Skills
97,905 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Audit macOS app release readiness including app bundle identity, signing, notarization, sandboxing, hardened runtime, permissions, keychain, app support data, launch agents, login items, menu bar, Dock behavior, file associations, universal builds, auto-update, crash logs, backup, uninstall, and support diagnostics. Use when shipping or reviewing macOS desktop apps and utilities.
Decide where code goes and which direction it points: where a new module belongs, whether a dependency may flow that way, what stays behind a boundary, whether an abstraction has been earned yet, and when a long flow should stay in one piece. Covers investigating before changing, proving a technical unknown before choosing the placement, keeping effects and dependencies explicit, and recording the compromise when existing architecture forces one. Use when the user says "where should this live", "is this the right structure", "should I split this", "this file is doing too much", or "clean this up", and when code hides I/O, passes a broad context object, hardcodes one caller into a generic mechanism, or grows a second architecture beside the first. Not for judging a change that already exists, and not for language-specific idiom. Structure chosen while a technical unknown is still open is a guess wearing the costume of design.
Use when creating or iterating on a project after the Make App requirements proposal is confirmed. Decide whether to generate the My Approvals navigation by default based on business entry, edit-and-save, or approval-processing capabilities. Also covers BPM, bpmDefinitionKey, approval creation fields, save and submit, submit and save, process status, and approval tags in detail titles. Handles generation conditions, runtime initiation configuration, saving and first initiation, and status display in business lists and details. Does not cover cancel/recall, installing the My Approvals npm package or implementing the task center, approval processing, approval history, the process designer, or Console approval management.
Indie maker playbook for bootstrapped apps inspired by Pieter Levels' MAKE: The Indie Maker Blueprint. Use when a user is starting or sizing an app idea, choosing what to build next, building a minimal product, preparing a launch, diagnosing stalled growth, deciding pricing or monetization, automating operations, maintaining a per-app MAKE.md tracker, or evaluating whether to sell a product.
A guide to verifying the Mastra framework's APIs, exploring the latest documentation and migrating versions. Use it to confirm current specifications before writing Mastra code, validate API signatures, build agent / workflow / tool / memory / RAG, and migrate such as from v0.x to v1.x. Treat internal knowledge as outdated assumptions and always verify against the type definitions of the installed version or the official documentation. For design decisions such as separation of responsibilities, use mastra-ai-architecture-rules.
Use when the user wants to use Arduino sensors or peripherals from MATLAB that are not directly supported by the MATLAB Support Package for Arduino Hardware. Triggers on requests to create, wrap, or expose a custom Arduino library to MATLAB. Also triggers on indirect questions like "How do I read humidity in MATLAB?" or "How do I display text on an LCD from MATLAB?" where the answer requires a custom Arduino add-on library. Covers: custom addon creation, third-party Arduino library integration, LibraryBase class, C++ header files, DependentLibraries, arduinoioaddons namespace, I2C/SPI/GPIO peripheral wrappers.
Guide authoring of Audio Toolbox plugins (audioPlugin, audioPluginSource) that pass validateAudioPlugin and generate deployable VST/AU code. Use when creating audio effect or generator plugins, writing classdef files inheriting from audioPlugin, or troubleshooting validateAudioPlugin failures.
MatrixScan AR (Barcode AR, BarcodeAr) in React Native projects — scanning multiple barcodes at once with AR overlays, highlights, and annotations on tracked barcodes. Use for integration, symbology configuration, highlight and annotation providers, session handling, feedback, migration from BarcodeBatch, or troubleshooting.
MatrixScan Batch (MatrixScan, BarcodeBatch, legacy BarcodeTracking) in React Native projects — tracking and scanning multiple barcodes at once. Use for integration, settings and symbologies, tracked-barcode handling, per-barcode brushes, advanced-overlay AR annotations, tap handling, manual feedback, lifecycle, third-party scanner replacement, or troubleshooting.
Guidance for implementing tap, swipe, pan, pinch, drag-and-drop, and pointer gesture recognizers in .NET MAUI applications. Covers XAML and C# usage, combining gestures, and platform differences. USE FOR: "tap gesture", "swipe gesture", "pan gesture", "pinch gesture", "drag and drop", "pointer gesture", "gesture recognizer", "TapGestureRecognizer", "SwipeGestureRecognizer", "PanGestureRecognizer", "combine gestures". DO NOT USE FOR: animations triggered by gestures (use maui-animations), CollectionView swipe actions (use maui-collectionview), or custom drawing interaction (use maui-graphics-drawing).
Add SQLite local database storage to .NET MAUI apps using sqlite-net-pcl. Covers data models with ORM attributes, async database service with lazy init, DI registration, WAL mode, and file management. Works with any UI pattern (XAML/MVVM, C# Markup, MauiReactor). USE FOR: "SQLite database", "local database", "sqlite-net-pcl", "offline storage", "CRUD database", "database service", "WAL mode", "CreateTableAsync", "local data persistence", "ORM attributes". DO NOT USE FOR: REST API data fetching (use maui-rest-api), secure credential storage (use maui-secure-storage), or file picking (use maui-file-handling).
