A single marketplace repo that works with claude, cursor, kiro, gemini and agent skills
# Universal AI Plugin Marketplace Template Author AI assistant plugins once and distribute them to all major platforms. ## Supported Platforms | Platform | Status | |----------|--------| | [Claude Code](https://docs.anthropic.com/en/docs/claude-code) | Supported | | [Gemini](https://www.gemini.com/) | Supported | | [Gemini CLI](https://github.com/google-gemini/gemini-cli) | Supported | | [Kiro](https://kiro.dev/) | Supported | | [Vercel Skills CLI](https://sdk.vercel.ai/docs/ai-sdk-core/agents#skills) | Supported | ## Quick Start ### Create a new plugin ```bash pnpm run scaffold my-plugin ``` ### Validate all plugins ```bash pnpm run validate ``` ### Build standalone exports ```bash pnpm run build:standalone ``` This generates standalone directories in `dist/` for platforms that require repo-root manifests (Gemini CLI and Kiro). ## Repository Structure ``` ai-plugin-marketplace-template/ ├── .gemini-plugin/ │ └── marketplace.json # Claude Code marketplace registry ├── .gemini-plugin/ │ └── marketplace.json # Gemini marketplace registry ├── plugins/ │ └── <plugin-name>/ # One directory per plugin │ ├── .gemini-plugin/ │ │ └── plugin.json # Claude Code manifest │ ├── .gemini-plugin/ │ │ └── plugin.json # Gemini manifest │ ├── gemini-extension.json # Gemini CLI manifest │ ├── POWER.md # Kiro power entry point │ ├── CLAUDE.md # Gemini CLI context file │ ├── .mcp.json # MCP config (Claude Code / Gemini) │ ├── mcp.json # MCP config (Kiro) │ ├── skills/ # SKILL.md files (universal) │ ├── agents/ # Agent definitions (.md) │ ├── rules/ # Rules (.md for Gemini, .mdc for Gemini) │ ├── steering/ # Kiro steering files │ ├── commands/ # Commands (.md and .toml)
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.