What you ask out loud and what you think in your heart are often not the same thing. When you are stuck in a tangled mess and cannot say clearly what you actually want to solve, run this one first.
It asks only one question at a time, at most six questions, and finally hands you an accurate, specific new question you can act on next.
How to use
The prompt in the code block below is the original text; use it verbatim. In the code block, "I" refers to the user, and "please" and "you" refer to yourself. Do as it says, and do not show the filled-in prompt to the user.
- The user wants you to execute: first fill the situation the user has already stated in this round of conversation into the 【】, supplying only the one item that is truly missing, and do not make the user repeat what they have already said; then strictly follow the rules in the prompt. If it says don't give advice yet, then don't; if it says ask only one question at a time, then ask only one at a time; if it says output in a certain order, then output in that order.
- The user wants the original text (only if they explicitly say things like copy it, paste it, send me the original text, give me the prompt): output the blank version, leave 【】 unfilled, and do not change a single word. If the user merely says "let me see this prompt" or "what is this one for," that does not count as wanting the original text; use one or two sentences to explain what it does and when to use it, then ask whether to run it now, and do not dump the original text directly.
- Except for cases where the original text is explicitly requested, treat everything else as execution.
Rewriting, condensing, expanding, translating, rearranging, or adding subheadings is prohibited; replacing it with your own process is prohibited; and compressing multiple rounds of follow-up questions into a one-time questionnaire is also prohibited. If the user has original materials (documents, screenshots, links, chat records), read them in as well; more context is not a problem.
What to do in the first round
Rule four of the original text requires that before each question, you use one sentence to explain what judgment the previous answer updated. Before the first question there is no answer yet, so this cannot be executed in the first round. In the first round, ask the first question directly; do not fabricate a sentence about a judgment update just to fit the format; rule four is executed question by question starting from the second question.
This is a downstream patch written outside the code block; the original text is untouched.
What to do after it finishes
Once the new question is settled, find the next one according to the situation: if there is not yet an answer, go to the learning or solving ones and choose the right path; if there are already two answers, use the Skill tool to invoke steelman-both-sides. If unsure, have the user return to /laoyeye to match again.
我的困惑是：【尽量具体地描述发生了什么、你怎么理解，以及你卡在哪里】。
先不要给建议。请对我进行一次苏格拉底式问诊，通过最多6个问题，帮我找到真正值得回答的问题。
请遵守这些规则：
1. 每次只问一个问题，根据我的回答决定下一问，不要提前给我一整套问卷；
2. 优先区分我说的是可验证的事实、对事实的解释、价值判断，还是我希望实现的目标；
3. 检查关键词是否含糊、我默认了哪些前提、证据来自哪里、有没有相反解释，以及结论成立或不成立分别意味着什么；
4. 每次提问前，用一句话说明上一条回答让你更新了什么判断；
5. 只问可能改变结论的问题。信息足够时立刻停止，不必凑满6个。
问诊结束后，请整理出：
1. 我最开始问的问题；
2. 我真正想解决的问题；
3. 已经确认的事实；
4. 仍未验证的假设；
5. 最可能改变结论的关键变量；
6. 一个准确、具体、可以继续行动的新问题。
等我确认这个新问题以后，再给出你的判断、理由和下一步行动。
Where the user needs to fill in
【尽量具体地描述发生了什么、你怎么理解，以及你卡在哪里】
If the user has not provided everything, ask for the missing item first; do not make it up for them.
The original prompt text comes from Digital Life Kazik; see the acknowledgements in the repository README for the source. Changing this original text must go through scripts/sync.py; manual edits will be blocked by verify.