Cursor

Read this before the first X Money action in a session and again on any X Money error, refusal, or missing capability. Covers the approval rule for every action that moves money (always ask, every time, no exceptions), how the connection works (connection code plus passkey in the X app), how to guide the user through connect, reconnect, and revoke at x.com/i/money/settings/connections, and what each failure message means.

ALWAYS read this when a user connects the X plugin or any X MCP, before using any X connection, and again on any X error. Do not call an X tool until this file has been read in the current turn. On first connect, confirm X tools are available, fetch get_usage_credits BEFORE any user-facing text, then send the congrats + capabilities message. Never tell the user to buy credits until that check returns ~$0 or a job would exceed the balance. If X is connected but tools are missing (tools=0, user-X-* not found), that is a setup failure — not a paywall. For encrypted X Chat / XChat DMs, also read skills/x-chat/SKILL.md. If chat tools or dm.read/dm.write are missing while other X tools work, tell them to reconnect the X plugin. Estimate the cost of every X call before making it and confirm with the user before anything expensive.

Read, summarize, or send encrypted X Chat (XChat) DMs via the X plugin MCP plus local chatxdk / xchat_lite.py. Use when the user mentions X Chat, xchat, encrypted DMs, Chat PIN, juicebox, inbox messages, or wants to reply in X Chat. Not for classic unencrypted DMs, posting tweets, or always-on daemons. If chat tools or dm.read/dm.write are missing, tell them to reconnect the X plugin — do not create an app or ask for Bearer tokens.

Extract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine feedback, personalize workflows, or generate team/person-specific agent guidance.

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, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

Summarize authored commits over a user-specified time period into a concise update

Produce a weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new work

Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE.

Cut AI tells from any writing. Must always apply.

TypeScript best practices. Use when reading or editing any .ts or .tsx file.

Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation. Use only from the configured Benny triage automation.

Launch both thermo-nuclear review subagents in parallel, then synthesize their findings. Use for thermos, double thermo review, or combined bug/security and code-quality branch audits.

Comprehensive security and correctness audit of a branch's changes. Use for thermo nuclear, thermonuclear, or deep review requests, or branch/PR diff audits focused on bugs, breaking changes, security issues, devex regressions, and feature-gate leaks.

Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.

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.

Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.

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.

Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.

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.

Configure which models pstack uses per role and at what reasoning budget. Detects your available models and writes an always-applied rule that overrides the skill defaults. Use for /setup-pstack, "configure pstack models", "pstack budget", or changing pstack's model choices.

Configure Benny and prepare its triage and repro automations. Use when installing Benny or changing its Slack, tracker, repository, routing, control, model, or budget settings.

Run Playwright smoke tests, debug failures, and verify fixes

Evaluate learning progress, identify blockers, and adjust the learning plan

Audit a Cursor plugin for marketplace readiness. Use when validating manifests, component metadata, discovery paths, and submission quality before publishing.

Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.

Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after proof. Use only from the configured Benny repro automation.

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.

Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', 'where did I leave off', before starting or resuming work.

Explain the Ralph Loop plugin, how it works, and available skills. Use when the user asks for help with ralph loop, wants to understand the technique, or needs usage examples.

Start a Ralph Loop for iterative self-referential development. Use when the user asks to run a ralph loop, start an iterative loop, or wants repeated autonomous iteration on a task until completion.

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.

Apply when you write, change, or keep a test. Call the code the way its users do and assert the result they observe against a literal expected value. If the test would still pass when every imported function returns undefined, rewrite the assertion or delete the test.

Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.

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.

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.

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 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.'

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.

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 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 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 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.

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.

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.

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.

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.

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.

Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.

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.

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.

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.

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.

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.

Generate an interactive PR review walkthrough as an HTML page. Fetches PR data via gh API, categorizes files into core vs mechanical changes, adds reviewer annotations, and renders diffs with moved-code detection. Use when the user pastes a GitHub PR URL and asks for a review, walkthrough, or summary, or says "review this PR".

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.

Use only when the user explicitly types `/orchestrate <goal>` to decompose a large task, spawn a tree of parallel cloud-agent workers/subplanners/verifiers via the Cursor SDK, and collect structured handoffs; do not invoke autonomously.

Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.

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

Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".

Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.

Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".

Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.

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.

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 mental models. Use why for motivation.

Build and edit Google Slides through the google-slides MCP tools - slides, grids of cards and columns, text boxes, shapes, images, tables, styling, layout inspection, and per-slide PNG rendering. Use when creating a deck, laying out slide elements, matching a template, or verifying how a slide looks.

