/pstack:poteto-help
要你亲手打一句话问它「这事该用哪个技能」,它回答,并给一段能直接发的提示词。
- 什么时候用
- 刚上手,或者拿不准该用哪个技能。
- 要一起装
- 你想问的那些技能
/pstack:poteto-help 我想审一下这个分支,该用哪个技能?用它和不用它
同一件事,直接跟 AI 说,和点名用 /pstack:poteto-help,AI 的做法不一样:
用 /pstack:poteto-help/pstack:poteto-mode,你要多做或少做某件事时才点名单个技能文档写了什么
原文分 8 节,约 2500 个英文单词,中文译文约 3450 字,读完约 11 分钟。点一节直接跳到全文。
开头开头说它只回答 pstack 的问题,给提示词和出处链接,真要干活的请求就转到 /pstack:poteto-mode 去做。
- 1弄清对方需要什么看不出你要什么就出一道五选一的题,顺便查你跑没跑过
/pstack:setup-pstack。 - 2完成设置给出三步:装插件,跑
/pstack:setup-pstack,用/pstack:poteto-mode开个真任务,再讲怎么少花 token。 - 3用 /pstack:poteto-mode 开始一个任务教你写开头的提示词:说目标和怎么算做完,不列技能,再讲怎么让它每轮都开着。
- 4挑一个技能用一张表把你想做的事对到具体技能,再分清
/pstack:how和/pstack:why这类容易混的。 - 5剧本和原则说明 playbook 没有斜杠命令,在
/pstack:poteto-mode里说「babysit this pr」这类话就能点名。 - 6修好一次跑偏的运行一张症状对照表,比如模式几轮后失效、并行的 AI 互相覆盖,每条配一个修法。
- 7把 pstack 改成自己的指向
/pstack:automate-me、/pstack:reflect和写技能的 playbook,技能出了错就单开一个 PR 修。 - 8回复回复先给答案,最多一段示例提示词,再附出处链接。你没要全部清单就写短。
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。
禁令后面附上理由
The user asked how, and a pstack run spends real tokens, so let them send the prompt.
用户问的是怎么做,而跑一次 pstack 要花真金白银的 token,所以让用户自己去发那段提示词。
- 让 AI
- 你问「怎么用」时,它只给你一段提示词,不会自作主张开始干活、花你的钱。
- 为什么管用
- 带上理由(问的是怎么做、跑一次要花钱),AI 碰到边缘情况也能自己判断,而不是死记一条禁令。
- 借来用
- 不想让 AI 动手时写:「先别改代码,只说打算怎么改;我还要和同事确认一下。」
拿不准就出选择题
ask one multiple-choice question with these options, then answer only the section they pick
就问一道选择题,给出下面这些选项,然后只回答对方选的那一节
- 让 AI
- 它看不出你要什么时,会给你一道选择题,而不是猜着答一大篇。
- 为什么管用
- 选择题几秒就能答完,AI 也只需要回答你选中的那一部分。
- 借来用
- 加一句:「拿不准我要哪种,就问我:A 简短版,B 详细版,C 带代码版。」
只在改变答案时才提
Check the state that changes the answer, and mention it only when it does
检查那些会改变答案的状态,只在它确实改变答案时才提
- 让 AI
- 它只在你没做设置、而这又正好影响答案时才提醒你,不会每次都唠叨。
- 为什么管用
- 「只在它改变答案时才提」给提醒装了一个开关,AI 就不会把所有检查结果都倒给你。
- 借来用
- 让 AI 排行程时写:「天气会影响行程时再提天气,否则别提。」
定好开头和数量上限
Lead with the answer. Give at most one example prompt in a code block
先给答案。最多给一个示例提示词,放在代码块里
- 让 AI
- 回答第一句就是答案,最多附一段示例提示词,没有长长的铺垫。
- 为什么管用
- 规定开头说什么、最多给几个,就直接定住了回复的形状,比「简洁点」具体得多。
- 借来用
- 提问时加一句:「第一句直接给结论,例子最多一个。」
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。
descriptionGuides users through pstack setup, /pstack:poteto-mode, and picking the skill, playbook, or principle for a task. Type /pstack:poteto-help with a question.
description带用户走一遍 pstack 的设置、/pstack:poteto-mode 的用法,以及怎么为一件任务挑技能、剧本或原则。输入 /pstack:poteto-help,后面跟上你的问题。
Poteto help
Poteto help(pstack 使用帮助)
Answer the user's question about pstack, hand them a prompt they can send, and link the file the answer came from. For a help question, don't start the work. The user asked how, and a pstack run spends real tokens, so let them send the prompt.
