gemini-image-describer
Official即刻以繁體中文詳述任意圖片
Authorduotify
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This skill converts user-provided images into detailed Traditional Chinese descriptions, including scene context, OCR results, and a key objects list to improve understanding and accessibility.
Core Features & Use Cases
- Scene description: Generate a rich zh-TW narrative of the image including environment and activities.
- OCR extraction: Capture and present readable text found within the image.
- Key object list: Identify and enumerate prominent elements visible in the image.
- Use case: Ideal for creating accessible image captions or understanding images quickly when you only have visuals.
Quick Start
Describe this image in Traditional Chinese and output a structured Markdown with a scene description, OCR text, and a key object list.
Dependency Matrix
Required Modules
@google/genai
Components
scripts
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: gemini-image-describer Download link: https://github.com/duotify/GitHubClawToolkit/archive/main.zip#gemini-image-describer Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.