Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Promote a Factorial Code app's code from its dev workspace to its prod workspace — fcode clone the dev- workspace, remote:add the prod- workspace, pull prod's current metadata, then add and push. Use when releasing, promoting, or deploying a Factorial Code (fcode) app's dev workspace to production, or pushing a dev- workspace's code to its prod- counterpart.
Expert blueprint for racing games including vehicle physics (VehicleBody3D, suspension, friction), checkpoint systems (prevent shortcuts), rubber-banding AI (keep races competitive), drifting mechanics (reduce friction, boost on exit), camera feel (FOV increase with speed, motion blur), and UI (speedometer, lap timer, minimap). Use for arcade racers, kart racing, or realistic sims. Trigger keywords: racing_game, vehicle_physics, checkpoint_system, rubber_banding, drifting_mechanics, camera_feel.
Expert blueprint for rhythm games, including audio synchronization (BPM conductor, latency compensation with AudioServer.get_time_since_last_mix), note highways (scroll speed, timing windows), judgment systems (Perfect/Great/Good/Bad/Miss), scoring with combo multipliers, input processing (lane-based, hold note detection), and chart/beatmap loading. Based on DDR/osu!/Beat Saber research. Trigger keywords: rhythm_game, audio_sync, timing_judgment, note_highway, combo_system, BPM_conductor, latency_compensation.
A comprehensive master guide to app development for 懒猫微服 (Lazycat MicroServer). Trigger when the user makes any request related to 懒猫微服 app development, packaging (lpk), route configuration, deployment parameters, authentication systems (OIDC), or app listing.
Design, implement, and debug MagicBlock applications on Solana. Covers Ephemeral Rollups with delegated state; ER/PER architecture and settlement; private payments and token flows; oracles and randomness; scheduling and temporary authority; security and local validation. Use for MagicBlock product selection, integration, cross-product design, or production troubleshooting
Create formal spec-driven MoonBit APIs and test suites. Use when asked to set up a spec.mbt, spec-driven tests, or a formal contract-first workflow (e.g., "set up a formal spec & test suite for Yaml in MoonBit"), including moon.mod.json/moon.pkg.json scaffolding and guidance to implement in separate files
React and Next.js performance optimization guide from Vercel Engineering (70 rules in 8 categories). Use when writing, reviewing, or refactoring React/Next.js code to eliminate waterfalls, reduce bundle size, prevent re-renders, optimize Server Components, or fix performance bottlenecks. Triggers on data fetching, Promise.all, Suspense, useMemo, dynamic imports, bundle analysis, code-splitting, and rendering performance tasks.
Expert guidance for Satori, the library that converts JSX/HTML and CSS into SVG (the engine behind dynamic Open Graph images and social cards). Use whenever writing or debugging Satori markup e.g. authoring JSX for OG images, choosing CSS that Satori actually supports, fixing layout that renders wrong, embedding fonts, rendering emoji or images, or resolving Satori errors like "Expected length unit" or unsupported property issues. Reach for this any time someone renders HTML/CSS to SVG or PNG with Satori, even if they do not name it.
Use when Godot 4.7 work must run without a mouse or at scale: batch import of hundreds of GLB props or an AI image-to-3D art drop, naming rules, import presets and post-import scripts, editor plugins, EditorScript and @tool, EditorImportPlugin, GUT or gdUnit4 tests in CI, a GitHub Actions export workflow, GDExtension basics, or a Godot MCP server; also when --import is slow, textures stay uncompressed, tests pass locally but CI fails, or an export ships test folders.
Implement, review, and operate Laravel applications involving domains, HTTP, Eloquent, queues, authorization, migrations, and tests. Use when the project contains artisan or laravel/framework and the task involves routes, controllers, models, policies, jobs, commands, events, cache, database, Pest, or PHPUnit; do not use for PHP without Laravel.
Implement Syncfusion Blazor Bullet Chart (SfBulletChart) for KPI and performance visualization. Use this when displaying target vs actual metrics, goal tracking, or performance dashboards. This skill covers actual/target bars, qualitative ranges, and comparative analysis for KPI visualization in Blazor applications.
Zustand state management for React and vanilla JavaScript. Use when creating stores, using selectors, persisting state to localStorage, integrating devtools, or managing global state without Redux complexity. Triggers on zustand, create(), createStore, useStore, persist, devtools, immer middleware.
**ANALYSIS SKILL** — Analyze any repository and generate AI-ready configuration — a canonical AGENTS.md, thin per-tool pointer files, skills, CI workflows, issue templates. WHEN: \"make this repo ai-ready\", \"set up AI config\", \"add copilot instructions\", \"prepare this repo for AI contributions\", \"generate AGENTS.md\". INVOKES: glob, grep, view, create, edit for repo analysis and file generation. FOR SINGLE OPERATIONS: use create/edit directly for individual config files.