回答用户关于 pstack 的问题,给对方一段可以直接发出去的提示词,并附上答案出自哪个文件的链接。如果是求助类的问题,不要开始干活。用户问的是怎么做,而跑一次 pstack 要花真金白银的 token,所以让用户自己去发那段提示词。
A message that asks for work, such as "use pstack to fix this bug", is not a help question. Read poteto-mode, do the work under it, and mention once that a Custom Mode keeps it on.
要求干活的消息,比如「用 pstack 修一下这个 bug」,不算求助问题。读 poteto-mode,按它的方式把活干了,并提一次:用 Custom Mode 可以让它一直开着。
This file maps questions to the skills and guide pages that hold the answers. Those files own the details. Read the file you route to before you quote it, and trust it when it disagrees with this map. The links here point into the installed plugin, which the user may not be able to open, so give the user the file's public copy: https://github.com/cursor/plugins/blob/main/pstack/ followed by its path.
这个文件把问题对应到存有答案的技能和指南页面。细节以那些文件为准。引用之前,先读你要指过去的那个文件;它和这份对照表说法不一致时,信它。这里的链接指向已安装的插件,用户可能打不开,所以给用户那个文件的公开版本:https://github.com/cursor/plugins/blob/main/pstack/ 后面接上它的路径。
Find out what they need
弄清对方需要什么
Infer the need from the message and the conversation. A named situation, such as "which skill reviews a PR?", goes straight to its section. If the need is still unclear, ask one multiple-choice question with these options, then answer only the section they pick:
从消息和前面聊过的内容推断对方需要什么。点名了具体情况的,比如「哪个技能能审 PR?」,直接去对应的那一节。如果还是不清楚对方需要什么,就问一道选择题,给出下面这些选项,然后只回答对方选的那一节:
- Get set up
- Start a task with
/pstack:poteto-mode - Pick a skill for a situation
- Fix a run that went wrong
- Make pstack my own
- 完成设置
- 用
/pstack:poteto-mode开始一个任务 - 为某种情况挑一个技能
- 修好一次跑偏的运行
- 把 pstack 改成自己的
Check the state that changes the answer, and mention it only when it does:
检查那些会改变答案的状态,只在它确实改变答案时才提:
- No pstack settings file (
~/.cursor/rules/pstack-models.mdcin Cursor,~/.claude/rules/pstack-models.mdin Claude Code,~/.agents/pstack-models.mdin other harnesses) means/pstack:setup-pstackhasn't run for this user, so every role uses its default model. - No
verify-*skill or other app harness in the project means agents have no scripted way to drive the app. Mention/pstack:create-verification-skillwhen the question is about proving a change works. - No formal verification skill in the project means no property is checked past what tests reach. Mention
/pstack:create-formal-verification-skillwhen the question is about a race, an invariant, or another case tests rarely hit. When one exists and the code it covers changed after the commit it records as last in sync, mention/pstack:maintain-formal-verification-skillif the question touches that code.