Build and edit Google Sheets with the google-sheets tools - values, formatting, charts, conditional formatting, structure, validation, named and protected ranges. Use when creating a spreadsheet or dashboard, formatting cells, adding or fixing charts, or reorganizing tabs and rows.

Author and edit Google Docs with the google-docs tools - structured writing, character and paragraph styling, lists, tables, images, headers/footers. Use when creating a formatted document, editing document content, or applying styles.

Fetch and summarize review comments from the active pull request

Resolve merge conflicts non-interactively, validate build and tests, and finalize conflict resolution

Find failing PR checks, inspect logs or external check links, and apply focused fixes

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 /figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.

Render a documentation-style Cursor Canvas that organizes architecture notes, API references, walkthroughs, and how-tos into a navigable layout with sections, tables of contents, and cross-references. Use when the user asks for a docs canvas, documentation overview, architecture walkthrough, API reference page, or wants to render structured documentation as an interactive canvas.

Remove AI-generated code slop and clean up code style

Use when the user runs /debug-voice, says voice mode has flaws, asks to see or capture what happened in a Grok realtime voice session, or a voice integration has no debug logging yet. Proposes a plan, then installs a dev-only log pipeline (client logger → local NDJSON) in the app's own language and conventions, then runs the fix loop: match the user's report to log signatures, fix one thing, re-test.

Guide users building apps, scripts, CI pipelines, or automations on top of the Cursor TypeScript SDK (`@cursor/sdk`). Use this skill whenever the user mentions integrating, installing, or writing code against the Cursor SDK; whenever they say `Agent.create`, `Agent.prompt`, `Agent.resume`, `agent.send`, `run.stream`, `CursorAgentError`, or `@cursor/sdk`; whenever they ask to run Cursor agents programmatically from a script, CI/CD pipeline, GitHub Action, backend service, or any other code that isn't the Cursor IDE itself; and whenever they want to pick between local and cloud runtime, configure MCP servers for an SDK agent, or handle streaming, cancellation, or errors from an SDK agent. Also trigger when a user is wiring Cursor into an automation, writing a bot that runs Cursor, or porting REST `/v1/agents` calls to the SDK, even if they don't explicitly name the package. Use this eagerly rather than answering from memory; the SDK surface evolves and this skill plus its references are the source of truth for the external package.

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 UI/CLI/service behavior.

Create a new Cursor plugin scaffold with a valid manifest, component directories, and marketplace wiring. Use when starting a new plugin or adding a plugin to a multi-plugin repository.

Build a personalized learning roadmap with milestones and practice checkpoints

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.

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.

Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to `agents-memory-updater`.

Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable errors, idempotency, dry-run, and predictable structure. Use when building a CLI, adding commands, writing --help, or when the user mentions agents, terminals, or automation-friendly CLIs.

Run compile and type-check commands and report failures

Run the full repository compatibility pass: scanner score, startup path, validation loop, and docs reliability.

Cancel an active Ralph Loop. Use when the user wants to stop, cancel, or abort a running ralph loop.

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

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 don't trust.

Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via create-skill + unslop, optionally pulling fresh evidence from recent transcripts.

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.

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.

Advisor mode. Consult a stronger (or different) model at key checkpoints: before major decisions, when stuck on an error, and before declaring a task done. Use when the user types /advisor, asks to turn the advisor on or off, picks an advisor model, or explicitly asks for a second opinion from a stronger or different model. Never enable it on your own.

Use when the user runs /add-voice, types Voice Mode, or asks to add Grok realtime voice to an app, including replacing an STT-LLM-TTS cascade or OpenAI Realtime. Wire speech-to-speech, safe auth, and app mic. Composer: waveform button, mic icon reserved for dictation. For mic-to-text only use /add-dictation; to speak text replies use /add-read-aloud. To add debug logging and fix from logs use /debug-voice.

Use when the user runs /add-read-aloud or wants the app to speak text with Grok text-to-speech: read-aloud button on assistant replies, auto-speak, TTS, voice output, narration, IVR prompts, speech tags, voice_id. For a two-way voice agent use /add-voice. For speech-to-text use /add-dictation.

Use when the user runs /add-dictation or wants speech turned into text with Grok speech-to-text: a mic button that dictates into the composer, live captions, or transcribing recorded audio (files, uploads, URLs) with word timestamps, diarization, subtitles, meeting notes. STT, transcribe, transcription. For a voice agent that talks back use /add-voice.