Back to Details

poteto-help

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Poteto help

Poteto 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.
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.
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.
回答用户关于 pstack 的问题，向他们提供可以直接发送的 prompt，并附上答案来源文件的链接。对于帮助类问题，不要直接开始执行工作。用户问的是“怎么做”，而运行一次 pstack 会消耗真实 token，因此应让用户自行发送 prompt。
要求执行工作的消息，例如“use pstack to fix this bug”，不属于帮助问题。读取 
poteto-mode
，按照其中的方式完成工作，并提及一次：使用 Custom Mode 可以让该模式持续生效。
本文件将问题映射到包含答案的 skill 和指南页面。详细内容由这些文件负责。在引用之前先读取路由目标文件；如果其内容与本映射不一致，以目标文件为准。这里的链接指向已安装的 plugin，用户可能无法打开，因此应向用户提供该文件的公开副本：
https://github.com/cursor/plugins/blob/main/pstack/
后接其路径。

Find out what they need

确定用户需求

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:
  • Get set up
  • Start a task with 
    /poteto-mode
  • Pick a skill for a situation
  • Fix a run that went wrong
  • Make pstack my own
Check the state that changes the answer, and mention it only when it does:
  • No 
    ~/.cursor/rules/pstack-models.mdc
    means 
    /setup-pstack
    hasn'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 
    /create-verification-skill
    when the question is about proving a change works.
根据消息和对话推断需求。如果用户明确指出具体场景，例如“which skill reviews a PR?”，直接进入相应章节。如果仍不清楚，先提出一个多项选择题，包含以下选项，然后只回答用户选择的章节：
  • 完成设置
  • 使用 
    /poteto-mode
    开始任务
  • 为特定场景选择 skill
  • 修复运行异常
  • 定制 pstack
检查会改变答案的状态，仅在确实影响答案时提及：
  • 不存在 
    ~/.cursor/rules/pstack-models.mdc
    ，意味着该用户尚未运行 
    /setup-pstack
    ，因此每个 role 都会使用其默认 model。
  • 项目中不存在 
    verify-*
    skill 或其他 app harness，意味着 agents 没有以脚本方式驱动 app 的方法。当问题涉及证明变更是否有效时，提及 
    /create-verification-skill
    。

Get set up

完成设置

  1. Install with 
    /add-plugin pstack
    in chat, or from Customize in the sidebar.
  2. Run 
    /setup-pstack
    . It asks for a reasoning budget, maps a model to each role, and writes a rule. The rule applies to new chats.
  3. Start a real task with 
    /poteto-mode
    , a goal, and a check that can pass or fail.
Installing changes nothing until the user invokes a skill. Only 
/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
.
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 
/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 
/poteto-mode
for work that needs rigor.
pstack is built for Cursor. Its skills use the Agent Skills format, so other tools can read them. But most workflow skills, including 
/poteto-mode
, 
/how
, 
/why
, and 
/teach
, spawn Cursor subagents with per-role models, and Custom Modes and 
/loop
are Cursor features, so those parts may not work there.
  1. 在聊天中输入 
    /add-plugin pstack
    ，或从侧边栏的 Customize 中安装。
  2. 运行 
    /setup-pstack
    。它会询问 reasoning budget，为每个 role 映射 model，并写入一条 rule。该 rule 应用于新的聊天。
  3. 使用 
    /poteto-mode
    、一个 goal 和一项可通过或失败的 check，开始一项真实任务。
安装本身不会产生任何变化，只有用户调用某个 skill 后才会生效。只有 
/setup-pstack
会根据用户输入自动加载。README 和指南第 1 页包含详细信息。可以按照 
references/prompting.md
 与用户一起措辞他们的第一个 prompt。
如果用户担心成本，说明 token 花在哪里以及如何减少消耗。pstack 会在 subagents 和 review panels 上消耗额外 token。重新运行 
/setup-pstack
并选择更小的 budget 或更便宜的 models。设为 
auto
或 
inherit-parent
的 role 会使用聊天所用的 model；当聊天运行于 Auto 或更便宜的 model 上时，这可以节省 token。review panel 列表越短，运行的 subagents 越少，每个条目对应一个 subagent。把 
/poteto-mode
留给需要严谨执行的工作。
pstack 是为 Cursor 构建的。它的 skills 使用 Agent Skills 格式，因此其他工具也能读取。不过，大多数工作流 skills，包括 
/poteto-mode
、
/how
、
/why
和 
/teach
，都会生成 Cursor subagents，并为每个 role 指定 model；Custom Modes 和 
/loop
是 Cursor 功能，因此这些部分在其他工具中可能无法工作。

