Collection · published
pstack — agent workflow and engineering skills
pstack — agent workflow and engineering skills. Installed together as the pstack plugin.
Install or use
/plugin marketplace add cursor/plugins /plugin install pstack@cursor-plugins
In this collection
- architect
Plans API contracts and module boundaries early, then keeps design choices aligned as implementation develops.
Source/architectin Cursor’s slash menu - arena
Compares several independent approaches, then combines the strongest ideas into one polished result.
Source/arenain Cursor’s slash menu - automate-me
Drafts or revises a personal -mode skill via create-skill + unslop, optionally pulling fresh evidence from recent transcripts.
Source/automate-mein Cursor’s slash menu - benchmark-checklist
Assess a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act.
Source/benchmark-checklistin Cursor’s slash menu - blast-radius
Tests what a change might break outside the diff and verifies the assumption that keeps it safe.
Source/blast-radiusin Cursor’s slash menu - bro
Rephrase the last message in plain human language, with no jargon.
Source/broin Cursor’s slash menu - correct
Identify the mistakes agents keep repeating in this repo and make each one impossible.
Source/correctin Cursor’s slash menu - create-formal-verification-skill
Produce a project-local skill that formally verifies the code where a bug costs the most and tests reach the least.
Source/create-formal-verification-skillin Cursor’s slash menu - create-verification-skill
Creates a project-specific skill that tests an application through the same steps a user takes.
Source/create-verification-skillin Cursor’s slash menu - figure-it-out
Builds an auditable playbook for a complex task, with hypotheses, checks, and a decision log.
Source/figure-it-outin Cursor’s slash menu - how
Explains a system’s design and runtime flow to answer ownership, placement, and implementation questions.
Source/howin Cursor’s slash menu - in-your-own-words
Rephrase in your own words what you think the user's goals are and what problem they're trying to solve.
Source/in-your-own-wordsin Cursor’s slash menu - interrogate
Challenges a change from several independent review angles to expose assumptions and overlooked risks.
Source/interrogatein Cursor’s slash menu - ketchup
Catch the user up on what changed in this chat since their last message, in plain words and small visuals.
Source/ketchupin Cursor’s slash menu - maintain-formal-verification-skill
Updates formal models and verification checks after code changes and distinguishes verification drift from bugs.
Source/maintain-formal-verification-skillin Cursor’s slash menu - maintain-verification-skill
Reviews a project’s verification guide against its features and tests those features in a live session.
Source/maintain-verification-skillin Cursor’s slash menu - make-bot-ui
Creates a control interface that triggers a Grok Bot through a webhook with the required sender handoff.
Source/make-bot-uiin Cursor’s slash menu - no-comments
Compare Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
Source/no-commentsin Cursor’s slash menu - poteto-help
Directs users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task.
Source/poteto-helpin Cursor’s slash menu - poteto-mode
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.
Source/poteto-modein Cursor’s slash menu - principle-attack-the-premise
Apply when two or more fixes that share one premise have failed the same gate.
Source/principle-attack-the-premisein Cursor’s slash menu - principle-boundary-discipline
Apply when wiring validation, error handling, or framework adapters.
Source/principle-boundary-disciplinein Cursor’s slash menu - principle-build-the-lever
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks.
Source/principle-build-the-leverin Cursor’s slash menu - principle-encode-lessons-in-structure
Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction.
Source/principle-encode-lessons-in-structurein Cursor’s slash menu - principle-exhaust-the-design-space
Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase.
Source/principle-exhaust-the-design-spacein Cursor’s slash menu - principle-experience-first
Apply when product, UX, or feature-scope tradeoffs come up.
Source/principle-experience-firstin Cursor’s slash menu - principle-explain-the-number
Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency.
Source/principle-explain-the-numberin Cursor’s slash menu - principle-fix-root-causes
Apply when debugging. Trace each symptom back to the first place the system went wrong and fix it there.
Source/principle-fix-root-causesin Cursor’s slash menu - principle-foundational-thinking
Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share.
Source/principle-foundational-thinkingin Cursor’s slash menu - principle-guard-the-context-window
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning.
Source/principle-guard-the-context-windowin Cursor’s slash menu - principle-laziness-protocol
Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading.
Source/principle-laziness-protocolin Cursor’s slash menu - principle-make-operations-idempotent
Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries.
Source/principle-make-operations-idempotentin Cursor’s slash menu - principle-migrate-callers-then-delete-legacy-apis
Apply when introducing a new internal API while old callers still exist.
Source/principle-migrate-callers-then-delete-legacy-apisin Cursor’s slash menu - principle-minimize-reader-load
Apply when reviewing or shaping code that's hard to trace.
Source/principle-minimize-reader-loadin Cursor’s slash menu - principle-model-the-domain
Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files.
Source/principle-model-the-domainin Cursor’s slash menu - principle-never-block-on-the-human
Apply when tempted to ask 'should I do X?' on reversible work.
Source/principle-never-block-on-the-humanin Cursor’s slash menu - principle-outcome-oriented-execution
Apply during planned rewrites and migrations with explicit phase boundaries.
Source/principle-outcome-oriented-executionin Cursor’s slash menu - principle-prove-it-works
Apply after completing a task, before declaring done.
Source/principle-prove-it-worksin Cursor’s slash menu - principle-redesign-from-first-principles
Apply when integrating a new requirement into an existing design.
Source/principle-redesign-from-first-principlesin Cursor’s slash menu - principle-separate-before-serializing-shared-state
Apply when concurrent actors might write to the same file, branch, key, or state object.
Source/principle-separate-before-serializing-shared-statein Cursor’s slash menu - principle-sequence-verifiable-units
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs.
Source/principle-sequence-verifiable-unitsin Cursor’s slash menu - principle-subtract-before-you-add
Apply when sequencing an addition, refactor, or rewrite.
Source/principle-subtract-before-you-addin Cursor’s slash menu - principle-test-behavior-not-implementation
Apply when you write, change, or keep a test.
Source/principle-test-behavior-not-implementationin Cursor’s slash menu - principle-type-system-discipline
Apply when designing types, reviewing a function signature, or writing code in any statically-typed language.
Source/principle-type-system-disciplinein Cursor’s slash menu - recall
Reconstructs recent work from chat, live state, and shared records into a short handoff.
Source/recallin Cursor’s slash menu - reflect
Compares independent reviews of a session and turns findings into edits to existing skills.
Source/reflectin Cursor’s slash menu - setup-pstack
Set up which models pstack uses per role and at what reasoning budget.
Source/setup-pstackin Cursor’s slash menu - sharpen
Create a task deeper, not bigger, then rewrite the prompt.
Source/sharpenin Cursor’s slash menu - show-me-your-work
Records decisions, evidence, and outcomes in a reviewable log during longer tasks.
Source/show-me-your-workin Cursor’s slash menu - statechart
Draw what an app's user sees as a Mermaid statechart from a TLA+ model.
Source/statechartin Cursor’s slash menu - swarm
Fan out N parallel workers, drain them, and return one report.
Source/swarmin Cursor’s slash menu - tdd
Builds features through a test-first cycle that checks behavior before and after implementation.
Source/tddin Cursor’s slash menu - teach
Clarify a body of work plainly so a person actually understands it.
Source/teachin Cursor’s slash menu - technical-writing
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax.
Source/technical-writingin Cursor’s slash menu - typescript-best-practices
TypeScript best practices. Use when reading or editing any .ts or .tsx file.
Source/typescript-best-practicesin Cursor’s slash menu - unslop
Removes common AI wording patterns from copy while preserving meaning and voice.
Source/unslopin Cursor’s slash menu - why
Searches project evidence to explain why a decision was made and cites the tradeoffs it finds.
Source/whyin Cursor’s slash menu