Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Guide for writing MoonBit bindings to C libraries using native FFI. Use when adding extern "c" declarations, writing C stubs with moonbit.h, configuring native-stub and link.native in moon.pkg, choosing #borrow/#owned ownership annotations, designing callback trampolines, wrapping C pointers with external objects and finalizers, converting strings across FFI, or validating bindings with AddressSanitizer.
Fast, accurate, and comprehensive multiline text measurement and layout library for JavaScript/TypeScript — without DOM reflow. Use when the user needs to calculate paragraph heights, line counts, manual line layouts (text flowing around floated images), or rich text rendering (emoji, CJK, RTL) on DOM, Canvas, or SVG targets. Covers npm install, core API (prepare/layout, prepareWithSegments/layoutWithLines), and options (whiteSpace, wordBreak, letterSpacing). Triggers on: pretext, text measurement, text layout, paragraph height, line layout, text reflow, canvas text measurement, DOM reflow
Develop or review put.io end-user apps and shared frontend packages: UI, state, tests, docs, test harnesses, delivery, and frontend machine setup. Use in a put.io frontend repository or for put.io frontend conventions. Not for unrelated frontend work, browser-only put.io inspection, SDK or API client work, or putio CLI consumer operations; frontend test-harness auth setup stays in scope.
Use when building a 2D game in Godot 4.7: make a platformer or top-down controller that feels right (coyote time, jump buffer, jump height), TileMapLayer and TileSet in code, terrains and autotiles that pick wrong tiles, a dual grid, a camera that jitters or stutters, pixel art that looks blurry or uneven, stretch and integer scaling, 2D lights and shadows, y-sort order wrong, parallax gaps, or importing AI-generated sprites and tilesets from Scenario.
Write and debug Tampermonkey userscripts—scripts that change or automate a website from inside the browser. Use when the user wants a userscript (Tampermonkey, Greasemonkey or Violentmonkey), wants JavaScript or CSS injected into a site they visit, wants page elements hidden or rearranged, wants a form auto-filled or page data scraped, needs to react to URL changes in a single-page app, needs cross-origin requests from a page script, has a userscript that does not run, or is setting one up in TypeScript. Do NOT use for Selenium, Puppeteer or Playwright automation—use a browser-automation tool; for building a browser extension (WebExtensions/Manifest V3), write it as an extension; or for server-side scripts.
Scores and prioritizes technical debt by impact, risk, and effort. Provides ranked backlog with ROI analysis and quarterly paydown recommendations. Use for "tech debt", "technical debt management", "code quality", or "refactoring priorities".
Add a custom in-app product tour (spotlight onboarding overlay) without a library (no joyride/intro.js/driver.js). Draw a dark layer with spotlight cutouts around elements selected by CSS selector, attach labeled tooltips, and place a “tap to close” pill in the largest empty space. Responsive on mobile and desktop, locks scrolling, measures with getBoundingClientRect, and closes on any click. Use when the user wants to “add a tour guide,” “onboarding tour,” “in-app guide,” “spotlight tour,” “product tour,” “walkthrough,” “bonbon-style tour,” or invokes /tour-guide. Suited to React/Next.js + Tailwind. Each route defines its own list of stops (spots); elements are marked with a stable data-tour attribute.
Expert API architect specializing in RESTful API design, GraphQL, gRPC, and API security. Deep expertise in OpenAPI 3.1, authentication patterns (OAuth2, JWT), rate limiting, pagination, and OWASP API Security Top 10. Use when designing scalable APIs, implementing API gateways, or securing API endpoints.
This skill should be used when working on Bevy game engine projects. It provides specialized knowledge for Bevy's Entity Component System (ECS) architecture, component-driven design patterns, system ordering, UI development, build strategies, and common pitfalls. Use this skill when implementing game features, debugging Bevy code, designing component architectures, or working with Bevy's UI system.
