Does it support image-to-image or reference-based generation?

Yes, when using Google multimodal models, you can use the --ref flag to provide one or more source images for editing or style reference.

How do I set up the API keys for this skill?

You can provide OPENAI_API_KEY or GOOGLE_API_KEY via environment variables, or store them in a .env file within the .content-gen-skills directory.

Can I generate images in specific sizes or aspect ratios?

Yes, you can use the --ar flag for common ratios like 16:9 and 1:1, or the --size flag to specify exact pixel dimensions like 1792x1024.

Which AI providers are supported by this skill?

The skill supports both OpenAI (DALL-E 3, GPT Image) and Google (Imagen 3, Gemini multimodal) APIs, with an auto-detection feature based on your available API keys.

Image Generation Skill

Name: Image Generation Skill
Author: zlh-428

byzlh-428

•

设计工具

Generates high-quality images and illustrations using OpenAI and Google APIs directly from your development workflow.

关于

This skill enables seamless image generation within Claude Code by leveraging the AI SDK to connect with industry-leading models like DALL-E 3, GPT Image, and Google Imagen. It simplifies the process of creating visual assets, social media graphics, and UI illustrations by offering built-in support for multiple aspect ratios, quality presets (up to 2K), and reference image editing. Whether you need a quick placeholder for a frontend project or a high-resolution cover image, this skill provides a standardized CLI interface for diverse creative tasks across different providers.

主要功能

High-resolution 2K quality presets for professional-grade visual assets
Batch generation capabilities using external text files for complex prompts
Reference image support for image-to-image editing and style transfers
Advanced aspect ratio controls (1:1, 16:9, 4:3, 9:16, and custom sizes)
Multi-provider support including OpenAI DALL-E/GPT and Google Gemini/Imagen
2 GitHub stars

使用场景

Automating the production of high-quality cover images and documentation visuals
Generating UI placeholders and custom illustrations for web development projects
Creating social media assets and marketing graphics with specific aspect ratios

关于

主要功能

High-resolution 2K quality presets for professional-grade visual assets
Batch generation capabilities using external text files for complex prompts
Reference image support for image-to-image editing and style transfers
Advanced aspect ratio controls (1:1, 16:9, 4:3, 9:16, and custom sizes)
Multi-provider support including OpenAI DALL-E/GPT and Google Gemini/Imagen
2 GitHub stars

使用场景

Automating the production of high-quality cover images and documentation visuals
Generating UI placeholders and custom illustrations for web development projects
Creating social media assets and marketing graphics with specific aspect ratios