mcpbeat Sign in

Agents SDK Skill for Codex

by openai

Use when the user wants to build, adapt, run, or evaluate an OpenAI Agents SDK app from Cursor. Prefer a docs-first workflow and route API credential decisions through openai-platform-api-key before API-backed work.

361 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
2
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/openai/openai-developers-for-cursor --skill agents-sdk

The instruction itself

4 sections, as written by the author

Agents SDK

Use this skill to turn an idea or repo into a focused Agents SDK implementation.

Before You Build

  • Use openai-docs to inspect current Agents SDK guidance.
  • If the work will call the OpenAI API, use openai-platform-api-key before building, running, testing, or debugging the API-backed path.
  • Inspect the repo's existing language, package manager, entrypoints, and testing style before choosing a structure.

Workflow

  • Define the agent contract:
  • goal
  • user input
  • expected output
  • tools
  • approval or escalation boundaries
  • Prefer the smallest runnable implementation first.
  • Use tools deliberately and keep side effects narrow.
  • Add evals when the user asks for reliability, comparison, or regression coverage.
  • Provide a local run command and a concrete smoke result when implementation is requested.

Guidance

  • Prefer Python unless the repo or user already points to TypeScript.
  • Start with one agent before introducing handoffs or orchestration.
  • Keep prompts, tools, tests, and deployment artifacts clearly separated.
  • Use openai-docs again when current SDK behavior or product guidance is central to the answer.

How to use it

Copy the folder

Take openai/openai-developers-for-cursor-agents-sdk from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.