Openai Agents Sdk

This is your go-to when building AI agents with OpenAI's official Python SDK. It covers the full stack: basic agents with instructions and models, function tools for external actions, multi-agent handoffs for delegation, streaming responses, Pydantic output schemas, and Azure OpenAI via LiteLLM. The skill smartly points you to the OpenAI Developer Docs MCP server first since model names and APIs shift constantly, then falls back to static references for agents, tools, sessions, and guardrails. Useful if you're wiring up chatbots, multi-step workflows, or anything that needs structured JSON responses and conversation history. The examples are production-ready, not toy demos.

skills.sh installs: 2.4K
GitHub stars: 72
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add laguagu/claude-code-nextjs-skills --skill openai-agents-sdk --agent claude-code

Installs into .claude/skills of the current project.

Files

OpenAI Agents SDK for Python

Use this skill for openai-agents / agents, not the TypeScript SDK. Resolve the installed package and its provider integrations before implementing an API. Current SDK documentation and a matching source tag take precedence over static examples.

Choose a model from the current OpenAI model catalog and model-selection guide. Check the selected model's tools, reasoning settings and provider availability; an SDK fallback or a demo ID is not a permanent recommendation.

The wheel ships no docs. Offline, read the installed source: the version from importlib.metadata.version("openai-agents"), public exports in agents/__init__.py, docstrings and types in the package directory (python -c "import agents; print(agents.__file__)"). The documentation source is docs/ at repository tag v<version>.