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

# OPENAI_IMAGE_EDIT

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

## Operate

1. Read GET /api/directory/OPENAI_IMAGE_EDIT 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_EDIT","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 edit from a reference image URL. Stores to R2 # WHEN_TO_USE: you need to openai image edit # ARGS: prompt|reference_url|size # EX: [OPENAI_IMAGE_EDIT]arg1|arg2|arg3[/OPENAI_IMAGE_EDIT] ["$1","$2","$3"]