Creates a DevOps Center WorkItem to track a fix for a test failure or Code Analyzer violation. Before creating anything, it shows a subject/assignee/project preview and requires explicit confirmation. Use this skill when you want to create a fix work item, track a remediation task, or assign a test or analysis failure to a developer. TRIGGER when: the user wants to create a fix work item, log a remediation, or assign a failure to a developer for resolution. DO NOT TRIGGER when: writing the fix code itself (use generating-apex).
DeepWorkPlan — turn any repo AI-first and run Deep Work Plans. Routes to create, execute, refine, resume, status, verify, upgrade, and repo-onboarding sub-skills based on intent. Use when the developer wants to plan, execute, manage, or verify structured multi-task work, or make a repository AI-agent-ready.
Emil Kowalski's design engineering skills. Creator of Sonner, Vaul, and animations.dev. Covers the animation decision framework, custom easing curves, component interaction principles, and typography rules, plus skills to review, audit, and improve motion, performance, and native-feeling mobile web UI.
Expert blueprint for fighting games including frame data (startup/active/recovery frames, advantage on hit/block), hitbox/hurtbox systems, input buffering (5-10 frames), motion input detection (QCF, DP), combo systems (damage scaling, cancel hierarchy), character states (idle/attacking/hitstun/blockstun), and rollback netcode. Based on FGC competitive design. Trigger keywords: fighting_game, frame_data, hitbox_hurtbox, input_buffer, motion_inputs, combo_system, rollback_netcode, cancel_system, advantage_frames.
Expert blueprint for MOBA games including lane logic (minion wave spawning every 30s), tower aggro priority (hero attacking ally over minion over hero), click-to-move controls (RTS-style raycasting), hero ability systems (QWER cooldowns, mana cost), fog of war (SubViewport projections), and authoritative networking (server validates damage). Use for competitive 5v5 or arena games. Trigger keywords: MOBA, lane_manager, minion_waves, tower_aggro, click_to_move, ability_cooldowns, fog_of_war, comeback_mechanics.
Optimizes hot module replacement and fast refresh for development speed with Vite, Next.js, and webpack configurations. Use when users request "hot reload", "HMR optimization", "fast refresh", "dev server speed", or "development performance".
Provide production-ready shell script templates for common Linux system administration tasks including backups, monitoring, user management, log analysis, and automation. These scripts serve as building blocks for security operations and penetration testing environments.
Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.
Primes the agent with deep codebase understanding by analyzing structure, documentation, and key files. Use when starting work on a codebase, at the beginning of a session, or when you need a fast orientation before planning or implementing. Optionally pulls external task context from Jira issues and Confluence pages first.
Complete guide to React and Next.js best practices covering performance optimization, component architecture, shadcn/ui patterns, Motion animations, and modern React 19+ patterns. Use when writing, reviewing, or refactoring React/Next.js code. Triggers on tasks involving React components, Next.js pages, data fetching, UI components, animations, or code quality improvements. Scope is client-side React/Next — for Node/Express/API backend, use backend-patterns; for cross-cutting TS/JS standards, coding-standards.
Implements TanStack Query (React Query) for server state management, with caching, mutations, optimistic updates, and infinite queries. Use when users request “react query,” “tanstack query,” “data fetching,” “cache management,” or “server state.”
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the Task tool for architecturally enforced context isolation. Supports Jest, Vitest, pytest, Go test, cargo test, PHPUnit, and RSpec.
Build terminal user interface (TUI) applications with the Textual framework. Use when creating new Textual apps, adding screens/widgets, styling with TCSS, handling events and reactivity, testing TUI apps, or any task involving "textual", "TUI", or terminal-based Python applications.
Step-by-step guide for setting up Better Auth authentication with Convex and TanStack Start. Use this skill when configuring authentication in a Convex + TanStack Start project, troubleshooting auth issues, or implementing sign up/sign in/sign out flows. Covers installation, environment variables, SSR authentication, route handlers, and the expectAuth pattern.
