pstack

Personal skills for daily workflows. Plugin ID: pstack. Version: 0.1.51.

Skills

Skill	Purpose and when to use	Setup
how	Explicit code walkthroughs, subsystem architecture, runtime flow, ownership, and layering questions before changes	Codebase read/search access; optional subagents with sequential fallback
create-verification-skill	Generate a project-local verification skill and feature map for real app workflows	Target codebase, project runtime/build tools, suitable harness, and disposable fixtures
maintain-verification-skill	Audit and repair verification documentation, feature maps, and owned harnesses using source and live coverage	Existing verification skill and map, runnable test environment, live harness; optional subagents
why	Investigate historical rationale and tradeoffs with cited, confidence-qualified evidence	Target code/history; available authorized connectors or authenticated `gh`; optional subagents
poteto-mode	Explicit engineering workflow and style guidance with task-specific playbooks	Compatibility guide; optional Bun/Node/Git helpers and authorized GitHub access
principle-attack-the-premise	Apply when two or more fixes that share one premise have failed the same gate. Take a census of which actors hold the imbalance before the next fix, then question the premise instead of writing another fix that assumes it.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-boundary-discipline	Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-build-the-lever	Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-encode-lessons-in-structure	Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-exhaust-the-design-space	Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-experience-first	Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-explain-the-number	Apply 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.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-fix-root-causes	Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-foundational-thinking	Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-guard-the-context-window	Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-laziness-protocol	Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-make-operations-idempotent	Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-migrate-callers-then-delete-legacy-apis	Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibility layers.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-minimize-reader-load	Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-model-the-domain	Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-never-block-on-the-human	Apply when tempted to ask 'should I do X?' on reversible work.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-outcome-oriented-execution	Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-prove-it-works	Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-redesign-from-first-principles	Apply when integrating a new requirement into an existing design.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-separate-before-serializing-shared-state	Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-sequence-verifiable-units	Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-subtract-before-you-add	Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-test-behavior-not-implementation	Apply when you write, change, or keep a test. Call the code as its users do and assert the exact result they see. Rewrite or delete a test that would pass if every imported function returned undefined.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
principle-type-system-discipline	Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
architect	Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.	Relevant code or current-conversation context and host-native subagents when available. Sequential fallback and review limitations are explicit.
arena	Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.	Relevant code or current-conversation context and host-native subagents when available. Sequential fallback and review limitations are explicit.
benchmark-checklist	Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.	A runnable target benchmark and OS/runtime measurement tools appropriate to the project.
bro	Restate the last message in plain human language, with no jargon.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
control-cli	Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services. Use for CLI UX checks, startup regressions, memory leaks, hangs, prompt flows, or terminal demos.	A local target application, its existing test/runtime tools, and host-supported terminal or browser control. No external service is bundled.
control-ui	Build or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI. Use for local UI verification, screenshots, accessibility snapshots, perf profiles, visual diffs, or reproducing UI bugs.	A local target application, its existing test/runtime tools, and host-supported terminal or browser control. No external service is bundled.
deslop	Remove AI-generated code slop and clean up code style	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
figure-it-out	Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions. Use for /figure-it-out or 'figure it out'.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
interrogate	Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.	Relevant code or current-conversation context and host-native subagents when available. Sequential fallback and review limitations are explicit.
ketchup	Catch the user up on what changed in this chat since their last message, in a few plain sentences and small visuals. Give each action item just enough context to make the call. Use for /ketchup.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
no-comments	Review scoped comments, remove supported redundancy, preserve contracts and safety constraints, and propose enforceable alternatives.	Relevant code or current-conversation context and host-native subagents when available. Sequential fallback and review limitations are explicit.
reflect	Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.	Relevant code or current-conversation context and host-native subagents when available. Sequential fallback and review limitations are explicit.
setup-pstack	Configure explicit, supported model and reasoning preferences for pstack roles in the current session or approved project guidance.	Host-exposed model capabilities and explicit user preferences; persistence is opt-in and not automatically loaded.
show-me-your-work	Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.	Bash for the bundled TSV helper; current-conversation evidence. Optional authorized independent review.
swarm	Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.	Relevant code or current-conversation context and host-native subagents when available. Sequential fallback and review limitations are explicit.
tdd	Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
technical-writing	Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
typescript-best-practices	TypeScript best practices. Use when reading or editing any .ts or .tsx file.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
unslop	Cut AI tells from any writing.	Relevant project or text context; no new runtime dependency. Follow applicable project tools and permissions.
verify-this	Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE.	A local target application, its existing test/runtime tools, and host-supported terminal or browser control. No external service is bundled.