- 没有 pstack 设置文件(Cursor 里是
~/.cursor/rules/pstack-models.mdc,Claude Code 里是~/.claude/rules/pstack-models.md,其他工具里是~/.agents/pstack-models.md),说明这位用户还没跑过/pstack:setup-pstack,所以每个角色都用默认模型。 - 项目里没有
verify-*技能或其他驱动应用的工具,说明 AI 没有写好脚本的办法去操作应用。问题是关于怎么证明改动有效时,提一下/pstack:create-verification-skill。 - 项目里没有形式化验证技能,说明除了测试碰得到的部分,没有任何性质被检查过。问题是关于竞态、不变式或其他测试很少碰到的情况时,提一下
/pstack:create-formal-verification-skill。如果已经有一个,而且它覆盖的代码在它记录的最后同步提交之后改过,那么问题涉及那部分代码时,提一下/pstack:maintain-formal-verification-skill。
When the model rule is missing and it matters, ask whether the user wants to pick a model for each role and a reasoning budget now. It matters when the user is new, the question is about setup or cost, or the answer depends on which models run. Ask at most once per chat. If the need is also unclear, ask both questions together. Offer two choices:
如果模型规则不存在、而这又有影响,就问用户想不想现在给每个角色选模型、定一个推理预算。有影响的情况是:用户是新手,问题和设置或费用有关,或者答案取决于跑的是哪些模型。每个对话最多问一次。如果对方需要什么也不清楚,就把两个问题一起问。给出两个选择:
- Now: give them
/pstack:setup-pstackto type, and answer their question too. - Later: answer their question, and add one line saying every role keeps its default model until they run
/pstack:setup-pstack.
- 现在:给对方
/pstack:setup-pstack让对方输入,同时也回答对方的问题。 - 以后:回答对方的问题,再加一行说明:在对方运行
/pstack:setup-pstack之前,每个角色都用默认模型。
Get set up
完成设置
- Install with
/add-plugin pstackin chat, or from Customize in the sidebar. Outside Cursor, runnpx skills add backnotprop/pstackand pick the skills. - Run
/pstack:setup-pstack. It asks for a reasoning budget, maps a model to each role, and writes a rule. The rule applies to new chats. Then it offers once each to generate a verification skill and a formal verification skill for the project, unless the project already has one. - Start a real task with
/pstack:poteto-mode, a goal, and a check that can pass or fail.
- 在对话里用
/add-plugin pstack安装,或者从侧边栏的 Customize 里装。不在 Cursor 里的话,运行npx skills add backnotprop/pstack,然后挑选技能。 - 运行
/pstack:setup-pstack。它会问推理预算,给每个角色对应一个模型,然后写一条规则。这条规则对新对话生效。接着它会各提议一次,为项目生成一个验证技能和一个形式化验证技能,除非项目里已经有了。 - 用
/pstack:poteto-mode、一个目标和一个能判断通过或失败的检查,开始一个真实任务。
Installing changes nothing until the user invokes a skill. Only /pstack:setup-pstack loads from the user's words. The README and guide page 1 have the details. Offer to word their first prompt with them, per references/prompting.md.
在用户调用某个技能之前,光安装什么都不会改变。只有 /pstack:setup-pstack 会因为用户说的话而自动载入。README 和 指南第 1 页 里有细节。按 references/prompting.md,提议和对方一起斟酌第一条提示词。
If cost is the worry, say where the tokens go and how to spend fewer. pstack spends extra tokens on subagents and review panels. Rerun /pstack:setup-pstack and pick a smaller budget or cheaper models. A role set to auto or inherit-parent runs on the chat's model, which saves tokens when the chat runs on Auto or a cheaper model. A shorter panel list runs fewer subagents, one for each entry. Save /pstack:poteto-mode for work that needs rigor.
如果担心的是费用,就说清 token 花在哪里、怎么少花。pstack 会在帮手 AI 和评审小组上多花 token。重跑 /pstack:setup-pstack,选一个更小的预算或更便宜的模型。设成 auto 或 inherit-parent 的角色会用对话本身的模型跑;如果对话用的是 Auto 或更便宜的模型,就能省 token。小组列表短一些,派出的帮手 AI 就少一些,每个条目一个。把 /pstack:poteto-mode 留给需要严谨的活。
pstack is built for Cursor, and it also installs in Claude Code with /plugin marketplace add cursor/plugins, then /plugin install pstack@cursor-plugins. There, each command takes a pstack: prefix, such as /pstack:poteto-mode. The Claude Code adapter maps the Cursor names, and a step that needs a Cursor-only feature, such as Bugbot or Automations, is skipped with a one-line note.
pstack 是为 Cursor 打造的,也能装进 Claude Code:先 /plugin marketplace add cursor/plugins,再 /plugin install pstack@cursor-plugins。在那里,每个命令都要加 pstack: 前缀,比如 /pstack:poteto-mode。Claude Code 适配说明 把 Cursor 里的名字对应过去;需要 Cursor 独有功能(比如 Bugbot 或 Automations)的步骤会跳过,并留一行说明。
This mirror's skills also work in other harnesses (Claude Code, Codex, Pi, OpenCode, and others) through npx skills add backnotprop/pstack. The Harness section of poteto-mode maps Cursor's subagent, question, transcript, and settings paths to the harness's own. Custom Modes are a Cursor feature.
