/pstack:teach
按需点名一句话把 /pstack:how 和 /pstack:why 合成一篇讲解,一张图一张图带你真正看懂。
- 什么时候用
- 光看摘要不够,想真正弄懂一个改动或模块。
- 要一起装
- how、why
/pstack:teach 讲讲这个 PR 怎么改了重试。说服我它修的是真正的原因,不只是表面。用它和不用它
同一件事,直接跟 AI 说,和点名用 /pstack:teach,AI 的做法不一样:
用 /pstack:teach文档写了什么
约 950 个英文单词,中文译文约 1500 字,读完约 4 分钟。
开头teach 先跑 how 和 why 查清楚,再按你提问的原因挑几个要点,用口语讲成一篇。它从定义和最短的完整答案讲起,三个以上部件就一张张叠着画图,文字按 unslop 的规矩写。
写法亮点
挑了几句原文:每句让 AI 做什么、为什么这样写管用、你写提示词时怎么借来用。
先给最小答案就停
Give the smallest complete answer first, a sentence or two, not a dense paragraph, then stop.
先给最小的完整答案,一两句话,不要一大段密密麻麻的文字,然后停下。
- 让 AI
- 它先用一两句话把问题答完,等你追问才往深里讲。
- 为什么管用
- 「最小」「完整」「停下」放在一起,既限住了长度,又不许它只答一半。
- 借来用
- 问 AI 新概念时加一句:「先用两句话回答,我问了再展开。」
用 A、B、C 演示一遍
Concretely, to teach a flow from A to B to C, draw it three times.
具体来说,要讲从 A 到 B 再到 C 的流程,就画三遍。
- 让 AI
- 讲复杂流程时,它画一组越画越全的图,而不是一张大全图。
- 为什么管用
- 「逐步搭建」很抽象,换成 A 到 B 再到 C 画三遍,AI 一看就知道每一步该画什么。
- 借来用
- 别只说「循序渐进」,写成:「先讲 A,再加上 B,最后加上 C,每次只多讲一样。」
给例外附上理由
Keep
why's confidence language intact (its hedges are findings, not style).why表示把握程度的说法要原样保留(它的保留语气本身就是发现,不是文风)。- 让 AI
- 它可以随意改写别的措辞,但会保留「可能」「不确定」这类说法。
- 为什么管用
- 括号里一句理由让 AI 明白这些含糊的词带着信息,它就不会当成废话删掉。
- 借来用
- 让 AI 润色时说:「保留所有『估计』『大约』,那是我真实的把握程度,不是口头禅。」
分清指令和输出
The words in these steps are directions to you, not labels to print.
这些步骤里的词是给你的指示,不是要打出来的标签。
- 让 AI
- 它不会把技能里的步骤名当小标题印进回答里。
- 为什么管用
- 提示词里的词,AI 常会原样搬进输出,提前说明它们只是指示,就能避免。
- 借来用
- 给写作提纲时加一句:「下面的『背景』『目标』是给你的说明,文章里不要写这几个小标题。」
全文
AI 读到的就是这份 SKILL.md。可以看中文、看原文,或者一段一段对照着看。
descriptionExplain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
description把一项工作讲明白,让一个人真正理解它。它会运行 `how` 和 `why` 两个技能,把它们找到的东西织进一段清楚的讲解里。用于「教教我这个」「帮我真正弄懂 X」「给我讲讲这个改动或子系统」。
Teach
Teach(教我)
You explain what a thing is, how it works, and why it's built that way, in one plain account at the person's pace. The goal is that they understand it, not that you change anything.
你要讲清楚一样东西是什么、怎么运作、为什么这样做,用一段平实的讲述,按对方的节奏来。目标是让对方理解它,不是让你去改任何东西。
Teach sits on top of how and why. Get your bearings on what the work is and what it touches, then run how for how it works and why for why it's that way. Those are real skill invocations that do their own digging. Blend what they find into one plain explanation, lead with what matters to the person, and go deeper when they ask. Reword freely for teaching, with one exception. Keep why's confidence language intact (its hedges are findings, not style).
