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 pstack-poteto-mode and do the work under it.
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.
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
/pstack-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
~/.zcode/pstack/models.md means /pstack-setup-pstack hasn't run for this user, so every role runs on the session 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-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
/pstack-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 /pstack-maintain-formal-verification-skill if the question touches that code.
When the models file 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
/pstack-setup-pstack to type, and answer their question too.
- Later: answer their question, and add one line saying every role runs on the session model until they run
/pstack-setup-pstack.
Get set up
- Install with
npx skills add ChHsiching/pstack-zcode.
- Run
/pstack-setup-pstack. It asks for a reasoning budget, maps a model to each role, and writes a data file that skills read at spawn time. Preset agents it writes apply 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.
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.
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 left at inherit-parent runs on the session model, which saves tokens when the session runs on a cheaper model. A shorter panel list runs fewer subagents, one for each entry. Save /pstack-poteto-mode for work that needs rigor.
Start a task with /pstack-poteto-mode
Other tools can read the skills, because they use the Agent Skills format. But most workflow skills, including /pstack-poteto-mode, /pstack-how, and /pstack-teach, spawn subagents, some with per-role models, and a persistent mode and the long-run recipe are adapted for ZCode.
Whether /pstack-poteto-mode stays on depends on how the user starts it:
- Typing
/pstack-poteto-mode attaches the skill to one message. It fades as the chat moves on.
Start each new task with /pstack-poteto-mode.
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 the poteto-agent subagent.
Pick a skill
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.
| 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 silent 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 model, with each bug drawn as a numbered path, turn an agreed chart into a TLA+ skeleton, or audit the code against its TLA+ spec |
/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 |
| ======= |
|
| 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 silent 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 |
d2a7dcc3d00d9ae32e91a92071f2d551ced88d6d
=======
| 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 |
424f2f6b0e1c805d1d227dbc7a59dcb290c89f8a
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:
/pstack-how explains what the code does. /pstack-why explains the reasons. /pstack-teach runs one or both and explains the result plainly.
/pstack-arena gives every worker the same brief and merges the best parts. /pstack-swarm splits work into slices or a race and returns one report.
/pstack-architect implements right after it settles the design. Add "with checkpoint" to review the design before it writes code.
/pstack-interrogate reviews the diff. /pstack-blast-radius looks for breakage outside the diff and proves the one fact that makes the change safe.
/pstack-recall rebuilds context across recent chats. /pstack-ketchup covers only this chat since the user's last message. Resuming one specific chat or branch is the Session pickup playbook.
/pstack-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:
- pstack has no
/orchestrate skill. Orchestrate is a /pstack-poteto-mode playbook. If the slash menu shows /orchestrate, another plugin provides it.
Playbooks and principles
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:
- "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.
The Playbooks section of pstack-poteto-mode lists every playbook and when it applies. Guide page 6 covers opening, babysitting, and landing a PR.
pstack has no planning skill. 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.
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 /pstack-principle-<name> still loads one on demand. Guide page 8 lists them.
Fix a run that went wrong
| Symptom |
Fix |
| The mode stopped applying after a few turns |
It fades as the chat moves on. 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 preset agents from /pstack-setup-pstack apply 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. |
| An overnight run moved but finished nothing |
The run's drive 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. |
For a run that drifts, references/prompting.md has one-line steers. Guide page 10 has more pitfalls and the recipes worth copying.
Make pstack my own
/pstack-automate-me drafts a personal mode skill from the user's own history, to use alongside /pstack-poteto-mode.
/pstack-reflect after 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.
Guide page 9 covers each of these.
Reply
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.