Effect-TS library usage in TypeScript — Effect.gen generators, Schema.Struct/Schema.Class definitions, Layer/Context.Tag/Service patterns, Effect.pipe pipelines, Data.TaggedError/Data.Class error types, Ref/Queue/PubSub/Deferred concurrency primitives, Match module, Config providers, Scope/Exit/Cause/Runtime patterns, or any code using Effect's typed error channel (E parameter). Trigger when writing, reviewing, debugging, or refactoring TypeScript code that uses Effect — when you see imports from `effect`, `effect/*`, or any `@effect/*` scoped package (schema, platform, sql, opentelemetry, cli, cluster, rpc, vitest). Also trigger when the user asks about Effect patterns, migration from Promises/fp-ts/neverthrow to Effect, or how to structure an Effect application. Do NOT trigger for React's useEffect, Redux side effects, or general English usage of "effect" unless the context clearly involves the Effect-TS library.
Pick up bugs a human flagged by pointing at them in the running app, each arriving with the element, the note they typed, and the source file and line. Use when the user says they marked or flagged something, when starting a session on an app someone has been clicking through, when a designer or PM has left feedback in the UI, or when the user describes a problem as “that button there” without saying which file.
Expert patterns for simplifying 3D games to 2D including dimension reduction strategies, 2.5D fake-depth, isometric ports, camera flattening, physics conversion, 3D-to-sprite art pipeline, and control simplification. Use when porting 3D to 2D, building 2.5D / isometric / fake-depth gameplay, creating 2D versions for mobile, or prototyping. Trigger keywords: CharacterBody3D to CharacterBody2D, Camera3D to Camera2D, Vector3 to Vector2, flatten Z-axis, 2.5D, isometric, fake depth, Y-sort, simulated Z, orthogonal projection, 3D to sprite conversion, performance optimization.
Expert patterns for scaling mobile games to desktop including mouse/keyboard controls, increased resolution and graphical fidelity, expanded UI layouts, settings menus, window management, and platform-specific features. Use when creating desktop ports or cross-platform releases. Trigger keywords: mouse_controls, keyboard_shortcuts, resolution_scaling, graphics_settings, fullscreen_toggle, window_modes, Steam_integration, desktop_optimization.
Implement cheat codes, hidden interactions, and unlockable meta-content via time-windowed input sequence buffers, spam thresholds, look-at (dot-product) detectors, progress-% unlocks, and meta persistence in user://secrets.cfg. Use when adding Konami-style codes, curiosity spam eggs, glimmer cues, lockout anti-brute-force, or gallery flags that must survive slot deletes. Keywords: Konami, sequence buffer, meta secrets.cfg, visibility detector, lockout, glimmer, spam threshold, progress unlock.
Run [implement-spec](../implement-spec/SKILL.md) with Codex handling the implementation passes while you orchestrate, integrate, and review. Use when the user asks to implement a spec with Codex or run implement-spec with Codex as the implementer.
This skill should be used when the user asks to "create bash scripts", "automate Linux tasks", "monitor system resources", "backup files", "manage users", or "write production shell scripts". It provides ready-to-use shell script templates for system administration
Operate LM Studio's `lms` CLI and local/remote LM Studio servers for model discovery, server status checks, model loading, endpoint smoke tests, and downstream OpenAI-compatible wiring. Use when the user mentions LM Studio, `lms`, a local model server, `/v1/models`, a remote LM Studio host, or wants to connect another tool to LM Studio; even if they only ask to test a local OpenAI-compatible endpoint or choose the correct loaded-model identifier. Triggers on: lmstudio, lm studio, lms, local model server, LM Studio API, LM Studio endpoint, /v1/models, connect Strix to LM Studio, load model in LM Studio.
Use when migrating a MAX model from the V2 graph API (max.nn, TensorValue, explicit Graph construction) to ModuleV3 (max.experimental.nn, Tensor, F.lazy() + compile()). Triggers on: "migrate to ModuleV3", "port a max.nn model to max.experimental", "convert TensorValue to Tensor", "update my model to the V3 API", "ModuleV3 migration". Workflow: read the concept map, rewrite imports and __call__ signatures, and replace graph building with compile(weights=...). Align weight names with the new module hierarchy and move the KV cache unflatten into forward(). Port sharding to a DeviceMesh when the V2 model is sharded, then verify greedy outputs match the V2 implementation.
