builder▌

Build tools that solve your own problems first, then expand to others. \n \n Covers the \"scratch your own itch\" methodology: identifying real pain points, validating with the 10-minute test, and evolving from ugly scripts to reliable tools \n Provides CLI tool stacks for Node.js (Commander, Chalk, Ora, Inquirer) and Python (Click), plus distribution strategies from npm to Homebrew \n Includes local-first architecture patterns using JSON files, SQLite, Electron, Tauri, and PWAs for offline-capa

Design AI agent tools with clear schemas, descriptions, and error handling that prevent hallucination and token waste. \n \n Focuses on JSON Schema best practices and description writing that helps LLMs understand tool intent and constraints, not just implementation details \n Covers tool validation, explicit error handling patterns, and recovery strategies that prevent silent failures and agent loops \n Includes guidance on the Model Context Protocol (MCP) standard for tool interoperability acr

Multi-component React artifacts for Claude with Tailwind CSS and shadcn/ui components. \n \n Scaffolds React 18 + TypeScript projects with Vite, pre-configured Tailwind CSS, and 40+ shadcn/ui components ready to use \n Bundles complete artifacts into single self-contained HTML files with all JavaScript, CSS, and dependencies inlined \n Includes design guidance to avoid common \"AI slop\" patterns like excessive centering, purple gradients, and uniform rounded corners \n Supports state management

Generate complete, runnable web scraper projects using the PageObject pattern with Playwright and TypeScript. This skill produces site-specific scrapers with typed data extraction, Docker deployment, and optional agent-browser integration for automated site analysis.

Build real-time applications with WebSockets and Socket.io.

Build reliable, maintainable integrations with third-party APIs.

Build a minimal but real security policy for sensitive apps. The output is a single, coherent Blue Book document using MUST/SHOULD/CAN language, with explicit assumptions, scope, and security gates.

Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.

Creates production-ready Agent Skills following the official specifications and best practices.

To build powerful frontend claude.ai artifacts, follow these steps: