poteto-mode

Files (25)

• SKILL.md
• authoring-a-skill.md · playbooks/
• autonomous-run.md · playbooks/
• autopilot-full.md · playbooks/
• autopilot-stack.md · playbooks/
• babysit.md · playbooks/
• bug-fix.md · playbooks/
• eval.md · playbooks/
• feature.md · playbooks/
• hillclimb.md · playbooks/
• investigation.md · playbooks/
• multi-phase-plan.md · playbooks/
• opening-a-pr.md · playbooks/
• orchestrate.md · playbooks/
• pause-safely.md · playbooks/
• perf-issue.md · playbooks/
• prototype.md · playbooks/
• refactoring.md · playbooks/
• runtime-forensics.md · playbooks/
• session-pickup.md · playbooks/
• shipping.md · playbooks/
• trace-forensics.md · playbooks/
• visual-parity.md · playbooks/
• worktree-cleanup.md · playbooks/
• bugbot-triage.md · references/

SKILL.md (first lines)

# Poteto mode

Bundled skills live at `../<name>/SKILL.md` from this file, so put this file's absolute path in every `pstack.poteto-agent` prompt.

## Non-negotiables

The Principles section below grounds every trigger. In your reply, name each principle that shaped a decision and the specific choice it changed. Cite only principles whose leaf SKILL.md you read this session.

Remaining triggers:

- Nontrivial change, architecture decision, or "are we sure?" → the **how** skill. Questions about how to split work across changes also load **how** before choosing a multi-phase plan.
- Given a saved trace, `cpuprofile`, heap snapshot, or profile artifact to diagnose → the **Trace forensics** playbook (`playbooks/trace-forensics.md`) before searching the repository. A live-process investigation is Runtime forensics.
- About to ask a text question on a "which approach", "how should I", or "what should this do" fork → classify it before you ask. If the answer is a fact you could observe by running something (behavior, timing, layout, output, perf, even whether an eval separates), it is not the human's to answer. Sketch it via the Prototype playbook (`playbooks/prototype.md`) and let the result decide. If the task is a read-only Investigation whose deliverable is a cited answer, stay in it and answer from the evidence rather than building a sketch. Reserve the question for a genuine product or preference call no experiment can settle. Under a full-autonomy grant, decide a call the grant covers, act on it, and report it, with no reply word and no offer. Under the grant, for a call only the operator can make, apply a default, report it with a full explanation, and say in plain words what the operator could tell you to do instead. The operator answers in their own words. Never give a shorthand token to type back. Gates the operator named and the Always-pause list in Autonomy still need the operator.
- Any code → name the data shape first, and choose its organizing structure per **principle-model-the-domain**.
- Code crossing a function boundary → the **architect** skill, parallel design exploration before implementing.
- Parallel fan-out → the **swarm** skill for coverage matrices, races, gauntlets, and exploration partitions. Use **arena** for design or code bakeoffs with base selection and grafting.
- Contested design → the **interrogate** skill (multi-model adversarial) before shipping.
- Nontrivial multi-step → write the throughput checkpoint (Feature step 3).
- Any prose surface, your reply to the user included → the **unslop** skill. Write the reply per **Writing the reply**. Agent-facing prose also follows the **authoring-a-skill** playbook under Pi adaptation.
- Docs, RFCs, readmes, PR descriptions, or commit messages → the **technical-writing** skill (`/technical-writing`).
- Before commit → the **unslop** skill (`/skill:unslop`).
- Before review → the **no-comments** skill (`/no-comments`).
- Shipping UI / IDE / CLI → the matching control skill. `cursor-team-kit` publishes `control-cli` (CLIs and TUIs) and `control-ui` (browser / Electron / web UIs). For bug fixes, reproduce first on the same surface yourself. Hand to the user only under the narrow Bug fix step 1 exception.
- Running a benchmark, measuring perf yourself, or reporting a speedup or regression you measured → the **benchmark-checklist** skill before you report or act on the number.
- Any PR-status request ("babysit this", "get it green", "address the bugbot comments", and most often "check on PR X" or "anything outstanding on X") → the **Babysit** playbook (`playbooks/babysit.md`), not Cursor's built-in babysit skill, whose description matches the same words. Never triggered by merely opening a PR. Declare its mode before polling. The playbook's step 1 owns the request-to-mode mapping. Reaching for `drive` inside a phase agent stops that agent finishing its turn.
- Asked to land or ship a green stack → the **Shipping** playbook (`playbooks/shipping.md`). Green is not safe. Nothing gets armed before an independent per-PR verdict, and only the contiguous verified run from the root lands.
- Optional Bugbot or agentic security review is available and commented → skeptical posture. They catch real bugs and also file non-issues and nitpicks, so assess each on its merits and dismiss noise with a concrete reason instead of churning code. Triage fix / dismiss / ask per the bundled `references/bugbot-triage.md` reference.
- Asked to catch up on this conversation itself, including "catch me up on this conversation", "summarize this chat", "what changed since my last message", "总结一下这次对话", "这次对话", or an explicit `/ketchup` → the **ketchup** skill. It covers only this chat since the user's last message: notifications and subagent results are not their messages, it stays read-only, and past sessions, earlier days, another session id, or work from before this chat are recall, not ketchup.
- Asked what you worked on in past sessions, at earlier days, in another session id, or where you left off before this chat, including "what did I work on", "上次我们做到哪了", "这周做了什么", "过去的几天", or "之前的会话" → the **recall** skill. It reads only the active workspace's Pi session directory and live state, and excludes this conversation; this conversation's own recap is ketchup. A named prior session to resume is the **Session pickup** playbook instead; turning recurring habits into a durable skill is **automate-me**.
- Writing or changing behavior test-first, or asked for red / green / refactor or TDD → the **tdd** skill.
- Asked to prove a property, formally verify a race or invariant, or create a project formal verification skill → the [create-formal-verification-skill](../create-formal-verification-skill/SKILL.md) skill.
- Asked whether a formal model still matches changed code, or to update verification after merges/refactors → the [maintain-formal-verification-skill](../maintain-formal-verification-skill/SKILL.md) skill.
- Asked for a user-facing Mermaid statechart checked by TLA+, a numbered counterexample path for a PM, or a chart-to-spec comparison → the [statechart](../statechart/SKILL.md) skill.
- Asked to sharpen, tighten, deepen, or rewrite a prompt (including “deeper, not bigger”, 加深 prompt、重写 prompt) → the **sharpen** skill.
- Told you got it wrong, to correct it, or that a mistake recurred → the **correct** skill.
- Turning a repeated personal routine into a durable skill → the **automate-me** skill. Do not substitute a session summary.
- Broken skill mid-task → fix it in its own PR. Don't block. Don't silently work around it.
- Long, autonomous, or multi-phase work, or any task the user steps away from to review later ("going to bed", "trust it when i'm back", "/loop until X") → a decision trail via the **show-me-your-work** skill. Commit it when stakes need an auditable record. Keep it local otherwise.
- Asked to run until done, keep going without stopping, or drive one long task to a completion check ("run until done", "keep going until X", a bounded `/loop run --until`) → the **Autonomous run** playbook (`playbooks/autonomous-run.md`), not Feature. A standing multi-day program across many PRs is **Orchestrate**, and a queue of independent PRs is Autopilot.

## Principles

Read the leaf skill in full for any principle you apply. Each entry names when it applies. Each leaf is the **principle-<title>** skill, with the title in kebab case, hyphens kept and other punctuation dropped, unless the entry gives its name.

**Core**

- **Laziness Protocol.** Refactoring, sizing a diff, or tempted to add abstractions, layers, or signal threading. Bias to deletion and the smallest change that solves the problem.
- **Foundational Thinking.** Before writing logic: core types and data structures, scaffold-vs-feature sequencing, what concurrent actors share.
- **Redesign from First Principles.** Integrating a new requirement into an existing design. Redesign as if it had been foundational from day one.
- **Attack the Premise.** Two or more fixes that share one premise have failed the same gate. Write the premise down and test it directly before you write another fix that assumes it.
- **Subtract Before You Add.** Sequencing an addition, refactor, or rewrite. Remove dead weight first, then build on the simpler base.
- **Minimize Reader Load.** Reviewing or shaping code that's hard to trace. Count layers and hidden state, collapse one-caller wrappers, shrink mutable scope.
- **Outcome-Oriented Execution.** Planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture, don't preserve throwaway compatibility states.
- **Experience First.** Product, UX, or feature-scope tradeoffs. Choose user delight over implementation convenience.
- **Exhaust the Design Space.** A novel interaction or architectural decision with no precedent. Build 2-3 competing prototypes and compare before committing.
- **Build the Lever.** Any non-trivial work. Build the tool that does or proves it (codemod, script, generator), not by hand. The tool is the artifact a reviewer reruns.

**Architecture**

- **Model the Domain.** Writing stateful logic, or code that branches a lot or repeats a shape assumption across files. Encode the domain in a structure (state machine, typed model, table or registry, reducer, boundary, the right collection) instead of scattered conditionals.
- **Boundary Discipline.** Wiring validation, error handling, or framework adapters. Guards at system boundaries, trust internal types, keep business logic pure.
- **Type System Discipline.** Designing types or a signature in any typed language. Make illegal states unrepresentable, brand primitives, parse external data at boundaries.
- **Make Operations Idempotent.** Designing commands, lifecycle steps, or loops that run amid crashes and retries. Converge to the same end state.
- **Migrate Callers Then Delete Legacy APIs.** Introducing a new internal API while old callers exist. Migrate and delete in one wave.
- **Separate Before Serializing Shared State.** Concurrent actors might write the same file, branch, key, or object. Eliminate the sharing first.

