Agent Skills Hub

vibe-run

A deterministic orchestration engine for autonomous coding agents, managing workflow loops, state persistence, and checkpoint-based execution.

connections

Lightweight MCP (Model Context Protocol) connection handler supporting stdio, SSE, and streamable HTTP transports for seamless server integration.

openai-agents-sdk

Build AI agents with the OpenAI Agents SDK for Python. Supports multi-agent handoffs, function tools, stateful sessions, streaming, and Azure OpenAI integration via LiteLLM.

orchestrate

Multi-phase feature development workflow for complex tasks using research, planning, implementation, and review gates.

mcp-patterns

Maintenance patterns for the @youdotcom-oss/mcp STDIO bridge, focusing on transport lifecycle management, shutdown guards, and robust error handling.

browser-booking-agent

Automate booking, search, and reservation workflows via browser automation with screenshot verification and confirmation tracking.

dev-cycle

Interactive development workflow manager. Coordinates discovery, planning, review, and build phases using a specialized team of AI agents (Scout, Bob, Garry, Arlo) for consistent project delivery.

sparc-methodology

SPARC methodology for multi-agent development: systematic Specification, Pseudocode, Architecture, Refinement, and Completion workflows via Claude Flow orchestration.

instagram-play

Automate Instagram interactions including feed browsing, story creation, Reels navigation, DM management, and posting.

backend-architect

Senior backend architecture expert specializing in Hexagonal Architecture, DDD, SOLID principles, clean code, and refactoring to guide development, reviews, and architectural problem-solving.

creating-opencode-agents

Expert guidance and configuration standards for creating specialized OpenCode AI agents, including YAML frontmatter, tool permissions, and operational modes.

state-management

Guidance on frontend state management, including global stores like Zustand/Pinia, server state via TanStack Query, and URL state handling.