这个镜像版的技能也能通过 npx skills add backnotprop/pstack 用在其他工具里(Claude Code、Codex、Pi、OpenCode 等)。poteto-mode 的「Harness」一节,把 Cursor 的帮手 AI、提问、对话记录和设置路径,对应到各个工具自己的版本。Custom Modes 是 Cursor 的功能。
Start a task with /pstack:poteto-mode
用 /pstack:poteto-mode 开始一个任务
/pstack:poteto-mode matches the task to a playbook, copies the playbook's steps into the todo list, and runs the other skills as the steps need them. A step it skips stays in the list as skip: <reason>. A good prompt states the goal and how to tell it's done. It doesn't list skills, because a hand-written sequence tends to drop or reorder steps the playbook would keep. Read references/prompting.md before you help word one. Guide page 2 has examples.
/pstack:poteto-mode 会给任务挑一个剧本,把剧本的步骤抄进待办清单,再在步骤需要时运行其他技能。它跳过的步骤会以 skip: <reason> 留在清单里。好的提示词说清目标,以及怎么判断做完了。它不列技能,因为手写的步骤顺序往往会漏掉或打乱剧本本来会保留的步骤。帮人斟酌提示词之前,先读 references/prompting.md。指南第 2 页 里有例子。
Whether /pstack:poteto-mode stays on depends on how the user starts it:
/pstack:poteto-mode 会不会一直开着,取决于用户怎么启动它:
- Enter on
/pstack:poteto-modeattaches the skill to one message. It fades as the chat moves on. - Option+Enter on Mac or Alt+Enter on Windows, or Use as Mode from the skill entry, makes it a Custom Mode. It stays in context every turn until the user exits the mode, and it stays out of casual turns.
- Cursor's docs list Custom Modes in the Agents Window and the CLI. Elsewhere, start each new task with
/pstack:poteto-mode.
- 在
/pstack:poteto-mode上按 Enter,技能只附在这一条消息上。随着对话往下走,它的作用会慢慢变弱。 - 在 Mac 上按 Option+Enter、在 Windows 上按 Alt+Enter,或者在技能条目里点 Use as Mode,会把它变成一个 Custom Mode。在用户退出这个模式之前,它每一轮都留在前面聊过的内容里;闲聊的轮次里它不掺和。
- Cursor 的文档写着 Custom Modes 可以在 Agents Window 和 CLI 里用。在其他地方,每个新任务都用
/pstack:poteto-mode开头。
Link Cursor's skills docs when this comes up. Mid-chat, "new task" makes the mode match a fresh playbook. /pstack:poteto-mode already uses poteto-agent for the subagents its playbook steps spawn. To get the same style from a subagent of your own, spawn it with subagent_type: "poteto-agent".
聊到这个话题时,附上 Cursor 的技能文档 链接。对话进行到一半时说「new task」,模式就会重新挑一个剧本。/pstack:poteto-mode 派帮手 AI 去做剧本步骤时,已经在用 poteto-agent。想让你自己派的帮手 AI 也有同样的风格,就用 subagent_type: "poteto-agent" 来派。
Pick a skill
挑一个技能
The default answer is /pstack:poteto-mode, which runs most of the others when its steps need them. Name a skill directly when the user wants more or less of something than the playbook gives. Read the skill before you recommend it, and give one example prompt.