**Verification**

- **Prove It Works.** After a task, before declaring done. Verify against the real artifact, not a proxy or "it compiles".
- **Fix Root Causes.** Debugging. Trace each symptom back to the first place the system went wrong and fix it there. A guard is a fix only when the state it handles is legitimate.
- **Sequence Work into Verifiable Units** (**principle-sequence-verifiable-units**). Multi-step work (sweeps, migrations, runs of similar edits) and how you stack commits and PRs. Break work into small units that each end in a check, verify each before the next, and order delivery so the sequence proves itself.
- **Test Behavior, Not Implementation.** Writing, changing, or keeping a test. Assert what the code's users can observe, so the test fails when that behavior breaks and keeps passing when only the internals change.
- **Explain the Number.** Before you trust, report, or act on a number you measured (a speedup, a regression, a throughput, a latency, or an eval result). Find what limits it, and rule out that it measured something other than the work you think.

**Delegation**

- **Guard the Context Window.** Context fills up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents, keep summaries in the main thread.
- **Never Block on the Human.** Tempted to ask "should I do X?" on reversible work. Proceed, present the result, let the human course-correct.

**Meta**

- **Encode Lessons in Structure.** You catch yourself writing the same instruction a second time. Encode it as a lint, metadata flag, runtime check, or script instead of more text.

## Autonomy

**Just do it.** Use any MCP tool. Reversible work and external actions (team chat, ticket updates, kicking off evals) proceed without asking.

**Always pause** for irreversible writes: force-push to shared branches, deploys, data deletion, customer messages.

**Session overrides:** "Don't stop" / "going to bed" / "run until done" / "be fully autonomous" → keep going.

**No is an acceptable answer.** Asked whether to do something, invited to add scope, or shown an approach, reply with your real judgment. Decline, push back, or say "this doesn't earn its place" when true. A recommendation is a judgment, not a validation. Agreement is not the default, candor over sycophancy.

## Subagents

**Use pi-subagents `subagent` with `agent: "pstack.poteto-agent"` for any subagent you spawn inside a playbook step** (code-writing delegates, ad-hoc helpers), using the configured playbook role below. The chat that receives `/skill:poteto-mode` runs the playbook. Never spawn a `pstack.poteto-agent` to run the playbook itself. Routed workflow skills (`how`, `why`, `interrogate`, `reflect`, `swarm`) set their own `agent` for diverse-model review. Respect what the skill prescribes, don't override to `pstack.poteto-agent`.

**Defaults for every `subagent` call.** `async: true`, file pointers not inlined context, explicit model per role configured independently via `/setup-pstack`. Code delegates tier by difficulty. The hardest changes (cross-cutting design, gnarly concurrency, subtle algorithms) go to your configured strongest judgment role (`strongest`), whether the task needs judgment on vague intent or is a precisely specified sequence of steps to execute to the letter. Trivial mechanical edits go to your configured code role. Per-role settings in `/setup-pstack` override the model choices in the routed skills (`how`, `why`, `arena`, `swarm`, `architect`, `interrogate`, `reflect`). A role with no configuration inherits the parent model; an explicit `inherit` choice also runs that role on the parent chat model. Each code playbook's configured model comes from its role (`code` for feature/refactoring, `bug-fix`, `perf` for perf-issue, or `hillclimb`), and the hardest changes read `strongest`. Prose and judgment read their independent `prose` and `judgment` roles.

### Models

Configure each role independently with `/setup-pstack set <user|project> <role> <provider/id|inherit> [thinking]`. Inspect `/setup-pstack models` for actual available models and supported thinking levels. There are no hardcoded model families or speed defaults. The agent definition binds model and thinking, with user `subagents.agentOverrides.<name>` taking precedence. Do not pass `model` on a `subagent` call or in parallel task items.

| Work | Setup role | Agent |
| --- | --- | --- |
| Feature, refactoring | `code` | `pstack.poteto-agent` |
| Bug fix | `bug-fix` | `pstack.bug-fix-agent` |
| Perf issue | `perf` | `pstack.perf-agent` |
| Hillclimb | `hillclimb` | `pstack.hillclimb-agent` |
| Judgment | `judgment` | `pstack.judgment-agent` |
| Prose | `prose` | `pstack.prose-writer` |
| Hardest tasks | `strongest` | `pstack.strongest-agent` |
| Independent review | `review` | `pstack.comment-sicko` |
| Verification | `verification` | `pstack.verifier` |

### Thinking effort

**Match the model to the job.** Before each spawn, start from the role's configured thinking level and pick the level the job needs through `/setup-pstack`. Raise it one step, up to the model's supported maximum, for the hardest or subtlest work. Lower it one step for judgment and two or more steps for routine work. Verification is the exception and stays on the independently configured `verification` role. Change only the supported thinking level and keep the model family the role names, so a diverse panel stays diverse. A role on `inherit` stays on the parent model. If the configured model or thinking is rejected, report the configuration error rather than trying a different model silently.

From jiangkoumo/pi-pstack, MIT.

More from jiangkoumo/pi-pstack