Openai

This is a Membrane integration that lets Claude interact with OpenAI's platform directly. You can manage assistants, threads, messages, and files, plus run the usual suspects like chat completions, embeddings, and image generation through DALL-E. The real value is skipping the auth dance entirely. Membrane handles OAuth and credential refresh automatically, so you point at openai.com and you're connected. You can search for actions with natural language queries or drop down to raw API proxying when the pre-built actions don't cover your edge case. If you're building agents that need to orchestrate OpenAI resources or you're just tired of managing API keys, this handles the plumbing.

skills.sh installs: 182
GitHub stars: 272
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add membranedev/application-skills --skill openai --agent claude-code

Installs into .claude/skills of the current project.

Files

OpenAI

OpenAI is an artificial intelligence research and deployment company. They offer various AI models and APIs for developers to build applications leveraging cutting-edge AI capabilities.

Official docs: https://platform.openai.com/docs/api-reference

OpenAI Overview

Assistant
- Thread
  - Message
File

Use action names and parameters as needed.

Working with OpenAI

This skill uses the Membrane CLI to interact with OpenAI. Membrane handles authentication and credentials refresh automatically — so you can focus on the integration logic rather than auth plumbing.

Install the CLI

Install the Membrane CLI so you can run membrane from the terminal:

npm install -g @membranehq/cli@latest

Authentication

membrane login --tenant --clientName=<agentType>

This will either open a browser for authentication or print an authorization URL to the console, depending on whether interactive mode is available.

Headless environments: The command will print an authorization URL. Ask the user to open it in a browser. When they see a code after completing login, finish with: