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 and do the work under it.

This file maps questions to the skills 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/lucasheriques/pstack/blob/main/ followed by its path from the repo root, such as skills/how/SKILL.md or skills/poteto-help/references/prompting.md.

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 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.

Get set up

1. Install with claude plugin marketplace add lucasheriques/pstack, then claude plugin install pstack@pstack. Update with claude plugin marketplace update pstack, then claude plugin update pstack@pstack, and restart Claude Code.
2. Check the requirements in the README: gh for PR work, the gh stack extension for stacks, and bun for the helper scripts.
3. Start a real task with /pstack:poteto-mode, a goal, and a check that can pass or fail.

Installing changes nothing until a skill runs. poteto-mode also switches on by itself for engineering work that matches a playbook. Offer to word their first prompt with them, per references/prompting.md.

To change which model a role uses, edit poteto-mode/references/models.md. claude plugin update overwrites the installed copy, so fork the repo and install from the fork to keep an edit. Roles map to opus, sonnet, or inherit. If cost is the worry, say where the tokens go. pstack spends extra tokens on subagents and review panels. A role set to sonnet costs less than opus, and a shorter panel list runs fewer subagents, one for each entry. Save /pstack:poteto-mode for work that needs rigor.

To let agents merge their own PRs, the user writes a policy at ~/.claude/pstack/merge-policy.json. The README's "Letting agents merge" section has the format. Without it agents open ready PRs and never merge.

Start a task with /pstack:poteto-mode

/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.

poteto-mode applies itself when a playbook matches or the task needs rigor, and stays out of casual turns. Invoke it again when the subject changes, so it matches a fresh playbook. Its subagents run as pstack:poteto-agent. To get the same style from a subagent of your own, spawn it with subagent_type: "pstack:poteto-agent".

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.

If a skill directory next to this one is missing from the table, read its frontmatter and route by its description. The principle-* files live under poteto-mode/principles/ and are covered 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: /loop, /simplify, and /run are Claude Code built-ins. pstack has no /orchestrate skill. Orchestrate is a poteto-mode playbook.

Playbooks and principles

Playbooks are step lists inside poteto-mode, not skills, so they have no slash command. Describing the task picks one. Phrases like these 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.
• An explicit instruction to land or merge, such as "land the stack", runs Shipping.
• Taking over a prior agent's work, such as "take over this branch", runs Session pickup.
• "pause safely" runs Pause safely.
• "full autopilot on this queue" runs Autopilot-full. "autopilot, don't merge" or "stack them, don't ship" runs Autopilot-stack.
• "run the eval playbook", or testing how a skill or prompt change affects agent behavior, runs Eval.

The Playbooks section of poteto-mode lists every playbook and when it applies. For work that spans phases or stacked PRs, asking 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 files 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."

Fix a run that went wrong

For a run that drifts, references/prompting.md has one-line steers.

Make pstack my own

• /pstack:automate-me drafts a personal mode skill from the user's own history, to use alongside 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.

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.