Ground the assistant in the target SAP system before any coding work by producing a local system-info.md that captures SID, release, components, detected features, RAP constraints, and ARC-1 lint preset. Use when asked to "set up system context", "bootstrap the SAP system", "create system-info.md", or when starting a session against an unfamiliar SAP system
Chakra UI v3 (React component library) reference. Also known as: Chakra, chakra, chakra-ui. Components (Button, Input, Modal, Drawer, Toast, Menu, Tabs, Tooltip, etc.), layout, forms, overlays, charts, themes, recipes, style props, responsive design, dark mode, and Chakra UI Pro blocks
Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent opinion from Claude, or asks to delegate a well-scoped task to Claude. Supports selecting `--model` and thinking/effort level with defaults of the current `opus` alias and `high`.
Deploy Next.js to Cloudflare Workers via the OpenNext adapter (@opennextjs/cloudflare). Use for SSR/ISR/SSG/App or Pages Router, getCloudflareContext, bindings (D1/R2/KV/AI/Hyperdrive), caching tiers, skew protection, multi-worker, custom worker, env vars, or worker size/runtime/keep_names/FinalizationRegistry/connection-scoping errors.
Generates comprehensive documentation templates for open-source and internal projects including README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT, LICENSE, and other standard docs with suggested sections and best practices. Use when users request "create project docs", "add OSS documentation", "setup standard docs", or "make it open-source ready".
Generate a complete RAP OData UI service from a natural-language business object description — table, CDS views, behavior definitions, metadata extension, service definition, and behavior pool class. Use when asked to “create a RAP service for X”, “scaffold a RAP UI”, “build a Fiori RAP app”, or “generate the RAP stack from scratch”
Generate OpenAPI documentation from source code. Analyzes repository to automatically discover API endpoints and create swagger.json and interactive HTML documentation. Use when generating API docs, creating OpenAPI specs, documenting REST APIs, or analyzing API endpoints.
Graph engineering for parallel task execution: convert a task, PRD, SPEC, or issue set into a dependency graph (DAG), layer it into supersteps, then implement each independent node concurrently with subagents — each node runs /goal → /review-it → /ship-it in an isolated git worktree, with a fan-in barrier between waves. Triggers on: graph, graph engineering, build a graph, task graph, dependency graph, DAG, parallel implement, 并发实现, 并行实现, 任务图, 把任务变成图, fan-out fan-in, superstep, dynamic workflow
Covers Stimulus controller fundamentals: lifecycle hooks, values and valueChanged callbacks, targets and target callbacks, outlets, action parameters, keyboard events, and controller architecture patterns. Prefer this skill when the request is primarily about Stimulus APIs and controller design independent of a specific Hotwire domain. Use hwc-forms-validation for form-specific workflows, hwc-navigation-content for Turbo navigation concerns, hwc-realtime-streaming for Turbo Streams/WebSocket patterns, hwc-media-content for media integrations, and hwc-ux-feedback for loading, progress, or transition UX patterns.
Optimizes CI pipelines for monorepos by detecting affected packages/apps and running only necessary builds and tests. Includes Turborepo/Nx strategies, caching, and parallel execution. Use for "monorepo CI", "affected detection", "incremental builds", or "workspace optimization"
Interactively collect and validate the parameters for a Uniswap v4 Permissioned Pool setup - chain, underlying token, allowlist checker, adapter owner, verification deposit, the four wrapper registrations, hook, and pool pricing - and emit the JSON config the deployer skill consumes. Use when the user says "configure a permissioned pool", "permissioned pool config", "adapter parameters", "permissioned pool setup parameters", "PermissionsAdapter configuration", or asks to set up parameters for a permissioned pool before deploying. Covers contract mechanics only - does not constitute legal, financial, investment, tax, or compliance advice, and is not a compliance review.
Reference guide for engineering teams setting up a Uniswap v4 Permissioned Pool for a transfer-restricted (RWA / tokenized-asset) ERC-20. Use when the user says "permissioned pool", "PermissionsAdapter", "PermissionsAdapterFactory", "PermissionedPositionManager", "PermissionedHooks", "allowlist checker", "BaseAllowlistChecker", "adapter verification", "verifyPermissionsAdapter", "updateAllowedWrapper", "setAllowedHook", "unwindPosition", "wrap a permissioned token for v4", or asks how an RWA issuer lists a restricted token on Uniswap v4. Explains the contract architecture, the ordered setup journey, the code-enforced ordering, and the trust model. Covers contract mechanics only - does not constitute legal, financial, investment, tax, or compliance advice, and is not a compliance review
This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.