Creates a comprehensive, context-rich implementation plan through deep codebase analysis, a short clarifying interview, and external research. Accepts a tracker ticket (a Jira/Linear/GitHub key or URL, fetched from the tracker) or a free-form feature request. Use when you have a ticket or feature and need a one-pass-ready plan before writing any code.
Rust best practices and code quality guidelines for writing idiomatic, safe, and performant Rust code. Use when writing, reviewing, or refactoring Rust code. Triggers on tasks involving Rust programming, code review, error handling, type safety, or performance optimization.
Use when lighting or rendering a Godot 4.7 3D scene: pick a renderer (Forward+, Mobile, Compatibility), choose GI (SDFGI, VoxelGI, LightmapGI, reflection probes), bake lightmaps without a mouse, tune WorldEnvironment, tonemapper (AgX, ACES, Filmic), glow, fog, volumetric fog and god rays, shadows and shadow acne, quality presets for PC and phones, Compositor post effects, or when 'my scene looks flat', 'too dark indoors', 'light leaks', 'lightmap is black', 'looks different on mobile'.
Complete reference for all SGDS web components, including installation and framework integration. Use when users ask about any <sgds-*> component: accordion, alert, badge, breadcrumb, button, card, checkbox, close-button, combo-box, data-table, datepicker, description-list, divider, drawer, dropdown, file-upload, footer, icon, icon-button, icon-card, icon-list, image-card, input, link, mainnav, masthead, modal, overflow-menu, pagination, progress-bar, quantity-toggle, radio, select, sidebar, sidenav, skeleton, spinner, stepper, subnav, switch, system-banner, tab, table, table-of-contents, textarea, thumbnail-card, toast, or tooltip. Also covers React 19+, React ≤18, Vue, Angular, and Next.js integration.
Sets up vector databases for semantic search, including Pinecone, Chroma, pgvector, and Qdrant, with embedding generation and similarity search. Use when users request “vector database,” “semantic search,” “embeddings storage,” “Pinecone setup,” or “similarity search.”
Writes and reviews Swift code for background execution on Apple platforms - BGTaskScheduler (app refresh, processing, continued processing), beginBackgroundTask assertions, background URLSession downloads/uploads, silent and VoIP push, background modes (audio, location, BLE), the SwiftUI .backgroundTask modifier, and macOS schedulers. Use when scheduling deferred work, finishing work after the app backgrounds, transferring files in the background, waking the app via push, or debugging background tasks that never run
Centrifugo real-time messaging server expert for WebSocket PUB/SUB, channel management, JWT authentication, event proxying, and horizontal scaling with Redis/NATS. Use when: centrifugo, centrifugal, real-time messaging, websocket pubsub, channel subscriptions, real-time notifications, live updates, presence, history recovery, server-sent events integration, real-time transport layer. Do not use for: general WebSocket programming without Centrifugo, Socket.IO, Pusher SDK, or other real-time frameworks
CesiumJS interaction and picking - ScreenSpaceEventHandler, multi-key KeyboardEventModifier input actions, Scene.pick, Scene.drillPick, Scene.pickPosition, Scene.snap edge snapping (1.144), mouse and touch events. Use when handling user clicks on the globe, selecting entities or 3D Tiles features, registering modifier-key shortcuts, implementing hover effects, snapping to model edges for measurement, or building drag-based interactions
CUDA kernel development, debugging, and performance optimization for Claude Code. Use when writing, debugging, or optimizing CUDA code, GPU kernels, or parallel algorithms. Covers non-interactive profiling with nsys/ncu, debugging with cuda-gdb/compute-sanitizer, binary inspection with cuobjdump, and performance analysis workflows. Triggers on CUDA, GPU programming, kernel optimization, nsys, ncu, cuda-gdb, compute-sanitizer, PTX, GPU profiling, and parallel performance.
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.