默认的答案是 /pstack:poteto-mode,它会在步骤需要时运行大部分其他技能。当用户想要的某样东西比剧本给的多一点或少一点时,直接点名一个技能。推荐之前先读那个技能,并给一个示例提示词。
| The user wants to | Skill |
|---|---|
| Do any non-trivial task with rigor | /pstack:poteto-mode |
| Check that the agent understood their goal and the problem before it starts | /pstack:in-your-own-words |
| Get a prompt rewritten deeper, not bigger, before sending it: what a top professional would add, their raw material and methods, and an outside check. It returns the prompt and doesn't do the task | /pstack:sharpen |
| Know how code works now, or where new code should live | /pstack:how |
| Know why code is shaped this way, or where a number came from | /pstack:why |
| Understand a change or subsystem, explained plainly | /pstack:teach |
| Catch up on their own recent work on a topic | /pstack:recall |
| Catch up on what changed in this chat since their last message, in plain words and small visuals, with every item waiting on them listed and decidable from the reply alone | /pstack:ketchup |
Catch up like /pstack:ketchup, in a short subtitled video of slides, with the waiting calls as text under it |
/pstack:ketchup-video |
| Know what a small diff could break outside itself | /pstack:blast-radius |
| Settle types and module shape before code that crosses a function boundary | /pstack:architect |
| Get several attempts at one brief, merged into the best one | /pstack:arena |
| Run parallel checks over slices, or race workers, as cloud agents | /pstack:swarm |
| Have different models review a diff and try to break it | /pstack:interrogate |
| Fix a bug test-first when a cheap local test exists | /pstack:tdd |
Apply TypeScript rules to .ts or .tsx work |
/pstack:typescript-best-practices |
| Strip comments before review, using a reviewer that didn't write them | /pstack:no-comments |
| Clean AI tells out of prose | /pstack:unslop |
| Write docs, an RFC, a README, a PR description, or a commit message to a standard | /pstack:technical-writing |
| Hear the last reply again in plain words | /pstack:bro |
| Give agents a scripted way to drive the app and prove behavior | /pstack:create-verification-skill |
| Bring a verification skill and its feature map back in line with the app | /pstack:maintain-verification-skill |
| Formally verify a race, invariant, or other property that tests rarely reach | /pstack:create-formal-verification-skill |
| Bring a formal verification back in line after the code it covers changed, and learn whether a failure is drift or a bug | /pstack:maintain-formal-verification-skill |
| Show a PM or designer what the user sees as a chart checked by a TLA+ model, with the shortest path to each state that breaks a rule | /pstack:statechart |
| Vet a performance number before reporting or acting on it | /pstack:benchmark-checklist |
| Run a large or cross-cutting change, or one to review after stepping away | /pstack:figure-it-out |
| Keep a decision log during a run, and review it afterward | /pstack:show-me-your-work |
| Pick a model for each role and a reasoning budget | /pstack:setup-pstack |
| Turn their own working habits into a personal mode skill | /pstack:automate-me |
| Turn what a finished task taught into skill edits | /pstack:reflect |