Example: “Use how to explain how authentication works in this repository.” For verification authoring, ask “Use create-verification-skill to create a verification workflow for this repository.” For maintenance, ask “Use maintain-verification-skill to audit this repository’s verification skill.” For historical rationale, ask “Use why to investigate why this subsystem was designed this way.” Automatic invocation is disabled for all bundled skills.

Attribution

how is imported from cursor/plugins at commit 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/how. It is MIT-licensed, copyright (c) 2026 Lauren Tan; the license is included. See the root import record for source links and local adaptations.

create-verification-skill is imported from cursor/plugins at commit 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/create-verification-skill. Its three example files are preserved unchanged. It is MIT-licensed, copyright (c) 2026 Lauren Tan; the license is included. See the root import record for adaptations and requirements.

maintain-verification-skill is imported from cursor/plugins at commit 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/maintain-verification-skill/SKILL.md. It is MIT-licensed, copyright (c) 2026 Lauren Tan; the license is included. See the root import record for adaptations and requirements.

why is imported from cursor/plugins at commit 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/why. It includes all upstream reference files and is MIT-licensed, copyright (c) 2026 Lauren Tan; the license is included. See the root import record for adaptations and requirements.

poteto-mode is imported from cursor/plugins at commit 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/poteto-mode, with all 46 upstream files. It is MIT-licensed, copyright (c) 2026 Lauren Tan; the license is included. See the import record and compatibility guide. Request “Use poteto-mode for this task” explicitly.

principle-attack-the-premise comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-attack-the-premise. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-boundary-discipline comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-boundary-discipline. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-build-the-lever comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-build-the-lever. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-encode-lessons-in-structure comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-encode-lessons-in-structure. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-exhaust-the-design-space comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-exhaust-the-design-space. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-experience-first comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-experience-first. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-explain-the-number comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-explain-the-number. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-fix-root-causes comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-fix-root-causes. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-foundational-thinking comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-foundational-thinking. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-guard-the-context-window comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-guard-the-context-window. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-laziness-protocol comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-laziness-protocol. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-make-operations-idempotent comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-make-operations-idempotent. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-migrate-callers-then-delete-legacy-apis comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-migrate-callers-then-delete-legacy-apis. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-minimize-reader-load comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-minimize-reader-load. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-model-the-domain comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-model-the-domain. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-never-block-on-the-human comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-never-block-on-the-human. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-outcome-oriented-execution comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-outcome-oriented-execution. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-prove-it-works comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-prove-it-works. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-redesign-from-first-principles comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-redesign-from-first-principles. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-separate-before-serializing-shared-state comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-separate-before-serializing-shared-state. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-sequence-verifiable-units comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-sequence-verifiable-units. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-subtract-before-you-add comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-subtract-before-you-add. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-test-behavior-not-implementation comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-test-behavior-not-implementation. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

principle-type-system-discipline comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/principle-type-system-discipline. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

benchmark-checklist comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/benchmark-checklist. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

show-me-your-work comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/show-me-your-work. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

technical-writing comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/technical-writing. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

typescript-best-practices comes from cursor/plugins at 1e5c90a4b6f249917bd21fe361b3a2a7deb741b8, path pstack/skills/typescript-best-practices. MIT, copyright (c) 2026 Lauren Tan; license, source and adaptations.

Verification

Manifest, frontmatter, invocation policy, references, and attribution receive static checks. Host installation and end-to-end execution have not been tested. The imported files require no installation. Executing either verification skill requires the target application’s tools and test environment; no target application was exercised during this import.