Frontend Components
Multi-agent AI coding platform powered by Vercel Sandbox and AI Gateway - Phase 3: Skills & MCP Integration Complete
Browse and install thousands of AI Agent skills in the Killer-Skills directory. Supports Claude Code, Windsurf, Cursor, and more.
Multi-agent AI coding platform powered by Vercel Sandbox and AI Gateway - Phase 3: Skills & MCP Integration Complete
/Lumina-Intelligence, /Luminor-intelligence & /StarlightOrchestrator building Arcanea with swarm intelligence that overlays any AI. Ten Gates, Guardians & Godbeasts, context that compounds, and the cr
deploy-mcp is a GitHub Actions-based AI agent skill for automating MCP server deployment and scaling, designed for seamless integration with Claude Code and AI coding workflows.
Universal Context Architecture. One source of truth for Cursor, Claude Code, GitHub Copilot, Gemini, Amazon Q, and 19+ AI coding assistants.
A curated collection of prompts, skills, plugins, and best practices for AI coding agents. Standardize and accelerate agent setup across teams.
agentic-mcp is a progressive MCP client with three-layer lazy loading, designed for efficient token usage and optimized AI coding workflows.
Enforce docs-before-code discipline in AI-assisted development. VibeFlow provides Claude Code skills and hooks for a full workflow with checkpoint gates and branch-locked enforcement.
Agentic Creator OS v11 — The operating system for AI-powered creators. 90+ skills, 65+ commands, 38 agents, 8 plugins. Works with Claude Code, Cursor, Windsurf, Gemini.
A structured prompt framework for building software products with AI coding assistants. This toolkit guides you through product specification, technical design, and implementation planning—producing documents that AI agents can execute against.
fix is a set of AI agent configurations and automated workflows optimized for Python and ML development, focused on regression test-driven bug fixing.
The Python Un-Notebook
Holon runs AI coding agents headlessly to turn issues into PR-ready patches and summaries — locally or in CI, without babysitting the agent.