What runtimes are supported by this skill?

The skill provides patterns for Node.js 22+, Deno, Bun, and includes specific experimental support for Cloudflare Workers and Next.js.

Can I use this for voice-based applications?

Yes, it includes specialized templates for Realtime voice agents using WebRTC or WebSockets, along with best practices for secure server-side session token generation.

How does it handle multi-agent communication?

It implements the handoff pattern where agents can delegate tasks to specialized colleagues based on the conversation context and predefined handoff descriptions.

Does it include error prevention for agent loops?

Yes, it provides specific configurations for maxTurns and instruction-based guardrails to prevent MaxTurnsExceededError and infinite tool-calling loops.

Is human-in-the-loop supported for sensitive actions?

Absolutely; the skill features implementation patterns for tools that trigger an 'interruption' state, requiring manual human approval before the action is executed.

OpenAI Agents SDK Integration

Name: OpenAI Agents SDK Integration
Author: jezweb

byjezweb

•

API開発

Builds sophisticated AI applications using the OpenAI Agents SDK with support for multi-agent workflows, realtime voice, and structured outputs.

概要

This skill empowers Claude to architect and implement complex agentic systems using the OpenAI Agents JS SDK. It provides comprehensive patterns for creating text and voice-based agents, managing autonomous multi-agent handoffs, and implementing robust safety guardrails. Whether you are deploying to Cloudflare Workers or Next.js, this skill offers production-tested templates for human-in-the-loop interactions, streaming responses, and advanced error handling to prevent common pitfalls like infinite loops, tool call failures, or Zod schema mismatches.

主な機能

Safety-first development with input/output guardrails and human-in-the-loop approval patterns
Multi-agent orchestration with autonomous handoffs between specialized agents
Realtime voice agent implementation using WebRTC and WebSocket transports
91 GitHub stars
Type-safe tool integration using Zod schemas for structured input and output
Comprehensive error handling for Zod mismatches, tracing failures, and MaxTurnsExceeded errors

ユースケース

Developing interactive voice-based AI assistants for web browsers using secure ephemeral session tokens
Building a multi-agent customer support system with specialized billing and technical triage agents
Implementing enterprise-grade AI workflows requiring human approval for critical tool-based actions

概要

主な機能

Safety-first development with input/output guardrails and human-in-the-loop approval patterns
Multi-agent orchestration with autonomous handoffs between specialized agents
Realtime voice agent implementation using WebRTC and WebSocket transports
91 GitHub stars
Type-safe tool integration using Zod schemas for structured input and output
Comprehensive error handling for Zod mismatches, tracing failures, and MaxTurnsExceeded errors

ユースケース

Developing interactive voice-based AI assistants for web browsers using secure ephemeral session tokens
Building a multi-agent customer support system with specialized billing and technical triage agents
Implementing enterprise-grade AI workflows requiring human approval for critical tool-based actions