Is this skill compatible with standard Claude Code?

No, this skill is specifically designed for the OpenClaw platform. Users on the standard Claude Code interface should ignore this skill.

Where does the skill store processed images?

Images are saved in the '~/.openclaw/media/inbound/' directory, using a UUID-based naming convention for organized storage.

What are the technical requirements for installation?

You will need Python 3.10 or higher, the 'mcp' Python library, and a valid MiniMax API key configured in your environment.

Is this skill suitable for legal professionals?

Yes, it is part of a legal-focused skill collection and is optimized for analyzing documents and visual evidence common in legal workflows.

Can I use this for analyzing web images?

Yes, the skill supports both local image file paths and publicly accessible image URLs as inputs for analysis.

MiniMax Image Understanding for OpenClaw

Name: MiniMax Image Understanding for OpenClaw
Author: cat-xierluo

bycat-xierluo

•

Data Science & ML

Integrates MiniMax's advanced image analysis capabilities into the OpenClaw platform for detailed visual interpretation and recognition.

This skill provides a specialized interface for the OpenClaw platform to leverage the MiniMax Model Context Protocol (MCP) for sophisticated image understanding. It allows users to process local image files or URLs to generate descriptions, identify objects, and analyze visual data within an automated workflow. Although housed in a legal skills repository, its robust vision capabilities make it ideal for any OpenClaw user needing to parse visual evidence, scanned documents, or complex imagery via the MiniMax API.

Key Features

01Support for both local file paths and remote image URLs

02Seamless integration with MiniMax MCP for high-fidelity image analysis

0357 GitHub stars

04Automated image handling within the OpenClaw media directory structure

05Simplified environment-based configuration for API key management

06Customizable prompting for targeted visual identification and description

Use Cases

01Generating descriptive metadata for visual assets within the OpenClaw ecosystem

02Analyzing visual evidence or scanned legal documents for automated review

03Extracting contextual data from images to assist in content management workflows

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add cat-xierluo/legal-skills minimax-image-understand

For use in Claude.ai and ChatGPT

Download Skill