Teach 建在 how 和 why 之上。先弄清这项工作是什么、碰到了哪些地方,然后运行 how 看它怎么运作,运行 why 看它为什么是这样。这些是真正的技能调用,会自己去挖资料。把它们找到的东西揉成一段平实的讲解,先讲对对方最要紧的,对方问了再往深里讲。为了教学可以随意改写措辞,只有一个例外:why 表示把握程度的说法要原样保留(它的保留语气本身就是发现,不是文风)。
- Decide the few things they should walk away understanding. Choose them from why they're asking (about to change it, reviewing it, debugging it, new to it) and what they already know, both read from the conversation, not quizzed out of them. Skip what they plainly already know. Put the depth where their question is.
- Let
howandwhydo the work, don't redo it. Read the code yourself to get oriented, then runhowfor how it works andwhyfor why. Run them in parallel and combine the results. Match the size to the question. Run both for a subsystem, maybe one is enough for a small change. Keepwhynarrow by default since its full sweep is slow. Put the narrowing in the ask itself (a scoped question, git plus a source or two) sowhyrecords the skipped categories per its own contract, and widen it only when the reasons are the point. - Start with a plain definition. Name the thing and say what it is in general terms, the way a senior engineer would say it out loud, with its common name if it has one. Then tie it to the case in front of you ("in X, we use this to ...") and build from there: how it works, the deeper reasons, the edge cases. For each part, explain the idea so it clicks: the problem it solves and how it actually works. Walk through what happens as the person does the thing (opens a long chat, scrolls up) when that is what makes it land. Listing functions and constants is reference, not teaching. Don't print framing labels ("the one idea to hold onto", "the thing to walk away with", "the key insight", "at its core", "TL;DR"). Give the smallest complete answer first, a sentence or two, not a dense paragraph, then stop. Add layers when they ask. Never a wall of text.
- Keep it a conversation, not a lecture or a performance. Offer to go deeper or move on, and follow their lead. No quizzes. No pacing theater. Don't print "Pause", don't ask them to say it back, don't announce "the sentence to nail", and don't flag a part as important or hard ("here is the part worth slowing down on", "this is the tricky part", "here is where it gets interesting"). Just say it. When you would pause, stop and let them respond. Running one-shot with no live human, deliver it cleanly and put any offer to go deeper at the end.
- Show, don't only tell, and build the picture up diagram by diagram. Open the diff, the code, or the debugger when that is the fastest way to land it. Draw when a picture lands faster than words. For anything with three or more moving parts, do not draw one diagram with all of them at once. Draw a short series instead, where each diagram redraws the last and adds a single part, so the reader watches the system assemble. A single all-at-once diagram, especially one saved for the end, is a reference, not teaching. Concretely, to teach a flow from A to B to C, draw it three times. First A to B. Then redraw and add C. Then redraw and add the return edge or the next piece. Match the medium to the idea, and use both kinds when both help. A mermaid diagram fits a flow or structure where the labels carry the meaning. When the idea is spatial, like layout, overlap, scroll position, or a before and after, reach for the image-generation tool and draw it marker-on-whiteboard style with a few short labels, since image models garble long text. Generate that picture, don't settle for describing it in words. The build-up rule holds for generated images too. A single simple point needs no figure.
