Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Command-line tool for generating, editing, and creating variations of images using OpenAI's GPT Image and DALL-E models. Supports batch processing, inpainting with masks, transparent backgrounds, and local history tracking. Configurable defaults for model, size, quality, and output format.
Wraps OpenAI's image API into a single CLI with batch support, history tracking, and per-request options that would otherwise require custom scripting against the raw API.
When to use it
- Generating product mockup images from text descriptions
- Batch-creating social media visuals from a JSONL prompt list
- Editing photos with text instructions like removing or adding objects
- Creating logo variations with transparent PNG backgrounds
- Automating image generation in shell scripts with JSON output
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: generate 4 logo variations with transparent backgrounds and save them to ./logos
- 1Run `openai-image generate "Logo design" -n 4 -b transparent -f png -o ./logos`
- 2CLI sends requests to OpenAI GPT Image model with specified parameters
- 3Images are downloaded and saved as PNG files in the ./logos directory
- 4Generation metadata is recorded in local history
4 PNG files saved to ./logos with transparent backgrounds, each listed with model, size, and token usage
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.