菜单
Clarify what the user actually wants before specs, plans, or code. Use when an ask is underspecified, when the user says "interview me", "grill me", "stress-test my thinking", or when you would otherwise fill in important product/architecture assumptions silently.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/kdlbs/kandev --skill interview-me命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Kandev release and version-channel conventions — unified Stable SemVer plus deterministic npm-only Nightlies. Use when cutting a release, changing channels, debugging artifacts, or answering version-channel questions.
Review changed code for quality, security, and architecture compliance. Use only when the user explicitly requests local review or a PR finding requires it.
Stage and commit changes using Conventional Commits. Use when there are dirty/staged files to commit, the user says "commit", or before pushing a PR.
基于 SOC 职业分类
正在显示 SKILL.md
| name | interview-me |
| description | Clarify what the user actually wants before specs, plans, or code. Use when an ask is underspecified, when the user says "interview me", "grill me", "stress-test my thinking", or when you would otherwise fill in important product/architecture assumptions silently. |
Use this before /spec-driven-development, /spec, or /plan when the requested outcome is not clear enough to implement without guessing.
Use when the ask is missing one or more of:
Skip for mechanical edits, obvious bug fixes, pure information requests, or when the user explicitly asks for speed over clarification.
Write one sentence plus a confidence number.
HYPOTHESIS: You want workspace switching to preserve task context because agents lose momentum when users navigate between workspaces.
CONFIDENCE: 45% - missing: who feels the pain, what "preserve" means, and what counts as done.
Format every question with a guess.
Q: Is this primarily for human users switching between workspaces, or for office agents operating across workspaces?
GUESS: Human users, because the pain sounds navigation-related rather than automation-related.
If the active harness provides a native user-question UI that supports multiple questions in one turn, ask 2-4 focused questions together. Keep each question short, include your guess in the prompt or options, and make the options concrete enough that the user can answer quickly.
If no multi-question tool is available, ask one question at a time in chat. Do not send a long questionnaire.
If the user says "modern", "scalable", "best practice", "dashboard", "robust", or "clean architecture" without concrete outcomes, ask:
If you did not have to justify this as best practice, what would you actually want?
When confidence is high, restate in this shape:
Here's what I think you want:
- Outcome:
- User:
- Why now:
- Success:
- Constraint:
- Out of scope:
Yes / no / refine?
Do not proceed to /spec, /plan, or implementation until the user explicitly confirms or corrects the restate.
The deliverable is a confirmed statement of intent. If the user wants it persisted, save it only after confirmation, usually in a feature spec via /spec; avoid creating standalone intent docs unless explicitly requested.