跳到正文
  1. 技能速查
  2. 汇报、复盘、越用越顺
  3. /pstack:ketchup-video

/pstack:ketchup-video

按需点名

一句话和 /pstack:ketchup 一样,但做成一段带字幕的幻灯片小视频。

什么时候用
想「看」进展,不想读。
要一起装
ketchup、bro
这样说
/pstack:ketchup-video

用它和不用它

同一件事,直接跟 AI 说,和点名用 /pstack:ketchup-video,AI 的做法不一样:

直接说用 /pstack:ketchup-video
幻灯片做成要点列表或表格每张只讲一点,在同一张图上变化,用箭头和高亮指出改动
字幕压在画面上,挡住内容字幕放在画面下方等高的条里,从不遮挡画面
渲染完不看就发出来每张抽一帧看字幕,量停留时长,读不完就重渲

文档写了什么

原文分 3 节,约 650 个英文单词,中文译文约 1150 字,读完约 3 分钟。点一节直接跳到全文。

开头说明它照 /pstack:ketchup 的规则走,只把总结和配图换成带字幕的短视频,回复里只放开头一句、视频、剩下的工作和待办。

  1. 1幻灯片先写一句要你记住的话和每张一行提纲,最多 10 张,只用真实截图、diff 和数据。
  2. 2字幕每张配一行约 10 个词的字幕,说画面的意思,放在画面下方固定高度的条里。
  3. 3渲染渲染一段无声横屏视频,字幕烧进画面,每三个词停一秒,发前逐张抽帧、量时长。

看写法亮点读全文

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。

  1. 动手前先写一句主旨

    Before you draw, write the one sentence the user should leave with and one line per slide.

    动手画之前,先写下用户看完应该记住的那一句话,以及每张幻灯片一行。

    让 AI
    整段视频围着一句主旨走,每张幻灯片都在帮你记住这句话。
    为什么管用
    先逼 AI 说出到底要传达什么,再动手,做出来的东西才不会东一块西一块。
    借来用
    让 AI 写报告前加一句:「先写下读者看完该记住的一句话,再动笔。」
  2. 把「够久」换成算式

    at least one second for each three words

    每三个词至少一秒

    让 AI
    每张幻灯片停的时间够你读完上面的字,不会一闪而过。
    为什么管用
    「停够久」是感觉,「每三个词一秒」是能算、也能事后核对的规矩。
    借来用
    把感觉换成算式:「回复按问题数来定长度,每个问题最多三句话。」
  3. 点名会骗人的检查方法

    not with a still-frame detector, which counts the faint ends of a fade as still

    不要用静止画面检测器,因为它会把淡入淡出末尾那点微弱的变化也算成静止

    让 AI
    它真的去核对每张停了多久,而不是相信一个会算错的工具。
    为什么管用
    说出常用工具具体错在哪,AI 就不会拿一个看起来对的数字糊弄过去。
    借来用
    让 AI 查链接时写明:「要打开页面看内容,不能只看状态码,有的错误页也返回 200。」

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。

descriptionCatch the user up like /pstack:ketchup, with a short subtitled video of slides for what happened and the waiting calls as text under it. Use for /pstack:ketchup-video.

description像 /pstack:ketchup 一样帮用户追上进度,但把发生了什么做成一段带字幕的幻灯片短视频,等用户拍板的事以文字写在视频下面。用于 /pstack:ketchup-video。

Ketchup video

Ketchup video(视频版追上进度)

Follow /pstack:ketchup, but show what happened in a short subtitled video instead of its summary and visuals. Its window starts at the last message the user wrote before /pstack:ketchup-video, not before any earlier /pstack:ketchup. Writing and rendering the video, outside the repo, is the one exception to its read-only rule. The reply is ketchup's opening sentence, the embedded video, one line naming any work left that you can do yourself, and the action items. When the video shows a call's options, call each option by the name the video gives it. If the render fails, say so in one line and give only the calls.

按 /pstack:ketchup 来做,但用一段带字幕的短视频展示发生了什么,代替它的总结和图。它的时间窗口从用户在 /pstack:ketchup-video 之前写的最后一条消息开始,而不是从更早的某次 /pstack:ketchup 之前开始。在仓库外面制作和渲染视频,是它「只看不改」规则的唯一例外。回复由这几样组成:ketchup 的开头那一句、嵌在正文里的视频、用一行说出还剩哪些活你自己能做,以及待办事项。视频里展示了某个决定的几个选项时,就用视频给每个选项起的名字来叫它。如果渲染失败,用一行说出来,然后只给出等用户做的决定。

Slides

幻灯片

Use the screenshots, recordings, diffs, and data the work produced, not the chat's prose about them. Before you draw, write the one sentence the user should leave with and one line per slide. Drop each slide that does not change what the user knows. Use at most 10 slides, and fewer is better. Neither note goes in the reply.