Start a task with 
/poteto-mode

使用 
/poteto-mode
开始任务

/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.
Whether 
/poteto-mode
stays on depends on how the user starts it:
  • Enter on 
    /poteto-mode
    attaches 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 
    /poteto-mode
    .
Link Cursor's skills docs when this comes up. Mid-chat, "new task" makes the mode match a fresh playbook. 
/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"
.
/poteto-mode
会把任务匹配到某个 playbook，将该 playbook 的步骤复制到 todo list，并在各步骤需要时运行其他 skills。被跳过的步骤会保留在列表中，并标记为 
skip: <reason>
。好的 prompt 应说明 goal 以及如何判断任务已完成。它不需要列出 skills，因为手写序列往往会遗漏或重排 playbook 会保留的步骤。帮助用户措辞 prompt 前，先读取 
references/prompting.md
。指南第 2 页提供了示例。
/poteto-mode
是否持续生效取决于启动方式：
  • 在 
    /poteto-mode
    后按 Enter，会将 skill 附着到一条消息上；随着聊天推进，它会逐渐失效。
  • 在 Mac 上按 Option+Enter、在 Windows 上按 Alt+Enter，或者从 skill 入口选择 Use as Mode，会将其创建为 Custom Mode。它会在每一轮中保留在上下文中，直到用户退出该模式，并且不会用于闲聊轮次。
  • Cursor 的文档列出了 Agents Window 和 CLI 中的 Custom Modes。其他情况下，每项新任务都用 
    /poteto-mode
    开始。
涉及此内容时，附上 Cursor 的 skills 文档链接。在聊天中说“new task”会让模式匹配一个新的 playbook。
/poteto-mode
已经使用 
poteto-agent
来启动其 playbook 步骤生成的 subagents。若要让你自己的 subagent 保持相同风格，请使用 
subagent_type: "poteto-agent"
启动。

