wilwaldon writes a curated toolkit of 70+ tools'' skills, plugins, MCP servers, and CLAUDE.md config snippets'' organized by use case to help Claude Code produce better-looking frontend output, covering everything from aesthetic direction and site-wide theming through animation, Figma-to-code pipelines, browser automation testing, and deployment.
- The "essentials" stack for any project is just three commands: the official frontend-design skill, Context7 (live docs), and Playwright MCP
- MCP servers consume ~55k tokens at session start; skills load only ~100 tokens, making them a cheaper way to inject specialized knowledge
- Figma's MCP server now supports "Code to Canvas" (Feb 2026), pushing a running UI back into Figma as editable layers
- The Design Tokens skill derives an entire OKLCH color palette from a single `--brand-hue` number
- The "essentials" stack for any project is just three commands: the official frontend-design skill, Context7 (live docs), and Playwright MCP
- MCP servers consume ~55k tokens at session start; skills load only ~100 tokens, making them a cheaper way to inject specialized knowledge
- Figma's MCP server now supports "Code to Canvas" (Feb 2026), pushing a running UI back into Figma as editable layers
- The Design Tokens skill derives an entire OKLCH color palette from a single `--brand-hue` number
Designlang is a powerful tool designed to extract complete design systems from any live URL using a headless browser. It goes beyond simple color picking by analyzing layout architectures, responsive behaviors across breakpoints, interaction states like hover and focus, and motion languages such as easing and spring physics. The tool generates over 17 different file types including W3C DTCG tokens, Tailwind configurations, shadcn themes, Figma variables, and typed React component stubs to bridge the gap between live websites and development environments.
Key features include:
- Automated extraction of design tokens (primitive, semantic, and composite layers)
- Responsive analysis across multiple viewports
- Interaction state capture for hover, focus, and active transitions
- WCAG accessibility scoring with color remediation suggestions
- Multi-platform support for iOS, Android, Flutter, and WordPress
- Integration as an MCP server for AI coding agents like Cursor and Claude Code
- Design drift detection and visual diffing capabilities
Key features include:
- Automated extraction of design tokens (primitive, semantic, and composite layers)
- Responsive analysis across multiple viewports
- Interaction state capture for hover, focus, and active transitions
- WCAG accessibility scoring with color remediation suggestions
- Multi-platform support for iOS, Android, Flutter, and WordPress
- Integration as an MCP server for AI coding agents like Cursor and Claude Code
- Design drift detection and visual diffing capabilities
Examples for common OpenSandbox use cases. Each subdirectory contains runnable code and documentation. Integrations and sandboxes are available for various tools and services like AI models, desktop environments, and web scraping.
Browser automation CLI for AI agents. Fast Rust CLI with Node.js fallback.
A guide to common pitfalls and best practices when starting with Playwright and Python, covering topics like browser context, waiting strategies, and handling different environments.
>The Playwright MCP Chrome Extension allows you to connect to pages in your existing browser and leverage the state of your default user profile. This means the AI assistant can interact with websites where you're already logged in, using your existing cookies, sessions, and browser state, providing a seamless experience without requiring separate authentication or setup.
This article details how to use Playwright MCP and GitHub Copilot to reproduce and debug web app issues. It covers setup, a sample scenario, and the benefits of this debugging approach.
New release of shot-scraper CLI tool for taking screenshots and scraping web pages with support for HTTP Archive (HAR) files.
Browserbase provides a programmable browser platform that allows developers to automate complex online tasks using code. It offers features like advanced debugging, session recording, a proxy supernetwork, and bot detection avoidance to streamline web automation for compatibility with popular tools like Puppeteer, Playwright, and Selenium. The startup aims to serve as a key building block in an emerging AI software stack.
“It’s not going to be just developers writing this code, it’s going to be large language models generating this code longer term,” Klein explains. “So it’s both developers and LLMs controlling these web browsers to go out and automate the daily tasks we do online.
“It’s not going to be just developers writing this code, it’s going to be large language models generating this code longer term,” Klein explains. “So it’s both developers and LLMs controlling these web browsers to go out and automate the daily tasks we do online.