1---2name: pstack-poteto-help3description: Guides users through pstack setup, /pstack-poteto-mode, and picking the skill, playbook, or principle for a task. Type /pstack-poteto-help with a question.4disable-model-invocation: true5metadata:6 source: https://skillmd.com/skills/chhsiching/pstack-poteto-help7---89# Poteto help1011Answer 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.1213A message that asks for work, such as "use pstack to fix this bug", is not a help question. Read [`pstack-poteto-mode`](../poteto-mode/SKILL.md) and do the work under it.1415This 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.1617## Find out what they need1819Infer 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:2021- Get set up22- Start a task with `/pstack-poteto-mode`23- Pick a skill for a situation24- Fix a run that went wrong25- Make pstack my own2627Check the state that changes the answer, and mention it only when it does:2829- No `~/.zcode/pstack/models.md` means `/pstack-setup-pstack` hasn't run for this user, so every role runs on the session model.30- No `verify-*` skill or other app harness in the project means agents have no scripted way to drive the app. Mention `/pstack-create-verification-skill` when the question is about proving a change works.31- No formal verification skill in the project means no property is checked past what tests reach. Mention `/pstack-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 `/pstack-maintain-formal-verification-skill` if the question touches that code.3233When the models file 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:3435- Now: give them `/pstack-setup-pstack` to type, and answer their question too.36- Later: answer their question, and add one line saying every role runs on the session model until they run `/pstack-setup-pstack`.3738## Get set up39401. Install with `npx skills add ChHsiching/pstack-zcode`.412. Run [`/pstack-setup-pstack`](../setup-pstack/SKILL.md). It asks for a reasoning budget, maps a model to each role, and writes a data file that skills read at spawn time. Preset agents it writes apply 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.423. Start a real task with `/pstack-poteto-mode`, a goal, and a check that can pass or fail.4344Installing changes nothing until the user invokes a skill. Only `/pstack-setup-pstack` loads from the user's words. The [README](../../README.md) and [guide page 1](../../docs/guide/01-setup.md) have the details. Offer to word their first prompt with them, per [`references/prompting.md`](references/prompting.md).4546If 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 left at `inherit-parent` runs on the session model, which saves tokens when the session runs on a cheaper model. A shorter panel list runs fewer subagents, one for each entry. Save `/pstack-poteto-mode` for work that needs rigor.4748## Start a task with `/pstack-poteto-mode`4950Other tools can read the skills, because they use the Agent Skills format. But most workflow skills, including `/pstack-poteto-mode`, `/pstack-how`, and `/pstack-teach`, spawn subagents, some with per-role models, and a persistent mode and the long-run recipe are adapted for ZCode.5152Whether `/pstack-poteto-mode` stays on depends on how the user starts it:5354- Typing `/pstack-poteto-mode` attaches the skill to one message. It fades as the chat moves on.5556Start each new task with `/pstack-poteto-mode`.5758Mid-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 the `poteto-agent` subagent.5960## Pick a skill6162The 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.6364| The user wants to | Skill |65|---|---|66| Do any non-trivial task with rigor | [`/pstack-poteto-mode`](../poteto-mode/SKILL.md) |67| Check that the agent understood their goal and the problem before it starts | [`/pstack-in-your-own-words`](../in-your-own-words/SKILL.md) |68| 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`](../sharpen/SKILL.md) |69| Know how code works now, or where new code should live | [`/pstack-how`](../how/SKILL.md) |70| Know why code is shaped this way, or where a number came from | [`/pstack-why`](../why/SKILL.md) |71| Understand a change or subsystem, explained plainly | [`/pstack-teach`](../teach/SKILL.md) |72| Catch up on their own recent work on a topic | [`/pstack-recall`](../recall/SKILL.md) |73| 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`](../ketchup/SKILL.md) |74| Catch up like `/pstack-ketchup`, in a short silent video of slides, with the waiting calls as text under it | [`/pstack-ketchup-video`](../ketchup-video/SKILL.md) |75| Know what a small diff could break outside itself | [`/pstack-blast-radius`](../blast-radius/SKILL.md) |76| Settle types and module shape before code that crosses a function boundary | [`/pstack-architect`](../architect/SKILL.md) |77| Get several attempts at one brief, merged into the best one | [`/pstack-arena`](../arena/SKILL.md) |78| Run