Pick a skill

选择 skill

The default answer is 
/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.
The user wants toSkill
Do any non-trivial task with rigor
/poteto-mode
Know how code works now, or where new code should live
/how
Know why code is shaped this way, or where a number came from
/why
Understand a change or subsystem, explained plainly
/teach
Catch up on their own recent work on a topic
/recall
Know what a small diff could break outside itself
/blast-radius
Settle types and module shape before code that crosses a function boundary
/architect
Get several attempts at one brief, merged into the best one
/arena
Run parallel checks over slices, or race workers, as cloud agents
/swarm
Have several models review a diff and try to break it
/interrogate
Fix a bug test-first when a cheap local test exists
/tdd
Apply TypeScript rules to 
.ts
or 
.tsx
work
/typescript-best-practices
Strip comments before review, using a reviewer that didn't write them
/no-comments
Clean AI tells out of prose
/unslop
Write docs, an RFC, a README, a PR description, or a commit message to a standard
/technical-writing
Hear the last reply again in plain words
/bro
Give agents a scripted way to drive the app and prove behavior
/create-verification-skill
Bring a verification skill and its feature map back in line with the app
/maintain-verification-skill
Vet a performance number before reporting or acting on it
/benchmark-checklist
Run a large or cross-cutting change, or one to review after stepping away
/figure-it-out
Keep a decision log during a run, and review it afterward
/show-me-your-work
Pick a model for each role and a reasoning budget
/setup-pstack
Turn their own working habits into a personal mode skill
/automate-me
Turn what a finished task taught into skill edits
/reflect
Stop agents from repeating the same mistakes in this repo
/correct
Build a page whose buttons wake a Grok Bot over a webhook
/make-bot-ui
Find their way around 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.
Close calls:
  • /how
    explains what the code does. 
    /why
    explains the reasons. 
    /teach
    runs one or both and explains the result plainly.
  • /arena
    gives every worker the same brief and merges the best parts. 
    /swarm
    splits work into slices or a race and returns one report.
  • /architect
    implements right after it settles the design. Add "with checkpoint" to review the design before it writes code.
  • /interrogate
    reviews the diff. 
    /blast-radius
    looks for breakage outside the diff and proves the one fact that makes the change safe.
  • /recall
    rebuilds context across recent chats. Resuming one specific chat or branch is the Session pickup playbook.
  • /figure-it-out
    designs 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.
Not in pstack:
  • /deslop
    , 
    control-cli
    , and 
    control-ui
    ship in the 
    cursor-team-kit
    plugin.
  • /loop
    and 
    /create-skill
    are Cursor built-ins.
  • pstack has no 
    /orchestrate
    skill. Orchestrate is a 
    /poteto-mode
    playbook. If the slash menu shows 
    /orchestrate
    , another plugin provides it.
默认建议是 
/poteto-mode
，它会在步骤需要时运行大多数其他 skills。当用户希望对某方面进行比 playbook 更多或更少的控制时，直接指定 skill。推荐前先读取该 skill，并给出一个示例 prompt。
用户需求Skill
严谨完成任何非简单任务
/poteto-mode
了解当前代码如何工作，或新代码应放在哪里
/how
了解代码为何采用当前设计，或某个数字从何而来
/why
以直白方式理解一项变更或子系统
/teach
补齐自己近期在某主题上的工作上下文
/recall
了解一个小 diff 可能对范围之外造成什么破坏
/blast-radius
在编写跨越函数边界的代码前，确定类型和模块结构
/architect
针对同一 brief 获得多个方案，并合并出最佳版本
/arena
以 cloud agents 并行检查不同切片，或让 workers 竞速
/swarm
让多个 models 审查 diff 并尝试找出问题
/interrogate
在存在廉价本地测试时，以测试优先方式修复 bug
/tdd
对 
.ts
或 
.tsx
工作应用 TypeScript 规则
/typescript-best-practices
审查前移除注释，并使用未编写这些注释的 reviewer
/no-comments
清除 prose 中的 AI 痕迹
/unslop
按标准编写 docs、RFC、README、PR description 或 commit message
/technical-writing
用直白语言再听一遍上一条回复
/bro
为 agents 提供以脚本方式驱动 app 并证明行为的方法
/create-verification-skill
让 verification skill 及其 feature map 与 app 重新保持一致
/maintain-verification-skill
在报告或依据性能数字采取行动前审核该数字
/benchmark-checklist
运行大型或跨模块变更，或在离开后回来审查它
/figure-it-out
在一次运行期间保留 decision log，并在之后进行审查
/show-me-your-work
为每个 role 选择 model 并设置 reasoning budget
/setup-pstack
将用户自己的工作习惯转化为个人 mode skill
/automate-me
将已完成任务带来的经验转化为 skill 修改
/reflect
防止 agents 在此 repo 中重复犯同样的错误
/correct
构建一个页面，其按钮可通过 webhook 唤醒 Grok Bot
/make-bot-ui
了解如何操作 pstack
/poteto-help
如果与本文件相邻的某个 skill 目录未出现在表中，读取其 frontmatter，并根据其 description 进行路由。
principle-*
目录在下方 principles 部分中介绍。

Playbooks and principles

容易混淆的选择

Playbooks are step lists inside 
/poteto-mode
, not skills, so they have no slash command. Inside 
/poteto-mode
, describing the task picks one, and these phrases name one directly:
  • "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. "stack them, don't ship" runs Autopilot-stack.
  • "run the eval playbook" runs Eval.
Without 
/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.
pstack has no planning skill. Cursor's Plan Mode works alongside it. For work that spans phases or stacked PRs, asking 
/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 
/architect
settles it in code first.
Principles are one-rule skills that 
/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.
  • /how
    解释代码的作用，
    /why
    解释设计原因，
    /teach
    运行其中一项或两项，并用直白方式解释结果。
  • /arena
    给每个 worker 相同的 brief，并合并最佳部分；
    /swarm
    将工作拆分为不同切片或竞速任务，并返回一份报告。
  • /architect
    确定设计后会立即实施。添加“with checkpoint”可以在编写代码前审查设计。
  • /interrogate
    审查 diff；
    /blast-radius
    查找 diff 范围之外的破坏风险，并证明使变更安全的关键事实。
  • /recall
    重建近期聊天的上下文。恢复某个特定聊天或分支应使用 Session pickup playbook。
  • /figure-it-out
    为一项严谨运行进行设计。Orchestrate playbook 运行一个可能持续数天并涉及多个 PR 的程序。Autonomous run playbook 驱动一项任务直至达到完成条件。
以下内容不属于 pstack：
  • /deslop
    、
    control-cli
    和 
    control-ui
    包含在 
    cursor-team-kit
    plugin 中。
  • /loop
    和 
    /create-skill
    是 Cursor 内置功能。
  • pstack 没有 
    /orchestrate
    skill。Orchestrate 是一个 
    /poteto-mode
    playbook。如果 slash 菜单显示 
    /orchestrate
    ，则说明另一个 plugin 提供了该功能。