Quicknode blockchain infrastructure for 80+ chains: Core RPC API, Streams, Webhooks, Blazar WSS, Solana gRPC, HyperCore gRPC, SQL Explorer, Metaplex DAS API, Blockbook, Ordinals & Runes API, Swap API, x402, MPP, Agent Subscriptions, CLI, and MCP. Use for any Quicknode product, blockchain data access, or wallet-paid agent access.
Automates releases and package publishing with changesets or semantic-release. Handles versioning, changelog generation, git tags, and release notes. Use for "release automation", "semantic versioning", "package publishing", or "changelog generation".
Review what actually changed—in a transport or in your unactivated drafts—by diffing each object's source and summarizing the change set with optional impact and quality signals. Produces a reviewable report (per-object unified diffs + risk flags), not a raw object dump. Use when asked to “review this transport”, “what changed in TR X”, “diff the objects in a transport”, “show my pending changes before I activate/release”, “prepare a transport/change review”, or “what am I about to ship”.
Use when adding or fixing sound in Godot 4.7: audio buses and effects, volume sliders, 'too many sounds', combat audio with hundreds of enemies, sounds clipping or distorting, 3D sound too quiet or not panning, reverb zones not working, occlusion, adaptive or interactive music (AudioStreamInteractive, layers, stingers), music loops with gaps, SFX that repeat, AudioStreamRandomizer, AudioStreamGenerator, import settings, or importing AI-generated music, SFX and voice from Scenario or ElevenLabs.
Expert patterns for Shopify app development including Remix/React Router apps, embedded apps with App Bridge, webhook handling, GraphQL Admin API, Polaris components, billing, and app extensions. Use when: shopify app, shopify, embedded app, polaris, app bridge.
Review a diff, PR, branch, or path against the Sliced Bread architecture rules: dependency direction, crust integrity, model purity, growth justification, and event usage. Use when the user asks for an architecture review, says "check this against sliced bread", "review the slice boundaries", "is this import allowed", or before merging changes that add directories, abstractions, or cross-slice imports. Do NOT use for general bug-hunting or a full repo audit — this reviews a bounded change set.
Software design philosophy guide based on John Ousterhout's "A Philosophy of Software Design." Use this skill during code reviews, architecture discussions, API design, module decomposition decisions, refactoring guidance, complexity analysis, naming and commenting improvements, and error handling strategy design. Trigger when the user mentions "code is too complex", "how to split modules", "interface design", "reduce coupling", "deep/shallow modules", "information leakage", "error handling", "code readability", "design philosophy", "pull complexity down", "define errors out of existence", or similar topics. Also trigger for any code review where design quality feedback is requested
Standardizes UX states for data fetching flows (loading, error, empty, success) and complex multi-view UI patterns. Provides state machine approach recommendations, loading skeletons, error boundaries, and empty state components. Use when implementing "loading states", "error handling", "empty states", or "state machines".
Implements the Syncfusion Blazor Chart Wizard for guided chart creation. Use this when building interactive chart builders that require step-by-step configuration, data binding, and export features. Covers chart customization, theming, and accessibility.
Set up, launch and drive a Decentraland Explorer through its MCP automation server to build and test a local SDK7 scene in-world: screenshot, walk, click and debug the running scene. Use when the user asks to see, test, verify, walk through, screenshot, or debug a scene in-world; when they name the Explorer or its MCP server; when they want the Explorer MCP installed, set up or connected; whenever an `mcp__explorer__*` tool is available; and whenever the `explorer` MCP server failed to connect or was never set up at all — ConnectionRefused, or no such server, only means the Explorer is not running yet, which is this skill's normal starting point, not a reason to skip it.
Call use_skill as your FIRST and ONLY action when the user asks to EDIT, UPDATE, MODIFY, or CHANGE an EXISTING run configuration for Mule applications. Use this ONLY for modifying configurations that already exist, NOT for creating new ones. Trigger phrases include “edit config”, “update config”, “modify config”, “change config”. When you call use_skill, it must be the only tool call in that response.
Plans safe API evolution with versioning strategies, client migration guides, deprecation timelines, and backward compatibility considerations. Use for "API versioning", "deprecation planning", "API evolution", or "breaking changes".
Implements secure authentication patterns including login/registration, session management, JWT tokens, password hashing, cookie settings, and CSRF protection. Provides auth routes, middleware, security configurations, and threat model documentation. Use when building "authentication", "login system", "JWT auth", or "session management".
Call use_skill as your FIRST and ONLY action when the user asks to DELETE, REMOVE, or GET RID OF an existing run configuration for Mule applications. Use this ONLY for deleting/removing configurations, NOT for creating or editing. Trigger phrases include "delete config", "remove config", "get rid of config", "delete all configs", "remove all my run configs", "clean up configs". When you call use_skill, it must be the only tool call in that response.
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.