Agent skill · software engineering · laguagu
openai-agents-sdk
OpenAI Agents SDK (Python) development. Use when building AI agents, multi-agent handoffs, function tools, guardrails, sessions, streaming, or tracing with the `openai-agents` / `agents` Python package — including Azure OpenAI via LiteLLM. Triggers on imports from `agents`, uses of `Runner.run_sync`/`Runner.run_streamed`, `@function_tool`, `AgentOutputSchema`, `SQLiteSession`, or questions about the openai-agents-python SDK. Python only — not the TypeScript `@openai/agents` SDK.
Why this skill is useful
Adds executable patterns and integration methods for building AI agents using the OpenAI Agents SDK that are not widely known.
What it needs
Requires openai-agents installed locally. Requires openai account access. About 3k tokens when loaded. Last updated 2026-08-03. 58 stars on the source repository.
What this skill does
OpenAI Agents SDK (Python) Use this skill when developing AI agents using OpenAI Agents SDK (openai-agents package). Quick Reference Installation Environment Variables Using Azure or another provider instead? See agents.md — don't hardcode provider env vars here, they vary and go stale. Basic Agent Omitting model= uses the SDK's built-in default (currently gpt-5.6-luna with low-effort reasoning settings) — set it explicitly in production so an upstream default change cannot swap tiers silently. Key Patterns Pattern Purpose --------- --------- Basic Agent Simple Q&A with instructions Azure/LiteLLM Azure OpenAI integration AgentOutputSchema Strict JSON validation with Pydantic Function Tools External actions (@functiontool) Streaming Real-time UI (Runner.runstreamed) Handoffs Specialized agents, delegation Agents as Tools Orchestration (agent.astool) LLM as Judge Iterative improvement loop Guardrails Input/output validation Sessions Automatic conversation history Multi-Agent Pipeline Multi-step workflows Sandboxing SandboxAgent — filesystem, shell and skills inside a local/Docker sandbox (beta) Tracing Built-in spans for runs, tools, handoffs and guardrails; pluggable processors The SDK has no separate Subagent class: express delegation with handoffs or agent.astool(). For model-written tool orchestration, use ProgrammaticToolCallingTool and verify its Responses-only constraints. Preferred: Live Docs via MCP Model names and API details change frequently. When available, consult the OpenAI Developer Docs MCP server (openaiDeveloperDocs) before relying on the static references below. Setup (Codex CLI): Setup (Claude Code): Or config (~/.codex/config.toml, VS Code .vscode/mcp.json, Cursor ~/.cursor/mcp.json): Key tools: mcpopenaiDeveloperDocssearchopenaidocs, fetchopenaidoc, listapiendpoints, getopenapispec. Rules: Cite fetched docs. Never speculate on field names, defaults, or current model IDs — fetch first. Keep quotes under 125 chars. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills laguagu/openai-agents-sdk