antigravity-awesome-skills
The Ultimate Collection of 900+ Agentic Skills for Claude Code/Antigravity/Cursor. Battle-tested, high-performance skills for AI agents including official skills from Anthropic and Vercel.
claude mcp add --transport stdio sickn33-antigravity-awesome-skills npx -y antigravity-awesome-skills \ --env INSTALL_PATH="Default installation path for skills"
How to use
Antigravity Awesome Skills is a comprehensive library of over 1,272 agentic skills designed for various AI coding assistants such as Claude Code, Gemini CLI, and GitHub Copilot. After installation, users can easily invoke skills by using natural language commands. For example, you can ask your AI agent to 'Use the @brainstorming skill to help me plan a SaaS' or 'Run @lint-and-validate on this file.' The skills are organized into bundles, allowing users to quickly find and utilize the skills relevant to their specific needs, such as web development or security tasks.
How to install
To install Antigravity Awesome Skills, follow these steps:
- Ensure you have Node.js installed on your system.
- Open your terminal and run the following command:
npx antigravity-awesome-skills - After installation, verify that the skills have been installed by running:
test -d ~/.gemini/antigravity/skills && echo 'Skills installed' - You can now start using your first skill by prompting your AI agent with a command like:
Use @brainstorming to plan a SaaS MVP.
Additional notes
For Windows users, be aware that this repository uses symlinks for official skills, which may require additional configuration. If you encounter issues, refer to the troubleshooting section in the documentation. The default installation path for skills is ~/.gemini/antigravity/skills, but you can specify a different path using the --path option during installation.
Related MCP Servers
code-mode
🔌 Plug-and-play library to enable agents to call MCP and UTCP tools via code execution.
AnyTool
"AnyTool: Universal Tool-Use Layer for AI Agents"
claude-talk-to-figma
A Model Context Protocol (MCP) that allows Claude Desktop and other AI tools (Claude Code, Cursor, Antigravity, etc.) to read, analyze, and modify Figma designs
forgetful
Opensource Memory for Agents
crawl4ai
🕷️ A lightweight Model Context Protocol (MCP) server that exposes Crawl4AI web scraping and crawling capabilities as tools for AI agents. Similar to Firecrawl's API but self-hosted and free. Perfect for integrating web scraping into your AI workflows with OpenAI Agents SDK, Cursor, Claude Code, and other MCP-compatible tools.
packt-netops-ai-workshop
🔧 Build Intelligent Networks with AI