用工作中产生的截图、录屏、diff 和数据,不用对话里关于它们的描述。动手画之前,先写下用户看完应该记住的那一句话,以及每张幻灯片一行。去掉每一张不会改变用户所知的幻灯片。最多 10 张,越少越好。这两样笔记都不放进回复。

Each slide makes one point. Build the slides on one picture and change it from slide to slide, rather than cut to an unrelated one. A color or shape means the same thing on every slide. Show the work in pictures, such as how a system works, a PR stack with each PR's state, a before and after of a fix, or options side by side. Point at what changed with arrows, highlights, and motion. A slide is never a bullet list, a status list, a table, or boxes with nothing connecting them.

每张幻灯片讲一个点。所有幻灯片都建立在同一张画面上,一张一张地改它,而不是切到一张不相干的画面。一种颜色或形状,在每张幻灯片上都表示同一个意思。用画面展示工作,比如一个系统怎么运作,一串 PR 以及每个 PR 的状态,一处修复的改前改后,几个选项并排对比。用箭头、高亮和动画指出变了什么。幻灯片绝不是要点列表、状态清单、表格,也不是几个互不相连的框。

Keep text to the minimum. Put each label on the thing it names, in plain words a person would say, not tags like "Tests: pass". Never caption what a picture shows, and never give a fact twice, across slides or in the text under them.

文字压到最少。每个标签都放在它所指的东西上,用人会说的大白话,不写「测试:通过」这种标签。绝不给画面已经展示的东西配说明。同一个事实绝不说两遍,几张幻灯片之间不行,下面的文字里也不行。

Show what came of each thing the user asked for, and whether it is done, still running, failed, or not checked. Never show something done that still waits on the user. Show any bug found and fixed on the way. If a visible change has no screenshot, say so on its slide and name what changed on screen. Draw only from facts you have. Never invent a number, and never draw a screen you did not capture.

展示用户要过的每件事有什么结果,以及它是做完了、还在跑、失败了,还是没检查。还在等用户的事,绝不显示成做完。路上发现并修好的 bug,要展示出来。如果一处看得见的变化没有截图,就在它的幻灯片上说出来,并说清屏幕上变了什么。只用你掌握的事实来画。绝不编数字,绝不画一张你没真正截到的界面。

Subtitles

字幕

Give each slide one short subtitle line, about ten words, that says its point the way you would tell the user, from only what that slide shows. Say what the picture means rather than read out its labels. Put the subtitle in a strip below the slide, the same height on every slide and empty except for the subtitle, so it never covers the slide. Set it small, but readable when the video plays at chat size.

每张幻灯片配一行短字幕,大约十个词,用你会对用户说的方式说出这张的要点,只根据这张幻灯片展示的内容。说出画面意味着什么,而不是把上面的标签念一遍。字幕放在幻灯片下方的一条字幕带里,每张幻灯片上这条带子的高度都一样,里面除了字幕什么都没有,这样字幕永远不会挡住幻灯片。字号设小一点,但视频以聊天窗口的大小播放时要看得清。

Render

渲染

Render one silent landscape video, such as an mp4, with motion between slides. Every frame is the slide itself, edge to edge, above its subtitle strip. Make the frames from the slides, never by recording a screen, and burn each subtitle into its slide's frames so it stays on screen for the slide's whole hold. The hold is the time a slide is fully on screen, not counting the motion into or out of it. Hold each slide long enough to read the words it adds, at least one second for each three words. A slide adds its subtitle and each word that was not on the slide before it, including a label it changes. The first slide adds all its words. Words inside a screenshot do not count.

渲染一段无声的横屏视频,比如 mp4,幻灯片之间有动画过渡。每一帧都是幻灯片本身,铺满整个画面,下面是它的字幕带。帧要从幻灯片生成,绝不靠录屏,并且把每条字幕烧进它那张幻灯片的帧里,让它在这张幻灯片停留的整段时间里都在屏幕上。停留时间指一张幻灯片完整显示在屏幕上的时间,不算切入和切出的动画。每张幻灯片停留的时间,要够读完它新增的字,每三个词至少一秒。一张幻灯片新增的字,包括它的字幕,以及上一张没有的每个词,也包括它改动过的标签。第一张幻灯片的所有字都算新增。截图里面的字不算。

Before you embed the video, check the rendered file. Look at one frame from each slide at chat size, and check that its subtitle is readable and covers nothing. Measure each hold by matching the file's frames to the slide, not with a still-frame detector, which counts the faint ends of a fade as still. Count the words each slide adds against its measured hold. Fix any slide you cannot read in that time, render again, and check again.

嵌入视频之前,检查渲染出来的文件。每张幻灯片取一帧,按聊天窗口的大小看,检查字幕看得清,并且没挡住任何东西。量每张的停留时间,要拿文件里的帧去对应幻灯片,不要用静止画面检测器,因为它会把淡入淡出末尾那点微弱的变化也算成静止。把每张幻灯片新增的字数和量出来的停留时间对一对。读不完的幻灯片就改,重新渲染,再检查一遍。

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

本站是 pstack 的非官方入门教程,不是官方文档;pstack 由 poteto 开发,命令和行为以官方仓库为准。教程原始源码见 GitHub。

由 airali部署,基于小小东的 MIT 授权教程改编。