What problem does it solve? It removes the friction of calling many different AI image generation APIs by providing one unified CLI that handles provider detection, model selection, sizing rules, retries, and batch parallelism. ## Core Features & Use Cases - Multi-provider image generation: Supports OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI, MiniMax, Jimeng, Seedream, and Replicate with automatic provider detection from API keys. - Reference images and batch mode: Accepts reference images for edit workflows and runs parallel batch generation from a JSON batch file with per-provider rate limiting and up to 3 retries per image. - Persistent preferences: Stores default provider, model, quality, and aspect ratio in an EXTEND.md config file loaded before any generation. - Use Case: A content team saves prompt files for ten article illustrations, assembles them into a batch.json, and generates all images in parallel with consistent quality settings. ## Quick Start Ask the AI to generate an image of your subject using this skill, for example: generate a 16:9 illustration of a sunset over a mountain lake and save it as sunset.png.
