AI Skills

blast-radius

Find what a change could break somewhere else before it ships, beyond the diff

bro

Restate the last message in plain human language, with no jargon

check-compiler-errors

Run compile and type-check commands and report failures

cli-for-agents

Designs or reviews CLIs so coding agents can run them reliably: non-interactive

continual-learning

Orchestrate continual learning

control-cli

Build or adapt a local harness to drive, inspect

control-ui

Build or adapt a local browser/CDP harness to drive and inspect a web, IDE

create-plugin-scaffold

Create a new Cursor plugin scaffold

create-verification-skill

Generate a project-local verification skill

cursor-sdk

Guide users building apps, scripts, CI pipelines

deslop

Remove AI-generated code slop and clean up code style

docs-canvas

Render a documentation-style Cursor Canvas

figure-it-out

Design an auditable playbook

fix-ci

Find failing PR checks, inspect logs or external check links

fix-merge-conflicts

Resolve merge conflicts non-interactively, validate build and tests

get-pr-comments

Fetch and summarize review comments from the active pull request

loop-on-ci

Monitor PR checks and fix failures until green

maintain-verification-skill

Periodic pass that keeps a project's verification skill

make-pr-easy-to-review

Prepare PRs for review by cleaning noisy history, improving PR descriptions

new-branch-and-pr

Create a fresh branch, complete work, and open a pull request

no-comments

Spawn Comment Sicko, fix accepted findings

orchestrate

Use only when the user explicitly types `/orchestrate `

poteto-mode

Poteto's agent style for concise, detailed responses, deliberate subagents

pr-review-canvas

Generate an interactive PR review walkthrough as an HTML page

principle-attack-the-premise

Apply when two or more fixes that share one premise have failed the same gate

principle-boundary-discipline

Apply when wiring validation, error handling, or framework adapters

principle-build-the-lever

Apply to any non-trivial work, not just bulk work: edits, migrations, analyses

principle-encode-lessons-in-structure

Apply when you catch yourself writing the same instruction a second time

principle-exhaust-the-design-space

Apply when facing a novel UI interaction or architectural decision

principle-experience-first

Apply when product, UX, or feature-scope tradeoffs come up

principle-fix-root-causes

Apply when debugging

principle-foundational-thinking

Apply before writing logic: choosing core types and data structures

principle-guard-the-context-window

Apply when context is filling up: large outputs, long files, repeated reads

principle-laziness-protocol

Apply when refactoring, evaluating diff size, or tempted to add abstractions

principle-make-operations-idempotent

Apply when designing commands, lifecycle steps, or processing loops

principle-migrate-callers-then-delete-legacy-apis

Apply when introducing a new internal API while old callers still exist

principle-minimize-reader-load

Apply when reviewing or shaping code that's hard to trace

principle-model-the-domain

Apply when writing stateful logic

principle-never-block-on-the-human

Apply when tempted to ask 'should I do X?' on reversible work

principle-outcome-oriented-execution

Apply during planned rewrites and migrations with explicit phase boundaries

principle-prove-it-works

Apply after completing a task, before declaring done

principle-redesign-from-first-principles

Apply when integrating a new requirement into an existing design

principle-separate-before-serializing-shared-state

Apply when concurrent actors might write to the same file, branch, key

principle-sequence-verifiable-units

Apply to multi-step work (sweeps, migrations, runs of similar edits)

principle-subtract-before-you-add

Apply when sequencing an addition, refactor, or rewrite

principle-test-behavior-not-implementation

Apply when you write, change, or keep a test

principle-type-system-discipline

Apply when designing types, reviewing a function signature

recall

Reconstruct your recent working context from your own chat history, live state

reflect

Spawn three parallel review subagents over the active transcript

review-and-ship

Review the current branch for bugs, intent fit, and test coverage