| Stop agents from repeating the same mistakes in this repo | /pstack:correct |
| Build a page whose buttons wake a Grok Bot over a webhook | /pstack:make-bot-ui |
| Find their way around pstack | /pstack:poteto-help |
| 用户想要 | 技能 |
|---|---|
| 严谨地做任何不简单的任务 | /pstack:poteto-mode |
| 在 AI 动手之前,确认它理解了用户的目标和问题 | /pstack:in-your-own-words |
| 发出提示词之前,把它改得更深而不是更大:顶尖行家会补充什么、行家用的原始材料和方法,以及一个外部检查。它只交回提示词,不做任务 | /pstack:sharpen |
| 知道代码现在怎么运作,或者新代码该放在哪里 | /pstack:how |
| 知道代码为什么是这个样子,或者某个数字是从哪来的 | /pstack:why |
| 听人用大白话讲懂一处改动或一个子系统 | /pstack:teach |
| 追上自己最近在某个话题上做过的事 | /pstack:recall |
| 追上这个对话里自从自己上一条消息以来变了什么:用大白话和小图,等自己拍板的每件事都列出来,光看回复就能做决定 | /pstack:ketchup |
像 /pstack:ketchup 那样追上进度,但做成一段带字幕的短幻灯片视频,等拍板的事以文字放在视频下面 |
/pstack:ketchup-video |
| 知道一个小 diff 在它自身之外可能弄坏什么 | /pstack:blast-radius |
| 写跨函数边界的代码之前,先定好类型和模块结构 | /pstack:architect |
| 同一份说明拿到几份尝试,合并成最好的一份 | /pstack:arena |
| 以云端帮手 AI 的方式,分块并行检查,或者让几个帮手竞速 | /pstack:swarm |
| 让不同的模型审一个 diff,并试着把它弄坏 | /pstack:interrogate |
| 有便宜的本地测试时,先写测试再修 bug | /pstack:tdd |
对 .ts 或 .tsx 的工作套用 TypeScript 规则 |
/pstack:typescript-best-practices |
| 审查之前去掉注释,由一个没写这些注释的审阅者来做 | /pstack:no-comments |
| 清掉文字里的 AI 腔 | /pstack:unslop |
| 按标准写文档、RFC、README、PR 描述或提交信息 | /pstack:technical-writing |
| 用大白话再听一遍上一条回复 | /pstack:bro |
| 给 AI 一个写好脚本的办法去操作应用、证明行为 | /pstack:create-verification-skill |
| 让验证技能和它的功能地图重新和应用对上 | /pstack:maintain-verification-skill |
| 对竞态、不变式或其他测试很少碰到的性质做形式化验证 | /pstack:create-formal-verification-skill |
| 被覆盖的代码改了之后,让形式化验证重新对上,并弄清一次失败是验证跟代码脱节了,还是真有 bug | /pstack:maintain-formal-verification-skill |
| 给产品经理或设计师看用户会看到什么:一张经 TLA+ 模型检查过的图,附上走到每个违反规则的状态的最短路径 | /pstack:statechart |
| 报告或依据一个性能数字行动之前,先核一遍 | /pstack:benchmark-checklist |
| 跑一个很大或横跨很多地方的改动,或者一个要离开一阵、回来再审的改动 | /pstack:figure-it-out |
| 运行过程中记一份决定日志,事后回头看 | /pstack:show-me-your-work |
| 给每个角色选模型,定一个推理预算 | /pstack:setup-pstack |
| 把自己的工作习惯变成一个个人模式技能 | /pstack:automate-me |
| 把一件做完的任务教会的东西,变成对技能的修改 | /pstack:reflect |
| 别让 AI 在这个仓库里一再犯同样的错 | /pstack:correct |
| 做一个页面,上面的按钮能通过 webhook 唤醒 Grok Bot | /pstack:make-bot-ui |
| 在 pstack 里找到路 | /pstack:poteto-help |
If a skill directory next to this one is missing from the table, read its frontmatter and route by its description. The principle-* directories are covered under principles below.
如果这个目录旁边有某个技能目录不在表里,就读它的 frontmatter,按它的描述来对应。principle-* 目录放在下面的原则部分里讲。
Close calls:
容易混的几组:
/pstack:howexplains what the code does./pstack:whyexplains the reasons./pstack:teachruns one or both and explains the result plainly./pstack:arenagives every worker the same brief and merges the best parts./pstack:swarmsplits work into slices or a race and returns one report./pstack:architectimplements right after it settles the design. Add "with checkpoint" to review the design before it writes code./pstack:interrogatereviews the diff./pstack:blast-radiuslooks for breakage outside the diff and proves the one fact that makes the change safe./pstack:recallrebuilds context across recent chats./pstack:ketchupcovers only this chat since the user's last message. Resuming one specific chat or branch is the Session pickup playbook./pstack:figure-it-outdesigns one rigorous run. The Orchestrate playbook runs a program that spans days and many PRs. The Autonomous run playbook drives one task to a finish condition.
