Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/scaryrawr/scarypilot.Loading the repository README…
Showing 40 of 53 collected skills.
Check a TLA+ model of a system that moves between states, such as a product flow, a protocol, or a service, and draw it as a Mermaid statechart. The report gives the shortest path to each state that breaks a rule. Use for /statechart, or to show a bug as a…
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.
Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-verification-skill, "model-check this race", "prove this…
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Adversaries try to break a change or design, and only findings proven by a run survive.
Catch the user up like /ketchup, with a short subtitled video of slides for what happened and the waiting calls as text under it. Use for /ketchup-video.
Answer explicitly typed /poteto-help requests or help questions about pstack setup, usage, skills, playbooks, and principles. Recommend a prompt without executing it. Not for generic coding, debugging, design, review, or implementation work.
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.
Apply before you measure, and 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.
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.
Configure which models pstack uses per role. Detect available Copilot Task models and write an always-applied user instruction in Copilot home. Use for /setup-pstack, "configure pstack models", or changing pstack's model choices.
Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.
Use when implementing a feature, fixing a bug, changing behavior, or refactoring code, including ordinary implement/fix/change requests that do not ask for proof. Check the actual acceptance condition and return proportionate evidence by default, or name the…
Create or modify repository guidance through GitHub Copilot CLI, including guidance consumed by Copilot code review. Use when asked to initialize, bootstrap, refresh, reorganize, or generate AGENTS.md, Copilot instructions, path-specific instructions, project…
Use for performing Azure DevOps work — create, inspect, review, discuss, comment on, vote on, or manage pull requests; find, query, create, update, and link Azure Boards work items (including building WIQL queries); parse and route dev.azure.com or…
Drive an Azure DevOps pull request from local changes through completion, including review threads, required policies, conflicts, safe auto-complete, and continued monitoring for new failures. Use when asked to "agent merge" an ADO PR, create an Azure DevOps…
Record agent-driven screen demos and edit video or audio with local FFmpeg. Use for screen recording or desktop capture while computer-use tools drive a workflow; trimming setup or dead time; putting videos side by side; adding captions or subtitles;…
Find mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Use for /correct or…
Catch the user up on what changed in this chat since their last message, in plain words and small visuals. List every item waiting on them with what they need to decide it from the reply alone. Use for /ketchup.
Bring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or properties to describe the code as it is now, rerun, and say whether each failure is drift in…
Apply when writing, changing, reviewing, or keeping tests in any language. Exercise a caller-visible contract and check an independently specified outcome; avoid assertions tied only to mocks, fixtures, constants, or private steps.
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, exhaust variants, derive from authoritative…
Make a task deeper, not bigger, then rewrite the prompt. Use for /sharpen.
Validate pstack snapshots, verification receipts, durable handoffs, or Markdown plans against the plugin's versioned contracts. Use for "validate this pstack artifact", checking pstack JSON, or verifying a pstack plan profile. Not for general JSON schema…
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.
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.
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove…
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 via show-me-your-work. Use for…
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding…
Restate in your own words what you think the user's goals are and what problem they're trying to solve. Use for /in-your-own-words.
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.
Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.
Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.
Apply when integrating a new requirement into an existing design. Redesign as if the requirement had been a foundational assumption from day one, instead of bolting it on.
Apply when sequencing an addition, refactor, or rewrite. Remove dead weight, redundant validators, and stub references first, then build on the simpler base.
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.
Cut AI tells from any writing.
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat,…
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…
Use when writing, reviewing, refactoring, or repairing TypeScript or JavaScript, and when asked to anti-slop, unslop, remove AI-generated slop, fix Anti-Slop findings, improve type precision, replace unsafe assertions, parse unknown data, or avoid lint-shaped…
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', or reviewing a small diff you…
Repository README source: README.md
Read the source README