Fix a run that went wrong

Playbooks 和 principles

SymptomFix
The mode stopped applying after a few turnsIt was started with Enter. Start it as a Custom Mode, or start each task with 
/poteto-mode
.
A question got treated as the next step of the last taskSay "new task", or say the turn doesn't need the mode.
A new model choice had no effectThe rule from 
/setup-pstack
applies to new chats. Start one.
Runs cost more than expectedSee the cost paragraph under Get set up.
A skill didn't load on its ownOnly 
/setup-pstack
loads from the user's words. The others load when the user types them or when 
/poteto-mode
runs them, and it doesn't run every skill.
Parallel agents overwrote each otherGive 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 buildAsk for the real command, flow, stored value, or profile. That's the prove-it-works principle.
For a run that drifts, 
references/prompting.md
 has one-line steers. Guide page 10 has more pitfalls and the recipes worth copying.
Playbooks 是 
/poteto-mode
内部的步骤列表，不是 skills，因此没有 slash command。在 
/poteto-mode
中，描述任务即可选定一个；以下短语可以直接指定：
  • “babysit this pr”或“check on pr 123”会运行 Babysit。它会推动 PR 达到可合并状态并就此停止。除非用户要求 merge、land 或 ship，否则它不会合并。
  • “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。“stack them, don't ship”会运行 Autopilot-stack。
  • “run the eval playbook”会运行 Eval。
不使用 
/poteto-mode
时，“babysit this pr”之类的短语可能会启动 Cursor 自带的同名 skill。
poteto-mode
 的 Playbooks 部分列出了所有 playbook 及其适用场景。指南第 6 页介绍了发起、跟进和落地 PR 的相关内容。
pstack 没有 planning skill。Cursor 的 Plan Mode 可与之配合使用。对于跨多个阶段或 stacked PRs 的工作，要求 
/poteto-mode
制定计划会运行 Multi-phase plan playbook，它只编写计划，不实施计划。对于设计问题，Prototype playbook 或 
/architect
会先通过代码确定方案。
Principles 是单规则 skills，
/poteto-mode
会读取并在回复中引用。用户很少直接调用 principle，通常通过名称来引导，例如“apply prove it works. show me the real output.”。输入 
/principle-<name>
仍可按需加载一个 principle。指南第 8 页列出了所有 principles。

Make pstack my own

修复运行异常

  • /automate-me
     drafts a personal mode skill from the user's own history, to use alongside 
    /poteto-mode
    .
  • /reflect
     after a session turns its lessons into skill edits the user approves.
  • /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.
Guide page 9 covers each of these.
症状修复方法
该模式在几轮后不再生效它是通过 Enter 启动的。改为以 Custom Mode 启动，或每项任务都用 
/poteto-mode
开始。
某个问题被当成上一任务的下一步说“new task”，或说明这一轮不需要该模式。
新选的 model 没有产生影响
/setup-pstack
中写入的 rule 仅应用于新聊天。请开始一个新聊天。
运行成本超出预期参见“完成设置”中的成本说明。
某个 skill 没有自动加载只有 
/setup-pstack
会根据用户输入加载。其他 skills 只会在用户手动输入时加载，或由 
/poteto-mode
运行；它不会运行每个 skill。
并行 agents 相互覆盖为每个 agent 分配独立的 worktree，或将它们作为 cloud agents 运行，每个 agent 都会获得独立机器。
通宵运行虽有进展却未完成任何结果
/loop
需要一项可通过或失败的 check，而不是运行时长。参见指南第 7 页。
回复仅凭构建通过就声称成功要求提供真实 command、flow、存储值或 profile。这正是 prove-it-works principle。
对于运行偏离目标的情况，
references/prompting.md
提供了一行式引导语。指南第 10 页介绍了更多常见陷阱和值得复用的 recipes。

Reply

定制 pstack

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.
  • /automate-me
     根据用户自己的历史记录起草个人 mode skill，以便与 
    /poteto-mode
    配合使用。
  • /reflect
     在一次 session 结束后，将其中的经验转化为用户确认的 skill 修改。
  • /poteto-mode write a skill for <workflow>
    会运行 authoring playbook。eval playbook 会以盲测方式测试 skill 修改。
  • 在独立 PR 中修复行为异常的 skill，不要在发生问题的 feature 工作内部修复。
指南第 9 页介绍了上述各项内容。
—

回复

—
先直接给出答案。最多提供一个 code block 中的示例 prompt；如果有合适的示例，可基于 
references/recipes.md
 改写，然后附上该文件的链接。除非用户要求查看完整映射，否则回复应保持简短。