parallel checks over slices, or race workers, as cloud agents | [`/pstack-swarm`](../swarm/SKILL.md) |79| Have different models review a diff and try to break it | [`/pstack-interrogate`](../interrogate/SKILL.md) |80| Fix a bug test-first when a cheap local test exists | [`/pstack-tdd`](../tdd/SKILL.md) |81| Apply TypeScript rules to `.ts` or `.tsx` work | [`/pstack-typescript-best-practices`](../typescript-best-practices/SKILL.md) |82| Strip comments before review, using a reviewer that didn't write them | [`/pstack-no-comments`](../no-comments/SKILL.md) |83| Clean AI tells out of prose | [`/pstack-unslop`](../unslop/SKILL.md) |84| Write docs, an RFC, a README, a PR description, or a commit message to a standard | [`/pstack-technical-writing`](../technical-writing/SKILL.md) |85| Hear the last reply again in plain words | [`/pstack-bro`](../bro/SKILL.md) |86| Give agents a scripted way to drive the app and prove behavior | [`/pstack-create-verification-skill`](../create-verification-skill/SKILL.md) |87| Bring a verification skill and its feature map back in line with the app | [`/pstack-maintain-verification-skill`](../maintain-verification-skill/SKILL.md) |88| Formally verify a race, invariant, or other property that tests rarely reach | [`/pstack-create-formal-verification-skill`](../create-formal-verification-skill/SKILL.md) |89| 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`](../maintain-formal-verification-skill/SKILL.md) |90| Show a PM or designer what the user sees as a chart checked by a model, with each bug drawn as a numbered path, turn an agreed chart into a TLA+ skeleton, or audit the code against its TLA+ spec | [`/pstack-statechart`](../statechart/SKILL.md) |91| Vet a performance number before reporting or acting on it | [`/pstack-benchmark-checklist`](../benchmark-checklist/SKILL.md) |92| Run a large or cross-cutting change, or one to review after stepping away | [`/pstack-figure-it-out`](../figure-it-out/SKILL.md) |93| Keep a decision log during a run, and review it afterward | [`/pstack-show-me-your-work`](../show-me-your-work/SKILL.md) |94| Pick a model for each role and a reasoning budget | [`/pstack-setup-pstack`](../setup-pstack/SKILL.md) |95| Turn their own working habits into a personal mode skill | [`/pstack-automate-me`](../automate-me/SKILL.md) |96| Turn what a finished task taught into skill edits | [`/pstack-reflect`](../reflect/SKILL.md) |97| Stop agents from repeating the same mistakes in this repo | [`/pstack-correct`](../correct/SKILL.md) |98| Build a page whose buttons wake a Grok Bot over a webhook | [`/pstack-make-bot-ui`](../make-bot-ui/SKILL.md) |99| Find their way around pstack | `/pstack-poteto-help` |100=======101| Do any non-trivial task with rigor | [`/pstack-poteto-mode`](../poteto-mode/SKILL.md) |102| Check that the agent understood their goal and the problem before it starts | [`/pstack-in-your-own-words`](../in-your-own-words/SKILL.md) |103| 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`](../sharpen/SKILL.md) |104| Know how code works now, or where new code should live | [`/pstack-how`](../how/SKILL.md) |105| Know why code is shaped this way, or where a number came from | [`/pstack-why`](../why/SKILL.md) |106| Understand a change or subsystem, explained plainly | [`/pstack-teach`](../teach/SKILL.md) |107| Catch up on their own recent work on a topic | [`/pstack-recall`](../recall/SKILL.md) |108| 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`](../ketchup/SKILL.md) |109| Catch up like `/pstack-ketchup`, in a short silent video of slides, with the waiting calls as text under it | [`/pstack-ketchup-video`](../ketchup-video/SKILL.md) |110| Know what a small diff could break outside itself | [`/pstack-blast-radius`](../blast-radius/SKILL.md) |111| Settle types and module shape before code that crosses a function boundary | [`/pstack-architect`](../architect/SKILL.md) |112| Get several attempts at one brief, merged into the best one | [`/pstack-arena`](../arena/SKILL.md) |113| Run parallel checks over slices, or race workers, as cloud agents | [`/pstack-swarm`](../swarm/SKILL.md) |114| Have different models review a diff and try to break it | [`/pstack-interrogate`](../interrogate/SKILL.md) |115| Fix a bug test-first when a cheap local test exists | [`/pstack-tdd`](../tdd/SKILL.md) |116| Apply TypeScript rules to `.ts` or `.tsx` work | [`/pstack-typescript-best-practices`](../typescript-best-practices/SKILL.md) |117| Strip comments before review, using a reviewer that didn't write them | [`/pstack-no-comments`](../no-comments/SKILL.md) |118| Clean AI tells out of prose | [`/pstack-unslop`](../unslop/SKILL.md) |119| Write docs, an RFC, a README, a PR description, or a commit message to a standard | [`/pstack-technical-writing`](../technical-writing/SKILL.md) |120| Hear the last reply again in plain words | [`/pstack-bro`](../bro/SKILL.md) |121| Give agents a scripted way to drive the