claude-vision-skill
Enable image recognition capabilities for AI models that lack this feature.
- Type
- Agent Skill
- Open source
- Yes
- GitHub Stars
- ★ 1.2k
- Source
- skill-github
- Repository
- github.com/asuojun/claude-vision-skill
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
Setup
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
mantis
Provides security review capabilities for AI coding agents, automatically discovering, reproducing, and fixing vulnerabilities.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
Lightswind-UI-Library
AI-native CLI-first React component library with MCP Server support.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.