openai-image-vision

Community

Analyze images with OpenAI Vision via Bash.

Authorzhayujie
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill provides a Bash-based wrapper to analyze images using OpenAI's GPT-4 Vision API, enabling quick and thorough understanding of visual content with minimal setup.

Core Features & Use Cases

  • Image analysis: Describe scenes, detect objects, colors, and text in local files or URLs.
  • OCR and extraction: Extract visible text from images for records and indexing.
  • Model flexibility: Choose among supported OpenAI Vision models and adjust base API URL as needed.

Quick Start

To use this skill, configure your OPENAI_API_KEY and run a vision query, for example:

  • bash "<base_dir>/scripts/vision.sh" "/path/to/image.jpg" "Describe this image"

Dependency Matrix

Required Modules

curlbase64sipsconvertmktempgrepsedheadwctr

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: openai-image-vision
Download link: https://github.com/zhayujie/chatgpt-on-wechat/archive/main.zip#openai-image-vision

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 223,000+ vetted skills library on demand.