Agent skill · marketing growth · composiohq
OpenAI Automation
Automate OpenAI API operations -- generate responses with multimodal and structured output support, create embeddings, generate images, and list models via the Composio MCP integration.
Why this skill is useful
Adds specific commands and workflows for automating OpenAI API operations that the AI wouldn't reliably generate on its own.
What it needs
Requires rube installed locally. Requires openai account access. About 3k tokens when loaded. Last updated 2026-07-24. 71,973 stars on the source repository.
What this skill does
OpenAI Automation Automate your OpenAI API workflows -- generate text with the Responses API (including multimodal image+text inputs and structured JSON outputs), create embeddings for search and clustering, generate images with DALL-E and GPT Image models, and list available models. Toolkit docs: composio.dev/toolkits/openai --- Setup 1. Add the Composio MCP server to your client: https://rube.app/mcp 2. Connect your OpenAI account when prompted (API key authentication) 3. Start using the workflows below --- Core Workflows 1. Generate a Response (Text, Multimodal, Structured) Use OPENAICREATERESPONSE for one-shot model responses including text, image analysis, OCR, and structured JSON outputs. Structured output example: Set text.format to { type: "jsonschema", name: "person", schema: { type: "object", properties: { name: { type: "string" }, age: { type: "integer" } }, required: ["name", "age"], additionalProperties: false }, strict: true }. 2. Create Embeddings Use OPENAICREATEEMBEDDINGS for vector search, clustering, recommendations, and RAG pipelines. 3. Generate Images Use OPENAICREATEIMAGE to create images from text prompts using GPT Image or DALL-E models. 4. List Available Models Use OPENAILISTMODELS to discover which models are accessible with your API key. --- Known Pitfalls Pitfall Detail --------- -------- DALL-E deprecation DALL-E 2 and DALL-E 3 are deprecated and will stop being supported on 05/12/2026. Prefer GPT Image models. DALL-E 3 single image only OPENAICREATEIMAGE with DALL-E 3 only supports n=1. Use GPT Image models or DALL-E 2 for multiple images. Token limits for embeddings Input must not exceed 8192 tokens per item and 2048 items per batch for embedding models. Reasoning model restrictions temperature and topp are not supported with reasoning models (o3-mini, etc.). Use reasoning.effort instead. Structured output strict mode When strict: true in jsonschema format, ALL schema properties must be listed in the required array. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills composiohq/openai-automation