Use Case
MiniMax Vision Captcha is a powerful AI agent skill that extends your assistant with new capabilities. Use the MiniMax visual model to identify the verification code, slider position, text content, etc. in the image. It is suitable for scenarios that require AI visual analysis, such as WeChat verification code recognition, web page screenshot analysis, and image text extraction. Use this skill when you need to identify image content, analyze verification codes, and extract screenshot information. This guide walks you through installing MiniMax Vision Captcha, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install MiniMax Vision Captcha: npx clawhub@latest --dir ~/.claude/skills install minimax-vision-captcha
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to general tools to trigger MiniMax Vision Captcha
Review the output and refine your prompt for better results
Combine MiniMax Vision Captcha with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing MiniMax Vision Captcha
Help me get started with MiniMax Vision Captcha
What can MiniMax Vision Captcha do for my general tools workflow?
Show me an example of using MiniMax Vision Captcha
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install minimax-vision-captchaOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install minimax-vision-captchaβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/minimax-vision-captcha/π‘Extract and place the folder at the path above, then restart your agent.