thedaviddias/Front-End-Checklist
Front-End Checklist is an open-source quality system for modern web development, offering comprehensive best practices for humans and AI agents.
Awesome AI Agents › MCP Server Framework
intellectronica/skillz
Skillz makes Anthropic-style Agent Skills usable outside the assistants that support them natively. It runs as an MCP server built on FastMCP, scans a skills root directory, and turns every skill it finds into a tool that any MCP client, such as Codex, GitHub Copilot or Cursor, can call. A skill is a folder or archive containing a SKILL.md file with YAML front matter; the server publishes the authored instructions, offers the remaining files as downloadable resources for the agent, and can execute bundled helper scripts. The skills root defaults to ~/.skillz and can be overridden with a positional argument. Its layout is more permissive than Claude Code''s, allowing nested subdirectories and skills packaged as .zip or .skill archives, and the README explains which flat layout to keep if one directory must be shared or symlinked between both tools. The command line accepts stdio, HTTP or SSE transports with host, port and path options, a --list-skills flag to check what will be exposed before wiring the server into an agent, and verbose or file logging. Installation is typically through uvx from PyPI, and a Docker image is published so the skills directory can be mounted into an isolated container; a companion Gemini CLI extension exists for that runtime. The author labels the project an experimental proof of concept and warns explicitly that skills should be treated as untrusted code and run in a sandbox or container, since serving them means running third-party instructions and scripts. It suits people who have collected skills and want them available in whichever agent they happen to use.
https://github.com/intellectronica/skillz
Also in MCP Server Framework
PrefectHQ/fastmcp
FastMCP offers a Pythonic framework for building Model Context Protocol (MCP) servers and clients, facilitating structured communication for AI agents and models.
pascalorg/editor
Local-first 3D building editor built with React Three Fiber and WebGPU that exposes an MCP service so AI agents can create and edit 3D scenes.
trycua/cua
c/ua is a high-performance framework that enables AI agents to control full macOS and Linux operating systems within secure, lightweight virtual containers on Apple Silicon Macs, supporting complex autonomous workflows and LLM integration.
nukeop/nuclear
Nuclear is a free, open-source, ad-free music player for Windows, macOS, and Linux, featuring streaming from various sources, playlist management, a powerful plugin system, and integration with AI ...
googleapis/mcp-toolbox
MCP Toolbox for Databases is an open-source server that connects AI agents and applications to enterprise databases using the Model Context Protocol (MCP).
apify/apify-mcp-server
Model Context Protocol server that exposes thousands of Apify Actors as tools, letting AI agents scrape social media, search engines, maps and e-commerce sites over hosted HTTP or local stdio.
grab/cursor-talk-to-figma-mcp
Cursor Talk to Figma MCP is an integration that enables Cursor AI to communicate with Figma programmatically for reading and modifying designs, automating and enhancing the design workflow.