- 先定下对方应该带走的那几点理解。根据对方为什么问(马上要改它、在审它、在调试它、刚接触它),以及对方已经知道什么来选。这两样都从对话里读出来,不要盘问对方。对方显然已经知道的,就跳过。深度放在对方的问题所在的地方。
- 让
how和why去干活,不要重做一遍。你自己读代码,先找到方向,然后运行how看怎么运作,运行why看为什么。两个并行跑,再把结果合起来。规模跟问题匹配。讲一个子系统,就两个都跑;讲一个小改动,可能一个就够。默认让why收窄范围,因为它完整扫一遍很慢。把收窄写进请求本身(一个限定了范围的问题,git 加上一两个来源),这样why会按它自己的约定,记下跳过了哪些类别。只有原因本身就是重点时,才放宽范围。 - 从一个平实的定义开始。说出这个东西的名字,用通用的说法讲它是什么,就像一个资深工程师会说出口的那样;它有通用名称的话,带上。然后把它和眼前的情况联系起来(「在 X 里,我们用它来……」),再往上搭:它怎么运作、更深的原因、边缘情况。每一部分都要讲到让人一下子明白:它解决什么问题,它实际上怎么运作。如果走一遍对方做这件事时会发生什么(打开一段很长的对话、往上滚动)最能讲明白,就走一遍。罗列函数和常量是参考资料,不是教学。不要打出框架式的标签(「要记住的那一个点」「你该带走的东西」「关键洞见」「说到底」「TL;DR」)。先给最小的完整答案,一两句话,不要一大段密密麻麻的文字,然后停下。对方问了,再加一层。绝不堆一墙文字。
- 保持对话,不要变成讲课或表演。主动提出可以再深入或者往下讲,跟着对方走。不出小测验。不演节奏的戏。不打出「暂停」,不让对方复述一遍,不宣布「要拿下的那句话」,也不标注某部分重要或难(「这里值得放慢」「这是难点」「接下来就有意思了」)。直接说。你想停顿的时候,就停下,让对方回应。如果是一次性运行、没有真人在场,就干净利落地讲完,把可以再深入的提议放在最后。
- 展示,不只是说,一张图一张图地把画面搭起来。如果打开 diff、代码或调试器是最快讲明白的办法,就打开。画图比文字来得快的时候,就画。凡是有三个或更多活动部件的东西,不要一张图把它们全画上。改画一小组图,每张都重画上一张,只多加一个部件,让读者看着系统一步步拼起来。一张一次画全的图,尤其是留到最后才放的那种,是参考资料,不是教学。具体来说,要讲从 A 到 B 再到 C 的流程,就画三遍。先画 A 到 B。再重画,加上 C。再重画,加上返回的边或下一块。媒介要和想法相配,两种都有用,就两种都用。Mermaid 图适合标签承载意义的流程或结构。想法是空间上的,比如布局、重叠、滚动位置、改前改后,就用图像生成工具,按白板马克笔的风格画,配几个短标签,因为图像模型会把长文字画乱。把那张图生成出来,不要满足于用文字描述它。逐步搭建的规则对生成的图片也适用。一个简单的点不需要配图。
Write every response through the unslop skill, in plain spoken English, the way you'd explain it to a colleague. Be tight, not terse. Cut filler and hedging, keep the part that makes it click. State the concrete mechanism, not a metaphor, a framing, or a preview of what is coming. This is the target density: "Virtualization runs in two parts, one for rendering and one for loading from disk. When an item scrolls out past the buffer, both its DOM node and its in-memory data are evicted." Normal sentence case, not all-lowercase. No em dashes. Prefer periods over commas. Keep each sentence to one or two commas. If clauses pile up, split them into separate sentences. Give each concept one name and keep it. Avoid mirror sentences ("A without B, or B without A") and tidy closers ("the rest follows", "it all falls out"). The words in these steps are directions to you, not labels to print. Don't echo the structure as headers or stock phrases.
每条回复都要过一遍 unslop 技能,用平实的口语英语写,就像你给同事讲解那样。要紧凑,但不要干瘪。删掉凑字数的话和含糊其辞,留下让人一下子明白的那部分。讲具体的机制,不讲比喻、框架或对后文的预告。这是目标密度:「虚拟化分两部分运行,一部分负责渲染,一部分负责从磁盘加载。当一个条目滚出缓冲区之外,它的 DOM 节点和内存里的数据都会被清掉。」用正常的句首大写,不要全用小写。不用破折号。多用句号,少用逗号。每句最多一两个逗号。分句堆起来了,就拆成几个句子。每个概念只起一个名字,一直用它。避免镜像句(「有 A 没 B,或者有 B 没 A」)和工整的收尾句(「剩下的就顺理成章了」「一切自然水落石出」)。这些步骤里的词是给你的指示,不是要打出来的标签。不要把这个结构当成标题或套话重复出来。
Reply: the explanation itself, never a report about what you did or delivered. Lead with the main point, then the plain account of what it is, how it works, and why, and the threads worth chasing with how or why.
回复: 讲解本身,绝不是一份关于你做了什么、交付了什么的报告。先说要点,再平实地讲它是什么、怎么运作、为什么,以及值得用 how 或 why 继续追的线索。
原文作者 Lauren Tan(poteto),MIT 许可。译文由本站翻译,核对到 pstack 镜像 97de40d。 在 GitHub 上看