Browse and install thousands of AI Agent skills in the Killer-Skills directory. Supports Claude Code, Windsurf, Cursor, and more.
A secure home and control plane for always‑on AI assistants that live across Slack, Discord, WhatsApp, Telegram, and WebChat, giving small teams and indie founders a production‑ready “Cloud Home” for their agents without touching infra.
replay-mcp is an AI Agent skill used to inspect the contents of replay.io recordings. These recordings are perfect captures of browser sessions, allowing for detailed investigation of web app behavior as if using a time machine to debug issues.
Don't let AI destroy your hard work! HardStop is a rock-solid protection for AI-generated commands. Pre-execution safety validation for Claude Code, Claude Cowork. Catches dangerous commands before they run: whether from AI mistakes, hallucinations, prompt injection, or misunderstood instructions. Seatbelts for the agentic AI era.
This extension transforms the Gemini CLI into "Pickle Rick," a hyper-intelligent, arrogant, yet extremely competent engineering persona. It enforces a rigid, iterative software development lifecycle through continuous AI agent loops. Emphasizing "God Mode" coding practices and a disdain for
FastMCP 2.14 Multi-Robot Coordination: Yahboom ROSMASTER, Dreame D20 Pro, Tdrone Mini, Unitree Go2/G1, and Philips Hue Bridge Pro collaborate through shared LIDAR maps, collaborative SLAM, RF-based movement detection, and real-time collision avoidance. Physical + virtual robots working as one system
Agent Capability Standard is an open specification for composable AI agent capabilities. It defines 36 atomic capabilities across 9 cognitive layers, a type-safe workflow DSL, and grounded world modeling with trust-aware conflict resolution. Built on the Grounded Agency philosophy, it makes agent reliability structural—not optional.
three-best-practices is an AI agent skill containing a comprehensive performance optimization guide for Three.js. It provides over 100 rules across 17 categories, based on official guidelines from the Three.js `llms` branch maintained by mrdoob.