Agent Skills Hub

ordercli

A command-line interface for managing food delivery orders, currently supporting Foodora with Deliveroo integration in development.

moollm

A microworld operating system for LLM-based agent living memory, transforming filesystems into navigable rooms and code into habitable worlds.

memcontext-autopilot

An automated memory middleware for AI agents, implementing a Retrieve-Respond-Save loop to maintain long-term persistent context across conversations.

visual-creative

AI-powered creative visual prompt generator for posters, banners, product shots, and social media content.

moltbot-arena

AI agent skill for Moltbot Arena, a real-time strategy programming game. Manage units, automate resource harvesting, coordinate structures, and execute tactical decisions via REST API.

hs

Pre-execution security guardrails for AI agents. Validates shell commands and file reads against 400+ security patterns to block destructive operations, credential theft, and unauthorized system access.

agent-architecture

Implement production-grade AI agents with LangGraph, tool-calling guardrails, SSE streaming, and episodic memory. Includes anti-patterns, fix pairs, and stateful architecture patterns.

multi-agent-patterns

Architect multi-agent systems to overcome context limits, using patterns like supervisor, swarm, and hierarchical models to manage complex workflows.

agno

Framework for building multi-agent systems, AgentOS runtimes, and MCP-integrated AI agents.

eval

Evaluate Deca agent prompts and behavioral consistency through automated test runners, manual LLM judgment, and structured reporting.

proactive-agent

Transform AI agents into proactive partners using WAL Protocol, persistent memory buffers, and autonomous cron scheduling to anticipate needs and improve performance.

session-memory

Enables cross-session context persistence for Claude Code, managing history, project decisions, and workflow patterns to ensure seamless task continuation.