Skill Library

Koog is a JVM framework for building reliable, enterprise-grade AI agents.

MCP server for the Godot game engine, providing features such as launching the editor, running projects, and capturing debug output.

High-performance AI pipeline engine supporting over 50 extensible nodes and multiple model providers.

Open Brain is an infrastructure layer that provides a unified database, AI gateway, and chat channel for your thinking.

Provides context management and multi-agent orchestration for Claude Code.

A real-time transport layer for Java AI agents, supporting WebSocket, SSE, gRPC, and WebTransport/HTTP3.

LangChain Skills is a set of agent skills for building LangChain, LangGraph, and Deep Agents.

Open-source video translation skill supporting multiple languages and speech synthesis.

CodexSkills is a suite of Codex/agent skills for planning, documentation access, frontend development, and browser automation.

Plugin for code repository management and iterative engineer workflows, enabling automated tasks and code validation.

AI agent security scanner that detects vulnerabilities in configurations, MCP servers, and tool permissions.

Secure scanning for your LLM agent workflows.

Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.

Integrate Burp Suite with AI clients via the MCP protocol.

Solana MCP by Vybe allows AI clients to browse modes or make real-time Solana API calls through a public MCP server.

A comprehensive Claude Code configuration set to help Chinese engineers use it efficiently.

An Agent designed specifically for mathematical modeling, automatically completing modeling tasks and generating full papers.

RAPTOR is an autonomous security research framework based on Claude Code, designed for vulnerability scanning, validation, and remediation.

Claude skill for developing graphics applications using Three.js and WebGPU.

Bankr Skills provides plug-and-play tools to help developers build more powerful agents.

PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents.

AI automation skills designed specifically for Unity.

Claude Code skill that delegates prompts to Codex for code analysis and editing.

Evaluate the effectiveness and efficiency of AI agents using skills.