claude-vision-skill

claude-vision-skill

Enable image recognition capabilities for AI models that lack this feature.

Agent SkillDevOpen source
Type
Agent Skill
Open source
Yes
GitHub Stars
★ 1.2k
Source
skill-github

Overview

Claude Vision Skill is a script that allows AI models without built-in image recognition to process images by calling external vision models. Users simply send an image, and the AI automatically returns a textual description. Supports multiple vision models such as Alibaba Cloud BaiLian and OpenAI. Setup involves downloading `vision.js`, replacing the API Key and model name, and merging `CLAUDE.md` into your project. Suitable for various use cases requiring image recognition functionality.

Capabilities

  • Read images and convert them to base64
  • Call external vision model APIs
  • Return textual descriptions of images
  • Support multiple vision models

Use cases

Add image recognition to a Claude Code projectIntegrate image recognition into cyberbossAutomatically process images sent by users

Setup

Requires: API KeyNode 环境
git clone https://github.com/asuojun/claude-vision-skill.git; add `vision.js` and `CLAUDE.md` to your project, then replace the API Key and model name.

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

Which vision models are supported?

Supports Alibaba Cloud BaiLian (recommended), OpenAI, and other models compatible with the OpenAI format.

How do I get an API Key?

Go to the respective platform's website, register an account, and apply for an API Key.

Related skills