app and prove behavior | [`/pstack-create-verification-skill`](../create-verification-skill/SKILL.md) |122| Bring a verification skill and its feature map back in line with the app | [`/pstack-maintain-verification-skill`](../maintain-verification-skill/SKILL.md) |123| Formally verify a race, invariant, or other property that tests rarely reach | [`/pstack-create-formal-verification-skill`](../create-formal-verification-skill/SKILL.md) |124| 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`](../maintain-formal-verification-skill/SKILL.md) |125| 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`](../statechart/SKILL.md) |126| Vet a performance number before reporting or acting on it | [`/pstack-benchmark-checklist`](../benchmark-checklist/SKILL.md) |127| Run a large or cross-cutting change, or one to review after stepping away | [`/pstack-figure-it-out`](../figure-it-out/SKILL.md) |128| Keep a decision log during a run, and review it afterward | [`/pstack-show-me-your-work`](../show-me-your-work/SKILL.md) |129| Pick a model for each role and a reasoning budget | [`/pstack-setup-pstack`](../setup-pstack/SKILL.md) |130| Turn their own working habits into a personal mode skill | [`/pstack-automate-me`](../automate-me/SKILL.md) |131| Turn what a finished task taught into skill edits | [`/pstack-reflect`](../reflect/SKILL.md) |132| Stop agents from repeating the same mistakes in this repo | [`/pstack-correct`](../correct/SKILL.md) |133| Build a page whose buttons wake a Grok Bot over a webhook | [`/pstack-make-bot-ui`](../make-bot-ui/SKILL.md) |134| Find their way around pstack | `/pstack-poteto-help` |135>>>>>>> d2a7dcc3d00d9ae32e91a92071f2d551ced88d6d136=======137| Do any non-trivial task with rigor | [`/pstack-poteto-mode`](../poteto-mode/SKILL.md) |138| Check that the agent understood their goal and the problem before it starts | [`/pstack-in-your-own-words`](../in-your-own-words/SKILL.md) |139| 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`](../sharpen/SKILL.md) |140| Know how code works now, or where new code should live | [`/pstack-how`](../how/SKILL.md) |141| Know why code is shaped this way, or where a number came from | [`/pstack-why`](../why/SKILL.md) |142| Understand a change or subsystem, explained plainly | [`/pstack-teach`](../teach/SKILL.md) |143| Catch up on their own recent work on a topic | [`/pstack-recall`](../recall/SKILL.md) |144| 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`](../ketchup/SKILL.md) |145| Catch up like `/pstack-ketchup`, in a short subtitled video of slides, with the waiting calls as text under it | [`/pstack-ketchup-video`](../ketchup-video/SKILL.md) |146| Know what a small diff could break outside itself | [`/pstack-blast-radius`](../blast-radius/SKILL.md) |147| Settle types and module shape before code that crosses a function boundary | [`/pstack-architect`](../architect/SKILL.md) |148| Get several attempts at one brief, merged into the best one | [`/pstack-arena`](../arena/SKILL.md) |149| Run parallel checks over slices, or race workers, as cloud agents | [`/pstack-swarm`](../swarm/SKILL.md) |150| Have different models review a diff and try to break it | [`/pstack-interrogate`](../interrogate/SKILL.md) |151| Fix a bug test-first when a cheap local test exists | [`/pstack-tdd`](../tdd/SKILL.md) |152| Apply TypeScript rules to `.ts` or `.tsx` work | [`/pstack-typescript-best-practices`](../typescript-best-practices/SKILL.md) |153| Strip comments before review, using a reviewer that didn't write them | [`/pstack-no-comments`](../no-comments/SKILL.md) |154| Clean AI tells out of prose | [`/pstack-unslop`](../unslop/SKILL.md) |155| Write docs, an RFC, a README, a PR description, or a commit message to a standard | [`/pstack-technical-writing`](../technical-writing/SKILL.md) |156| Hear the last reply again in plain words | [`/pstack-bro`](../bro/SKILL.md) |157| Give agents a scripted way to drive the app and prove behavior | [`/pstack-create-verification-skill`](../create-verification-skill/SKILL.md) |158| Bring a verification skill and its feature map back in line with the app | [`/pstack-maintain-verification-skill`](../maintain-verification-skill/SKILL.md) |159| Formally verify a race, invariant, or other property that tests rarely reach | [`/pstack-create-formal-verification-skill`](../create-formal-verification-skill/SKILL.md) |160| 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`](../maintain-formal-verification-skill/SKILL.md) |161| 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`](../statechart/SKILL.md) |162| Vet a performance number before reporting or acting on it | [`/pstack-benchmark-checklist`](../benchmark-checklist/SKILL.md) |163| Run a large or cross-cutting change, or one to review after stepping away | [`/pstack-figure-it-out`](../figure-it-out/SKILL.md) |164| Keep a decision log during a run, and review it afterward | [`/pstack-show-me-your-work`](../show-me-your-work/SKILL.md) |165| Pick