dsh-help-me-to-ask

提问引导 · dsh-HelpMe-To-Ask

简体中文 · English

仓库：github.com/DoreiHime/dsh-help-me-to-ask

---

简体中文

你好呀，谢谢你点进来看。

做这个小插件的原因其实挺朴素的：我在 DSH 里干活的时候，经常一开始只说一句“帮我搞一下这个”，等模型吭哧吭哧做完，才发现方向不太对，又要推倒重来。后来就想，要是有个东西能在动手之前先轻轻问一句“你是想要 A 还是 B 呀”，大概能少很多来回。

所以有了它：回答之前，先帮你把话问清楚，再把你的回答整理成一张小小的「任务说明」（也可以理解成开工前的小单子），你确认之后才交给模型。就这些，没有别的了。

想直接用最新版？

在 DSH 的插件安装输入框里填：

dsh-help-me-to-ask@1.0.5

带版本号可以跳过 npm 新版本的 24 小时观察期；只写包名时，DSH 可能先给你装稍旧的 1.0.2。

它会做什么

每个聊天窗口里，当你发出第一段真正的工作内容时（纯寒暄不算），它会先弹一张卡片：

• 先复述一句“我理解你想做的是……”，让你看看有没有跑偏；
• 只问真正缺的东西：目标、交付物、范围限制、验收标准、有没有什么要特别注意的；
• 每个问题都尽量给出从你原话里推出来的具体选项，不太会问那种“请描述你的需求”的空话；
• 实在不想一项项选，可以点“一键明确目标”，让它自己补全。

你回答完（或者点了跳过），它会整理成一张很短的任务说明，大概长这样：

要做成什么 / 最后给你什么 / 限制（能改哪些、用什么）/ 怎样算做好 / 明确不碰的 / 没问到、先这样定

看一眼，确认、改一改、或者直接跳过。确认之后，模型就知道自己到底要做什么、做到什么程度算完成。

卡片出现时会响一声提示音（可在设置里关掉）；最多保留 10 分钟，底部有倒计时，填不完可以点「还没写完！+5 分钟」续时；填写内容会边写边暂存在本机，刷新页面或重启也能恢复。

什么时候会出现

插件启用、并且当前聊天窗口没有跳过时：

• 只在需求模糊时问：第一段工作内容里，分析觉得缺目标 / 交付物 / 限制，才弹卡；
• 复杂任务也问：第一段工作内容里，即使目标清楚，只要任务复杂也先确认关键细节；
• 跳过这个窗口：当前聊天窗口里不再引导，其他窗口不受影响；
• 帮我一下（金色）：只接管当前聊天窗口的下一条消息，不管它清晰、模糊还是寒暄，都会走一次确认流程；用完自动恢复原来的模式。

纯打招呼（你好、在吗、谢谢、哈哈、晚安等）不会触发，也不会消耗分析 token；等你说出真正想做的事，它才开始工作。

我不想被问的时候

输入框左边有个「提问引导」的小开关，点齿轮可以：

• 切换上面的提问时机；
• 本窗口跳过 / 帮我一下；
• 调最多追问几轮（1–10，默认 3）；
• 关掉“开始前先看任务说明”，直接开工。

它也不会一直追问下去。没有新的信息可问了，它会停，把剩下的细节写成“假设”，或者留给你和模型在聊天里慢慢补。

设置里还能改什么

设置 → 提问引导：

• 总开关：不想用了随时关掉；
• 提问时机：同上；
• 后续目标变化时提示更新任务说明：只在你明确说“换个 / 改成 / 重新来”这类话时才会出现，不会每轮都打扰；
• 开始前先看任务说明；
• 最多追问轮数；
• 弹卡时响一声提示音：不想被声音打扰可以关掉；
• 大脑模型：插件自己分析需求时用的模型。默认自动选 DSH 里最新的 DeepSeek 模型 + Max 推理；也可以自己选客户端里任意可用的模型和推理档位。

怎么装

从插件市场看到这个页面的话，点安装就好。

想手动装的话：

dsh plugin add dsh-help-me-to-ask

想直接装最新版：在插件安装输入框里带版本号：

dsh-help-me-to-ask@1.0.5

这是因为 pnpm 默认会给新发布的版本一个 24 小时观察期；带准确版本号可以越过它。或者下载 release 里的 tgz 用本地安装。装好之后重启 DSH（或刷新页面），输入框左边就能看到它了。

一些说明

• 每个聊天窗口只处理第一段真正的工作内容；纯寒暄不触发，之后只有出现明显“改口”信号时才会提示更新任务说明，不会每轮都插话。
• 「帮我一下」是一次性的：只接管当前窗口的下一条消息，处理完自动恢复你原来的模式。
• 它不碰你的模型和推理档位设置。以前我做过一版会自动帮人切模型、切推理，后来发现身边几乎没人真的想为 DSH 选推理等级，就把它去掉了，只留下“问清楚”这件事。
• 正在执行任务的子智能体不会用到这个插件。
• 分析用的模型是你自己在设置里选的那个，调用方式和普通对话一样，数据不会额外传到别的地方。
• 聊天窗口里的任务说明只存在你自己电脑上：$DSH_HOME/dsh-help-me-to-ask-sessions.json。
• 它也有点笨的时候，如果问得不对、或者你觉得哪句话说得不清楚，欢迎告诉我，我慢慢改。

更新日志

见 CHANGELOG.md。

谢谢

写这个插件的时候被 DSH 的社区帮了很多，也谢谢愿意试用它的你。

如果有什么想跟我说的，可以发邮件到 doreihime.cn@gmail.com，我看到会回。

MIT License。

---

English

Hi, thank you for stopping by.

