deepseek-eyes

Community

Enhance image understanding for models that can't natively see images.

Authorhawkongz
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides a bridge for models that cannot natively process images, allowing them to understand and interact with image content by routing images through Alibaba Cloud Bailian vision models.

Core Features & Use Cases

  • Image to Text Description: Converts images into detailed Chinese text descriptions.
  • Enhanced Image Understanding: Allows models to reason about image content without direct image processing capabilities.
  • Use Case: When a user shares an image that the model cannot process, this Skill can generate a description that the model can then use to answer questions or provide insights.

Quick Start

Use the deepseek-eyes skill to analyze the image 'screenshot.png' and describe its content.

Dependency Matrix

Required Modules

dashscope

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: deepseek-eyes
Download link: https://github.com/hawkongz/deepseek-eyes/archive/main.zip#deepseek-eyes

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.