Agent Skills Hub

design-references

Provides predefined design system references for UI reviews, including Material Design 3, Apple HIG, Tailwind UI, Ant Design, and Shadcn/ui.

webmcp

Create and test AI-ready MCP tools for any web application. Inject code, automate browser interactions, and turn websites into intelligent agents.

formik-patterns

Formik form handling, validation schemas with Yup, and submission patterns for React applications.

document

Interactive terminal canvas for rendering, editing, and selecting markdown text, emails, and project documentation in Claude Code.

ask-user-question

Implement interactive, step-by-step user input workflows within software agents using the AskUserQuestion tool for guided decision-making and configuration.

react

React component development guide for LobeHub, including styling with antd-style, layout building with @lobehub/ui, and routing management.

Fluxwing Screen Scaffolder

Build complete UI screens by composing multiple uxscii components. Use when you need to create, scaffold, or build .uxm screens like login, dashboard, profile, settings, or checkout pages.

mcp-rails

Implement a full Model Context Protocol (MCP) stack in Rails. Connect to external servers, expose your Rails app as an MCP server, or manage subprocess MCP containers via Docker with OAuth 2.1 PKCE support.

z-card-image

Automated text-to-image rendering engine for social media posts, article covers, and long-form threads. Supports X-style, WeChat, and poster templates with high-precision text formatting and highlights.

fullstack-workflow

A standardized fullstack pattern for Next.js features, integrating GET API routes, server actions, SWR data fetching, and React Hook Form with Zod validation.

vitest-runner

Automated Vitest management skill: handles test execution, coverage reporting, failure diagnosis, and configuration management for TypeScript/JavaScript projects.

browser-debugger

Comprehensive UI testing, visual fidelity analysis, and browser debugging using Chrome DevTools MCP and AI-driven vision models.