The idea behind this little plugin is pretty simple: when I work in DSH, I often start with something vague like “help me fix this”, and only after the model has done a whole round of work do I realize the direction was off. So I thought: what if something asked me one gentle question before it starts — “did you mean A or B?” — that would save a lot of back-and-forth.

That’s all it does. Before answering, it helps you state your request clearly, turns your answers into a tiny task sheet, and waits for your confirmation before handing it to the model.

Want the newest version directly?

In the DSH plugin install field, enter:

dsh-help-me-to-ask@1.0.5

Pinning the exact version skips pnpm’s 24-hour release-age gate. With the bare package name, DSH may install the slightly older 1.0.2 first.

What it does

In every chat window, on the first real work message (pure greetings don’t count), it shows a card first:

• It repeats back “here’s what I understand you want…”, so you can catch a misunderstanding early;
• It asks only for what’s genuinely missing: goal, deliverable, constraints, acceptance criteria, anything special to watch out for;
• Each question offers concrete options derived from your own words, instead of empty prompts like “please describe your requirements”;
• If you don’t feel like picking each item, press One-click brief and it fills in the gaps itself.

After you answer (or skip), it produces a very short task sheet:

What to make / What you get / Limits (what may be touched, what to use) / How we know it’s done / What not to touch / Guesses for gaps

Check it, confirm, modify, or skip. Once confirmed, the model knows exactly what to do and what “done” means.

A short chime plays when the card appears (can be muted in settings). The card stays for up to 10 minutes with a visible countdown; press “Still writing · +5 min” to extend it. Answers are saved locally as you type, so a refresh or restart restores them.

When it appears

When the plugin is enabled and this chat window isn’t skipped:

• Only when the request is vague — on the first real work message, ask first only if goal / deliverable / constraints are missing;
• Also for complex tasks — on the first real work message, confirm key details even when the goal is clear, if the task looks complex;
• Skip this window — no guidance in this chat window; other windows are unaffected;
• Help me out once (gold) — take over the next message in this chat window, whatever it is, run one confirmation pass, then return to the previous mode automatically.

Pure greetings (hi, hello, thanks, haha, good night…) never trigger it and never spend analysis tokens; it waits for real work intent.

When it stays quiet

There’s a small Ask Guide switch on the left of the input box. Click the gear to:

• switch the trigger mode above;
• skip this window / help me out once;
• set the maximum number of follow-up rounds (1–10, default 3);
• turn off “review the task sheet before starting”.

It also stops on its own: when there is no genuinely new information left, it stops asking and either writes the remaining details as assumptions or leaves them to be resolved in the chat.

Settings

Settings → Ask Guide:

• Master switch — turn it off whenever you like;
• When to ask — same as above;
• Offer to update the task sheet when the goal changes — only reacts to explicit change phrases (“instead”, “redo”, “change it to…”), never nags every turn;
• Review the task sheet before starting;
• Max follow-up rounds;
• Play a chime when the form appears — turn it off if you prefer silence;
• Brain model — the model used for the plugin’s own analysis. By default it auto-picks the newest DeepSeek model in DSH with Max reasoning; you can also choose any available model and reasoning level from the client.

Install

From the plugin market: just click install.

Manually:

dsh plugin add dsh-help-me-to-ask

To install the newest version directly, pin the version in the install field:

dsh-help-me-to-ask@1.0.5

pnpm gives freshly published versions a 24-hour observation window by default; pinning the exact version bypasses it. You can also download the tgz from a release and install locally. Restart DSH (or refresh the page) and the switch will appear next to the input box.

A few notes

• Each chat window handles only its first real work message; pure greetings don’t trigger it, and afterwards it only offers to update the task sheet when an explicit change-of-mind signal appears. It never interrupts every turn.
• Help me out once is one-shot: it takes over the next message in this chat window only, then restores your previous mode.
• It does not touch your model or reasoning-level settings. I once built a version that switched models/reasoning automatically; later I realized almost nobody actually wants to pick reasoning levels for DSH, so I removed it and kept only the “ask clearly first” part.
• Subagents doing work never use this plugin.
• The analysis model is the one you choose in settings; calls go through the same route as normal conversations, and no data is uploaded anywhere else.
• Task-sheet state lives only on your own machine: $DSH_HOME/dsh-help-me-to-ask-sessions.json.
• It can be a bit clumsy sometimes. If it asks the wrong thing or a sentence feels off, tell me and I’ll keep improving it.

Changelog

See CHANGELOG.md.

Thanks

DSH’s community helped me a lot while building this, and thank you for giving it a try.

If you want to reach me, email doreihime.cn@gmail.com — I read it.

MIT License.