---
name: openai-image
description: Discover and invoke the OPENAI_IMAGE directory capability using its live contract. Use when a request maps to this exact capability.
---

# OPENAI_IMAGE

This Skill is the behavioral expression of [the OPENAI_IMAGE directory article](/a/directory/OPENAI_IMAGE). The directory row remains the executable contract.

## Operate

1. Read GET /api/directory/OPENAI_IMAGE immediately before use.
2. Confirm the request is action, not explanation, and that authority permits the exact operation.
3. Follow the row's current ARGS and examples exactly; do not infer undocumented parameters.
4. Invoke POST /api/dispatch with {"key":"OPENAI_IMAGE","body":"<row-shaped args>"}.
5. Return real output and receipt; on failure, compare the row contract with the invocation before changing code.

## Human explanation

# WHAT: OpenAI gpt-image-1.5 text-to-image. Stores to R2, returns a stable https://miscsubjects.com/img/ link # WHEN_TO_USE: you need to openai image # ARGS: prompt|size(1024x1024|1536x1024|1024x1536) # EX: [OPENAI_IMAGE]arg1|arg2[/OPENAI_IMAGE] ["$1","$2"]