入访谈结论与实施计划(任务分解、依赖关系、验收标准、风险缓解)
ExitPlanMode 进入执行阶段。/ 分隔rg 替代 grepcommit、push 等 Git 写操作task_plan.md(文件模式)或原生 Plan(降级模式)task_plan.md 和 notes.md 创建在工作目录根路径,不创建子目录development
Use only when the user explicitly asks for swarm, subagents, parallel agents, dynamic workflow, multi-agent orchestration, 多智能体编排, or when the task truly needs coordinated research plus implementation plus review plus verification packets. Do not use for ordinary code review, planning-only work, single-line bugfixes, routine audits, or migrations unless orchestration is requested or at least two independent workflow dimensions are present.
development
Run a code quality review focused on maintainability, structure, abstraction quality, file growth, branching complexity, boundary cleanliness, and refactoring opportunities. Use when the user asks for code quality review, code review, maintainability review, architecture quality review, PR code quality feedback, 代码质量审查, 代码质量 review, 可维护性审查, 架构质量审查, or review comments about code structure. Do not use for pure security review, formatting-only review, performance profiling, or implementation tasks unless the user also asks for a code quality review.
development
Plan-first brainstorming workflow that turns an idea into an approved Markdown implementation plan by default. Use when the user wants to brainstorm, design, scope, or plan a feature/spec before implementation. Spark explores project context, asks only blocking questions, writes the plan under the project root's .plannings/YYYY-MM-DD-feature-slug.md path, self-reviews it, and waits for user approval. Create an HTML or visual plan/spec only when the user explicitly asks for HTML, browser-viewable, or visual output; save the paired .html beside the Markdown plan.
development
Run a code quality review focused on maintainability, structure, abstraction quality, file growth, branching complexity, boundary cleanliness, and refactoring opportunities. Use when the user asks for code quality review, code review, maintainability review, architecture quality review, PR code quality feedback, 代码质量审查, 代码质量 review, 可维护性审查, 架构质量审查, or review comments about code structure. Do not use for pure security review, formatting-only review, performance profiling, or implementation tasks unless the user also asks for a code quality review.