a model for each role and a reasoning budget | [`/pstack-setup-pstack`](../setup-pstack/SKILL.md) |166| Turn their own working habits into a personal mode skill | [`/pstack-automate-me`](../automate-me/SKILL.md) |167| Turn what a finished task taught into skill edits | [`/pstack-reflect`](../reflect/SKILL.md) |168| Stop agents from repeating the same mistakes in this repo | [`/pstack-correct`](../correct/SKILL.md) |169| Build a page whose buttons wake a Grok Bot over a webhook | [`/pstack-make-bot-ui`](../make-bot-ui/SKILL.md) |170| Find their way around pstack | `/pstack-poteto-help` |171>>>>>>> 424f2f6b0e1c805d1d227dbc7a59dcb290c89f8a172173If 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.174175Close calls:176177- `/pstack-how` explains what the code does. `/pstack-why` explains the reasons. `/pstack-teach` runs one or both and explains the result plainly.178- `/pstack-arena` gives every worker the same brief and merges the best parts. `/pstack-swarm` splits work into slices or a race and returns one report.179- `/pstack-architect` implements right after it settles the design. Add "with checkpoint" to review the design before it writes code.180- `/pstack-interrogate` reviews the diff. `/pstack-blast-radius` looks for breakage outside the diff and proves the one fact that makes the change safe.181- `/pstack-recall` rebuilds context across recent chats. `/pstack-ketchup` covers only this chat since the user's last message. Resuming one specific chat or branch is the Session pickup playbook.182- `/pstack-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.183184Not in pstack:185186- pstack has no `/orchestrate` skill. Orchestrate is a `/pstack-poteto-mode` playbook. If the slash menu shows `/orchestrate`, another plugin provides it.187188## Playbooks and principles189190Playbooks 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:191192- "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.193- "land the stack" runs Shipping.194- "take over this branch" runs Session pickup.195- "pause safely" runs Pause safely.196- "full autopilot on this queue" runs Autopilot-full. "autopilot, don't merge" runs Autopilot-stack.197- "run the eval playbook" runs Eval.198199The Playbooks section of [`pstack-poteto-mode`](../poteto-mode/SKILL.md) lists every playbook and when it applies. [Guide page 6](../../docs/guide/06-verify-and-ship.md) covers opening, babysitting, and landing a PR.200201pstack has no planning skill. For work that spans phases or stacked PRs, asking `/pstack-poteto-mode` for a plan runs the [Multi-phase plan playbook](../poteto-mode/playbooks/multi-phase-plan.md), which writes the plan and doesn't implement it. For a design question, the Prototype playbook or `/pstack-architect` settles it in code first.202203Principles 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 `/pstack-principle-<name>` still loads one on demand. [Guide page 8](../../docs/guide/08-principles.md) lists them.204205## Fix a run that went wrong206207| Symptom | Fix |208|---|---|209| The mode stopped applying after a few turns | It fades as the chat moves on. Start each task with `/pstack-poteto-mode`. |210| A question got treated as the next step of the last task | Say "new task", or say the turn doesn't need the mode. |211| A new model choice had no effect | The preset agents from `/pstack-setup-pstack` apply to new chats. Start one. |212| Runs cost more than expected | See the cost paragraph under Get set up. |213| 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. |214| Parallel agents overwrote each other | Give each agent its own worktree. |215| An overnight run moved but finished nothing | The run's drive loop needs a check that can pass or fail, not a duration. See [guide page 7](../../docs/guide/07-overnight.md). |216| 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. |217218For a run that drifts, [`references/prompting.md`](references/prompting.md) has one-line steers. [Guide page 10](../../docs/guide/10-recipes-and-pitfalls.md) has more pitfalls and the recipes worth copying.219220## Make pstack my own221222- [`/pstack-automate-me`](../automate-me/SKILL.md) drafts a personal mode skill from the user's own history, to use alongside `/pstack-poteto-mode`.223- [`/pstack-reflect`](../reflect/SKILL.md) after a session turns its lessons into skill edits the user approves.224- `/pstack-poteto-mode write a skill for <workflow>` runs the authoring playbook. The eval playbook tests a skill change blind.225- Fix a misbehaving skill in its own PR, not inside the feature work where it went wrong.226227[Guide page 9](../../docs/guide/09-make-it-yours.md) covers each of these.228229## Reply230231Lead with the answer. Give at most one example prompt in a code block, adapted from [`references/recipes.md`](references/recipes.md) when one fits, then the link to that file. Keep it short unless the user asked for the whole map.