Create software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams, sequence diagrams, flowcharts, ERDs, C4 architecture diagrams, state diagrams, git graphs, and other diagram types. Triggers include requests to diagram, visualize, model, map out, or show the flow of a system.
Download and convert AI models using the Model Download microservice. Use this skill whenever a user wants to download a model from HuggingFace, Ollama, Ultralytics, Geti, or Pipeline Zoo; convert a model to OpenVINO IR format for OVMS; download healthcare AI models (3D Pose, rPPG, AI-ECG) via the HLS plugin; set up the model download service; submit a download or conversion job via the REST API or the MCP server; connect an MCP client (Claude Desktop, Copilot) to model-download; or asks, “How do I get model X working with OVMS?” Also trigger on phrases like “download model,” “download weights,” “convert to int4,” “OVMS-ready model,” “prepare model for inference,” and “model-download MCP server.”
Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting Code node errors, or choosing between Code node modes.
Configures TypeScript for Node libraries and apps - strict tsconfig, module and moduleResolution choices, verbatimModuleSyntax, isolatedDeclarations, declaration emit. Use when the user asks to set up TypeScript, tighten tsconfig, add a tsc type-check step that fails the build, or fix declaration output. Not for lint rules, bundling, or package exports.
Create maintainer-friendly pull requests for open source projects with clean code submissions and professional communication. Prevents 16 common mistakes that cause PR rejection. Use when: contributing to public repositories, submitting PRs to community projects, migrating from contributor to maintainer workflows, or troubleshooting PR rejection, working on main branch errors, failing CI checks, or personal artifacts in commits.
When the user wants to combine machine learning with optimization, use ML predictions in optimization models, or integrate AI with mathematical programming. Also use when the user mentions "ML-optimization hybrid," "predict-then-optimize," "learning-augmented optimization," "neural network in optimization," "end-to-end learning," or "ML for optimization parameters." For pure optimization, see optimization-modeling. For pure ML, see ml-supply-chain.
Full lifecycle management skill for dbmate migrations. Handles status checks, up, down, and creating new migrations. Triggered by keywords such as "run migration", "DB up", "DB down", "migration status", "create migration", "dbmate", "migration", "apply table changes", "apply schema", "DB rollback". Use this skill for any request related to DB migrations.
Full workflow skill for Mermaid ERD. One-stop handling from installing MCP → generating mmd → browser preview → saving PNG/SVG. Triggered by keywords such as "update ERD", "preview ERD", "save ERD", "draw an ERD", "add table", "change relationship", "visualize DB design", "add column to ERD", "edit erd.mmd". Use this skill when the intent is to visualize a DB schema or table structure.
Only use when the user explicitly invokes /plan-explain (or $plan-explain in Codex). Never auto-invoke. Reads a plan file such as those under `.sisyphus/plans/` and generates a structured summary report so a human can immediately grasp what that plan does. It only extracts facts and performs no interpretation, speculation or additional investigation.
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).
Only use when the user explicitly invokes /pr (or $pr in Codex). Never auto-invoke. Safely performs the whole sequence of Git operations from creating a feature branch to staging, committing, pushing and creating a Pull Request, while complying with branch rules (prefer develop, no direct commits to protected branches).
Only use when the user explicitly invokes /pr-stage (or $pr-stage in Codex). Never auto-invoke. Commits only changes that are already staged (already git added) and, if needed, goes as far as creating a feature branch, pushing and creating a PR. The authoritative procedures and safety guards live in the pr skill; this skill defines only the difference (it handles staged changes only) and is a thin wrapper.
Multi-turn PRD (Product Requirements Document) creation assistant. Asks clarifying questions one at a time to gather requirements, then generates a complete, professional PRD. Use when starting a new feature, product, or project. Triggers on 'write PRD', 'create PRD', 'new feature', 'product requirements', or '/prd'.
Only use when the user explicitly invokes /pre-define (or $pre-define in Codex). Never auto-invoke. A skill for refining a user's vague request into concrete input that can be handed to detailed requirements definition (/define). It does not make specification decisions or define requirements itself; it investigates related existing specifications and asks simple questions repeatedly, aiming to eliminate miscommunication.
Create premium, Awwwards-quality website designs as React (.jsx) components that look like they were built by a top-tier agency charging $50k+ per project. Use this skill whenever the user asks for a website, landing page, portfolio, or web component that should look expensive, premium, luxury, editorial, high-end, or agency-quality. Also trigger when the user mentions Awwwards, FWA, award-winning design, or references brands like Apple, Aesop, Bottega Veneta, Stripe, or any luxury/fashion/design-forward brand. Trigger when the user says things like "make it look professional", "make it look expensive", "I want it to look really good", "high quality design", "not generic", or expresses dissatisfaction with typical AI-generated website aesthetics. Do NOT trigger for dashboards, admin panels, internal tools, or functional UI where aesthetics are secondary to utility — the standard frontend-design skill handles those.
This skill should be used when the user asks to "install proto", "configure proto", "manage tool versions", "pin versions", "set up .prototools", "install node version", "install rust version", "install python version", "proto plugins", or mentions proto commands, .prototools file, or multi-language version management.
Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.