poteto-help
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.
- License 许可
- MIT
- 最近更新
- 2026-10-21
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- poteto-help
- description
- 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.
02 资源文件 2
- 参考文档references/prompting.md3.2 KB
- 参考文档references/recipes.md3.9 KB
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 how to keep 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 port, which the user may not be able to open, so give the user the file's path under ~/.config/opencode/: skills under skills/pstack/<name>/, docs under pstack-docs/.
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
model:line in~/.config/opencode/agents/pstack/<role>.mdmeans/pstack/setup-pstackhasn't run for this user, so every role inherits the parent 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-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.
When no role agent carries a model: line and it matters, ask whether the user wants to pick a model for each role and a 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-pstackto type, and answer their question too. - Later: answer their question, and add one line saying every role keeps inheriting the parent session model until they run
/pstack/setup-pstack.
Get set up
- Install pstack into
~/.config/opencodewithnode scripts/install.mjsfrom the pstack checkout. Add--projectto install into./.opencodeinstead. - Run
/pstack/setup-pstack. It asks for a budget, maps a model to each role, and writes themodel:line of each role agent. The choice applies to new subagents and new sessions. 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. Every skill except /pstack/poteto-mode is advertised by ID, so the model can load it from the user's words; /pstack/poteto-mode loads only when the user types it. 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 agent with no model: line inherits the session's model, which saves tokens when the session runs on a cheaper model. A panel runs one subagent per agent ID, so its seats are the cost. Save /pstack/poteto-mode for work that needs rigor.
pstack is built for OpenCode v2. Every skill is an ID, <name>, loaded with the skill tool and typed as /pstack/<name>. Agents are the pstack/ files under ~/.config/opencode/agents/pstack/, and pstack's model-per-role choice is the model: line of those files. A step that needs a feature OpenCode lacks, such as webhook routines or a hosted bot reviewer, is skipped with one line, Skipped in OpenCode: <step>. <reason>., and the run continues. The adapter maps every name.
Other tools can read the skills, because they use the Agent Skills format. But most workflow skills, including /pstack/poteto-mode, /pstack/how, /pstack/why, and /pstack/teach, spawn subagents through OpenCode's subagent tool and rely on its agent files, so those parts may not work elsewhere.
Start a task with /pstack/poteto-mode
/pstack/poteto-mode matches the task to a playbook, opens the plan at the top of its reply, updates it as each step lands, and runs the other skills as the steps need them. A step it skips stays in the plan 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 /pstack/poteto-mode stays on depends on how the user starts it:
- Typing
/pstack/poteto-modewith the message attaches the skill to that turn. It fades as the session moves on. - Selecting the primary agent in the TUI, or launching with
opencode run --agent <id>, keeps it in context every turn, and keeps it out of casual turns. - There is no mode list to pick from. Everywhere else, start each new task with
/pstack/poteto-mode.
Mid-chat, "new task" makes the mode match a fresh playbook. /pstack/poteto-mode already uses pstack/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 /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 |
| 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, each in its own worktree | /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 |
| 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 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 trigger a bot through a local command | /pstack/make-bot-ui |
| Find their way around pstack | /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:
/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.
Not in pstack:
- There is no separate cleanup plugin. The repo's own verification skill is the way to drive a surface and prove a change, and
/pstack/create-verification-skillgenerates one. With none, drive the surface with the shell and say so. - pstack has no loop command. A loop is a
background: truesubagent that polls, or a shell watcher. It has no built-in skill author either: authoring a skill is the Authoring a skill playbook,playbooks/authoring-a-skill.mdinpoteto-mode. - pstack has no
/orchestrateskill. Orchestrate is a/pstack/poteto-modeplaybook. 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. "stack them, don't ship" runs Autopilot-stack.
- "run the eval playbook" runs Eval.
Without /pstack/poteto-mode, a phrase such as "babysit this pr" can start another installed 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, and OpenCode has no plan mode. 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 was attached to one turn. Select the primary agent in the TUI, 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 | /pstack/setup-pstack writes the model: line of each role agent. A subagent spawned before the change keeps its model, so 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 | Every skill except /pstack/poteto-mode is advertised by ID, so it loads when the model picks it or the user names it. /pstack/poteto-mode loads only when the user types it. |
| Parallel agents overwrote each other | Give each agent its own worktree with worktree_create, and run it in that directory. |
| An overnight run moved but finished nothing | A polling background: true subagent 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-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.
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.
04 同仓库更多 Skills
why
Trace why code works this way or why a design was chosen, from source control, trackers, docs, and telemetry. Use for rationale, regressions, or postmortems.
unslop
Cut AI tells from any writing.
typescript-best-practices
TypeScript best practices. Use when reading or editing any .ts or .tsx file.
technical-writing
Write or review docs, RFCs, readmes, PR descriptions, and commit messages in Diataxis structure with Google style, STE, and Global English.
teach
Explain a body of work so a person actually understands it, running how and why and weaving both into one clear explanation. Use for teach me this.
tdd
Use only when the user asks for TDD, a failing test, or a regression test, or when a bug has a cheap local test target; skip unclear or costly test paths.