Agent Skills Hub

template-structure

Standardize project scaffolding with pre-configured Claude Code directories, commands, and agents to ensure consistency across all your development templates.

Ralph-Loop-Ultra

Seamlessly toggle between live and mocked external dependencies using the Model Context Protocol (MCP) for autonomous development environments.

agno

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

use-railway

Operate Railway infrastructure: manage projects, services, databases, object storage, deployments, environments, variables, logs, and performance metrics.

trigger-dev-tasks

Expert assistant for designing and optimizing production-grade Trigger.dev background jobs, AI workflows, and resilient asynchronous task architectures in TypeScript.

kagent

Expert guide for kagent: the Kubernetes-native framework for building, deploying, and managing AI agents, MCP tools, and A2A protocols.

agentic-workflows

Build production-grade AI agents using LangGraph, Anthropic/OpenAI/vLLM, and structured outputs. Features streaming, A2A protocol, Pydantic validation, vector memory, and guardrails for resilient, multi-agent workflows.

rule-validation

Validates Skill, Agent, and Command syntax using validate_skills.py, logs errors, and manages the automated QC workflow for agent development.

claude-ralph

An autonomous AI agent loop that executes Claude Code repeatedly to build features from structured PRDs until completion.

persona

An AI-driven framework for crafting bespoke, authentic portfolio websites from scratch. Guides agents through research, design, and code implementation to build unique developer and professional sites.

langgraph

Expert LangGraph architect skill for designing stateful, multi-actor AI agent workflows with robust persistence, conditional branching, and ReAct patterns.

vibe-orchestrator

Master workflow controller for Lovable-style, AI-driven development. Instantly generates premium, multi-page, animated applications by routing to specialized sub-agents. No prompts needed—just build.