AGENT SKILL

poteto-help

Guides users through pstack setup, /skill:poteto-mode, and picking the skill, playbook, or principle for a task. Use for help about pstack.

License 许可
MIT
最近更新
2026-11-03
Stars
★ 35
Forks
0

01 前言 Front Matter

name
poteto-help
license
MIT
description
Guides users through pstack setup, /skill:poteto-mode, and picking the skill, playbook, or principle for a task. Use for help about pstack.
disable-model-invocation
true

02 资源文件 2

03 SKILL.md 正文

Poteto help

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 /poteto on keeps it on.

This file maps questions to the skills and reference 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 package, which the user may not be able to open, so give the user the file's path and installed location as well as the link.

Find out what they need

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 /skill: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 configured role in ~/.pi/agent/pstack.json 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.
  • No formal verification skill in the project means no property is checked past what tests reach. Mention /create-formal-verification-skill when 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 /maintain-formal-verification-skill if the question touches that code.

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:

  • Now: give them /setup-pstack to type, and answer their question too.
  • Later: answer their question, and add one line saying every role keeps its default model until they run /setup-pstack.

Get set up

  1. Install the package with Pi's package mechanism, from the project or the user's Pi configuration.
  2. Run /setup-pstack. It asks for a reasoning budget, maps an available model and thinking level to each role, and writes pstack.json. The configuration applies to new sessions.
  3. Start a real task with /skill: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 Pi adapter and migration plan have the details. Offer to word their first prompt with them, per 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 inherit or unset runs on the chat's model, which saves tokens when the chat runs on a cheaper model. A shorter review panel runs fewer subagents, one for each seat. Save /skill:poteto-mode for work that needs rigor.

pstack began on Cursor. Its skills use the Agent Skills format, so other tools can read them. This Pi package replaces Cursor subagents with pi-subagents, Custom Modes with /poteto on and /poteto off, and Cursor transcripts with Pi sessions, so parts written against Cursor features may not behave the same way.

Start a task with /skill:poteto-mode

/skill: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 prompting.md before you help word one.

Enter on /skill:poteto-mode attaches the skill to one message. Explicit skill invocation does not change persistent mode.

  • /poteto on enables persistent mode for later turns until /poteto off.
  • /poteto status, or /poteto without arguments, reports the current state.
  • /poteto-mode remains a deprecated alias throughout 0.3.x and 0.4.x and will be removed in 0.5.0. Every invocation warns first. Pi 1.4 has no public command API to hide it from completion, so it remains visible with a [已弃用] description.

Link the Pi skills docs when this comes up. Mid-chat, "new task" makes the mode match a fresh playbook. /skill: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 agent: "pstack.poteto-agent".

Pick a skill

The default answer is /skill: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 to Skill
Do any non-trivial task with rigor /skill:poteto-mode
Check that the agent understood their goal and the problem before it starts /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 /sharpen
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
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 /ketchup
Catch up like /ketchup, in a short subtitled video of slides, with the waiting calls as text under it /ketchup-video
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, in isolated worktrees /swarm
Have different 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
Formally verify a race, invariant, or other property that tests rarely reach /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 /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 /statechart
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
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. /ketchup covers only this chat since the user's last message. 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 shipped as skills in this package:

  • /deslop, control-cli, and control-ui come from Cursor's cursor-team-kit. Here /unslop and /no-comments cover the local cleanup, and app verification uses the operator's available browser or CLI driver.
  • /loop and /setup-pstack are Pi extension commands. /create-skill is not shipped; use the manual authoring procedure in the Pi adapter.
  • pstack has no /orchestrate skill. Orchestrate is a /skill:poteto-mode playbook. If the slash menu shows /orchestrate, another plugin provides it.

Playbooks and principles

Playbooks are step lists inside /skill:poteto-mode, not skills, so they have no slash command. Inside /skill: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. "autopilot, don't merge" runs Autopilot-stack.
  • "run the eval playbook" runs Eval.

Outside /skill:poteto-mode, a phrase such as "babysit this pr" does not start a hidden skill here; read the playbook directly or turn the mode on. The Playbooks section of poteto-mode lists every playbook and when it applies.

pstack has no planning skill. The host's plan mode works alongside it. For work that spans phases or stacked PRs, asking /skill: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 /skill: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.

Fix a run that went wrong

Symptom Fix
The mode stopped applying after a few turns It was started with /skill:poteto-mode. Run /poteto on, or start each task with /skill: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 config from /setup-pstack applies to new sessions and must match an available model. Inspect the actual dispatched model. Start a new session.
Runs cost more than expected See the cost paragraph under Get set up.
A skill didn't load on its own Only /setup-pstack loads from the user's words. The others load when the user types them or when /skill:poteto-mode runs them, and it doesn't run every skill.
Parallel agents overwrote each other Give each agent its own worktree and keep one writer per worktree.
An overnight run moved but finished nothing /loop needs a check that can pass or fail, not a duration. Give it a bounded budget and an exit-0 predicate.
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.

For a run that drifts, prompting.md has one-line steers. The Pi adapter has more pitfalls and the recipes worth copying.

Make pstack my own

  • /automate-me drafts a personal mode skill from the user's own history, to use alongside /skill:poteto-mode.
  • reflect after a session turns its lessons into skill edits the user approves.
  • /skill: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.

Reply

Lead with the answer. Give at most one example prompt in a code block, adapted from recipes.md when one fits, then the link to that file. Keep it short unless the user asked for the whole map. Help does not grant permission to delegate, install, send messages, commit, push, or merge.

04 同仓库更多 Skills