What are 'Rich Images' in this skill?

Rich images use specialized templates for thumbnails and illustrations, allowing you to provide JSON data for titles, subtitles, and character presets for consistent branding.

Does it support text rendering in languages like Japanese?

Yes, the GLM-Image (ZhipuAI) provider is specifically optimized for high-accuracy text rendering in multiple languages including Japanese and Chinese.

Can I create images with transparent backgrounds?

Yes, you can generate natively transparent PNGs using the OpenAI provider or use the built-in background removal tools (Vision API or Magenta removal) for other models.

How do I choose between different AI providers?

The skill includes an automated logic: OpenAI is recommended for native transparency, Gemini for style-copying from reference images, and ZhipuAI for high-precision text rendering.

What setup is required to use this skill?

You need the 'uv' package manager and the relevant API keys (GEMINI_API_KEY, OPENAI_API_KEY, or GLM_API_KEY) set as environment variables.

Image Creator AI

Name: Image Creator AI
Author: haboshi

byhaboshi

0•

Design Tools

Generates, edits, and processes high-quality AI images across multiple providers including Gemini, OpenAI, and ZhipuAI.

Image Creator is a comprehensive Claude Code skill that empowers developers to generate and manipulate visual content directly from their terminal workflow. It provides a unified interface for Google Gemini (Nano Banana), OpenAI GPT Image, and ZhipuAI GLM-Image, allowing users to handle diverse tasks from generating transparent stickers and YouTube thumbnails to creating complex technical diagrams. With advanced features like Vision-based background removal, sticker sheet splitting, and template-based 'rich' image generation, it streamlines the creation of design assets without leaving the development environment.

Key Features

01High-precision text rendering (91%+ accuracy) for banners and logos using GLM-Image

02Rich template system for automated YouTube thumbnails and technical diagrams

03Multi-provider support including Gemini NB2/Pro, OpenAI GPT Image 1.5, and ZhipuAI GLM

04Automatic sticker sheet generation and individual object splitting

050 GitHub stars

06Native transparent background generation and Vision API-based background removal

Use Cases

01Visualizing technical documentation through automated charts and comparison diagrams

02Creating professional YouTube thumbnails and blog headers with custom character presets

03Generating transparent UI icons and stickers for frontend development

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add haboshi/claude-code-skills image-creator

For use in Claude.ai and ChatGPT

Key Features

01High-precision text rendering (91%+ accuracy) for banners and logos using GLM-Image

02Rich template system for automated YouTube thumbnails and technical diagrams

03Multi-provider support including Gemini NB2/Pro, OpenAI GPT Image 1.5, and ZhipuAI GLM

04Automatic sticker sheet generation and individual object splitting

050 GitHub stars

06Native transparent background generation and Vision API-based background removal

Use Cases

01Visualizing technical documentation through automated charts and comparison diagrams

02Creating professional YouTube thumbnails and blog headers with custom character presets

03Generating transparent UI icons and stickers for frontend development