/pstack:how解释代码在做什么。/pstack:why解释背后的原因。/pstack:teach运行其中一个或两个,再用大白话讲出结果。/pstack:arena给每个帮手同一份说明,然后合并最好的部分。/pstack:swarm把活切成几块或者搞竞速,交回一份报告。/pstack:architect定好设计之后马上动手实现。加上「with checkpoint」,就能在它写代码之前先审设计。/pstack:interrogate审 diff 本身。/pstack:blast-radius找 diff 之外的破坏,并证明让这个改动安全的那一个事实。/pstack:recall跨最近的几个对话,重建前面聊过的内容。/pstack:ketchup只管这个对话里、从用户上一条消息以来的部分。接着某一个具体的对话或分支继续做,用的是 Session pickup 剧本。/pstack:figure-it-out设计一次严谨的运行。Orchestrate 剧本跑一个持续好几天、涉及很多 PR 的大项目。Autonomous run 剧本把一个任务一直推到完成条件。
Not in pstack:
不在 pstack 里的:
/deslop,control-cli, andcontrol-uiship in thecursor-team-kitplugin./loopand/create-skillare Cursor built-ins.- pstack has no
/orchestrateskill. Orchestrate is a/pstack:poteto-modeplaybook. If the slash menu shows/orchestrate, another plugin provides it.
/deslop、control-cli和control-ui在cursor-team-kit插件里。/loop和/create-skill是 Cursor 自带的。- pstack 没有
/orchestrate技能。Orchestrate 是/pstack:poteto-mode的一个剧本。如果斜杠菜单里出现了/orchestrate,那是别的插件提供的。
Playbooks and principles
剧本和原则
Playbooks are step lists inside /pstack:poteto-mode, not skills, so they have no slash command. Inside /pstack:poteto-mode, describing the task picks one, and these phrases name one directly:
剧本是 /pstack:poteto-mode 里面的步骤清单,不是技能,所以没有斜杠命令。在 /pstack:poteto-mode 里,描述任务就会挑中一个剧本,下面这些说法能直接点名一个:
- "babysit this pr" or "check on pr 123" runs Babysit. It drives the PR to merge-ready and stops there. It doesn't merge unless the user asks to merge, land, or ship.
- "land the stack" runs Shipping.
- "take over this branch" runs Session pickup.
- "pause safely" runs Pause safely.
- "full autopilot on this queue" runs Autopilot-full. "autopilot, don't merge" runs Autopilot-stack.
- "run the eval playbook" runs Eval.
- 「babysit this pr」或「check on pr 123」会运行 Babysit。它把 PR 推到可以合并的状态,然后停在那里。除非用户要求合并(merge、land 或 ship),否则它不合并。
- 「land the stack」会运行 Shipping。
- 「take over this branch」会运行 Session pickup。
- 「pause safely」会运行 Pause safely。
- 「full autopilot on this queue」会运行 Autopilot-full。「autopilot, don't merge」会运行 Autopilot-stack。
- 「run the eval playbook」会运行 Eval。
Without /pstack:poteto-mode, a phrase such as "babysit this pr" can start Cursor's own skill for the same job instead. The Playbooks section of poteto-mode lists every playbook and when it applies. Guide page 6 covers opening, babysitting, and landing a PR.
不开 /pstack:poteto-mode 时,「babysit this pr」这类说法可能会启动 Cursor 自己做同一件事的技能。poteto-mode 的「Playbooks」一节列出了每个剧本和它适用的场合。指南第 6 页 讲了怎么开 PR、盯 PR 和合入 PR。
pstack has no planning skill. Cursor's Plan Mode works alongside it. For work that spans phases or stacked PRs, asking /pstack:poteto-mode for a plan runs the Multi-phase plan playbook, which writes the plan and doesn't implement it. For a design question, the Prototype playbook or /pstack:architect settles it in code first.
pstack 没有做计划的技能。Cursor 的 Plan Mode 可以和它一起用。对于跨好几个阶段或一串叠起来的 PR 的活,让 /pstack:poteto-mode 出一份计划,就会运行 Multi-phase plan 剧本,它只写计划,不去实现。如果是设计上的问题,Prototype 剧本或 /pstack:architect 会先在代码里把它定下来。
Principles are one-rule skills that /pstack:poteto-mode reads and cites in its replies. The user rarely invokes one. They steer with the names instead, as in "apply prove it works. show me the real output." Typing /principle-<name> still loads one on demand. Guide page 8 lists them.
原则是只有一条规则的技能,/pstack:poteto-mode 会读它们,并在回复里引用。用户很少直接调用原则,而是用原则的名字来引导,比如「用上 prove it works,把真实输出给我看」。输入 /principle-<name> 仍然可以按需载入一个。指南第 8 页 列出了它们。
Fix a run that went wrong
修好一次跑偏的运行
| Symptom | Fix |
|---|---|
| The mode stopped applying after a few turns | It was started with Enter. Start it as a Custom Mode, or start each task with /pstack:poteto-mode. |
| A question got treated as the next step of the last task | Say "new task", or say the turn doesn't need the mode. |
| A new model choice had no effect | The rule from /pstack:setup-pstack applies to new chats. Start one. |
| Runs cost more than expected | See the cost paragraph under Get set up. |
| A skill didn't load on its own | Only /pstack:setup-pstack loads from the user's words. The others load when the user types them or when /pstack:poteto-mode runs them, and it doesn't run every skill. |
| Parallel agents overwrote each other | Give each agent its own worktree, or run them as cloud agents, which each get their own machine. |
| An overnight run moved but finished nothing | /loop needs a check that can pass or fail, not a duration. See guide page 7. |
| The reply claims success from a green build | Ask for the real command, flow, stored value, or profile. That's the prove-it-works principle. |
| 症状 | 解决办法 |
|---|---|
| 几轮之后模式就不起作用了 | 它是用 Enter 启动的。改成以 Custom Mode 启动,或者每个任务都用 /pstack:poteto-mode 开头。 |
| 一个问题被当成了上一个任务的下一步 | 说「new task」,或者说这一轮不需要这个模式。 |
| 换了模型却没效果 | /pstack:setup-pstack 写的规则对新对话生效。开一个新对话。 |
| 跑起来比预想的贵 | 见「完成设置」下面讲费用的那一段。 |
| 某个技能没有自己载入 | 只有 /pstack:setup-pstack 会因为用户说的话而自动载入。其他技能在用户输入它们、或者 /pstack:poteto-mode 运行它们时才载入,而它并不会运行每一个技能。 |
| 几个并行的 AI 互相覆盖了对方的改动 | 给每个 AI 各自的 worktree,或者把它们当云端帮手 AI 来跑,每个都有自己的机器。 |
| 一次通宵运行动了不少,却什么都没做完 | /loop 需要一个能判断通过或失败的检查,而不是一段时长。见 指南第 7 页。 |
| 回复看到构建变绿就说成功了 | 要真实的命令、流程、存下来的值或性能剖析结果。这就是 prove-it-works 原则。 |
For a run that drifts, references/prompting.md has one-line steers. Guide page 10 has more pitfalls and the recipes worth copying.
如果一次运行跑偏了,references/prompting.md 里有一句话就能纠偏的提示。指南第 10 页 有更多坑,以及值得照抄的做法。
Make pstack my own
把 pstack 改成自己的
/pstack:automate-medrafts a personal mode skill from the user's own history, to use alongside/pstack:poteto-mode./pstack:reflectafter a session turns its lessons into skill edits the user approves./pstack:poteto-mode write a skill for <workflow>runs the authoring playbook. The eval playbook tests a skill change blind.- Fix a misbehaving skill in its own PR, not inside the feature work where it went wrong.
/pstack:automate-me根据用户自己的历史记录,起草一个个人模式技能,和/pstack:poteto-mode搭配使用。- 一次会话之后用
/pstack:reflect,它会把这次的教训变成技能修改,由用户批准。 /pstack:poteto-mode write a skill for <workflow>会运行写技能的剧本。eval 剧本会对一次技能修改做盲测。- 某个技能表现不对,就单独开一个 PR 去修,不要在它出错的那个功能开发里顺手修。
Guide page 9 covers each of these.
指南第 9 页 对这几样都有讲。
Reply
回复
Lead with the answer. Give at most one example prompt in a code block, adapted from references/recipes.md when one fits, then the link to that file. Keep it short unless the user asked for the whole map.
先给答案。最多给一个示例提示词,放在代码块里;有合适的,就从 references/recipes.md 改编,然后附上那个文件的链接。保持简短,除非用户要的是整张地图。
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