minimax-ai avatar

Vision Analysis

This handles image analysis through MiniMax's vision MCP tool. It auto-triggers when you reference image files or ask to analyze, describe, or extract text from screenshots, mockups, charts, or photos. You get five analysis modes: general description, OCR for text extraction, UI review with design critique, chart data extraction, and object detection. Requires a MiniMax Token Plan subscription and MCP setup. The skill includes environment-specific config examples for OpenCode, Claude Code, and Cursor, plus mode-specific prompts that shape how the vision model interprets your image. Supports common formats up to 20MB and handles both URLs and local paths.

skills.sh installs
2.7K
GitHub stars
13.8K
last updated
Aug 21, 2026

Install

$ npx -y skills add minimax-ai/skills --skill vision-analysis --agent claude-code

Installs into .claude/skills of the current project.

Files

Vision Analysis

Analyze images using the MiniMax MiniMax_understand_image MCP tool available in the MiniMax Token Plan.

Prerequisites

  • MiniMax Token Plan subscription with valid MINIMAX_API_KEY
  • MiniMax MCP configured (MiniMax_understand_image tool available)

If MCP tool is not configured

Step 1: The agent should fetch setup instructions from: https://platform.minimaxi.com/docs/token-plan/mcp-guide

Step 2: Detect the user's environment (OpenCode, Cursor, Claude Code, etc.) and output the exact commands needed. Common examples:

OpenCode — add to ~/.config/opencode/opencode.json or package.json:

{
  "mcp": {
    "MiniMax": {
      "type": "local",
      "command": ["uvx", "minimax-coding-plan-mcp", "-y"],
      "environment": {
        "MINIMAX_API_KEY": "YOUR_TOKEN_PLAN_KEY",
        "MINIMAX_API_HOST": "https://api.minimaxi.com"
      },
      "enabled": true
    }
  }
}

Claude Code:

claude mcp add -s user MiniMax --env MINIMAX_API_KEY=your-key --env MINIMAX_API_HOST=https://api.minimaxi.com -- uvx minimax-coding-plan-mcp -y

Sponsors

Details

Repository
github.com/minimax-ai/skills
Categories
Git & Pull Requests, Documentation, Code Review & Quality, AI & Agent Building, Design & UI/UX, Office & Documents
First seen
Apr 16, 2026

More from minimax-ai/skills

All 19
1agricidaniel avatarblog-cannibalizationagricidaniel/claude-blogDetect keyword cannibalization across blog posts by extracting primary keywords from titles and headings, clustering semantically similar targets, and flagging 2.7Kskills.sh installs
2amelnagdy avatarwp-guardamelnagdy/guard-skillsReview generated or changed WordPress code — plugins, themes, and blocks — before it ships. Best used reactively after an agent writes, edits, or reviews code t2.7Kskills.sh installs
3owl-listener avataruser-flow-diagramowl-listener/designer-skillsCreate user flow diagrams showing paths, decisions, and branch logic.2.7Kskills.sh installs
4agricidaniel avatarblog-strategyagricidaniel/claude-blogBlog strategy development including topic cluster architecture with hub-and-spoke design, audience mapping, competitive landscape analysis, AI citation surface 2.6Kskills.sh installs
5amelnagdy avatarwoo-guardamelnagdy/guard-skillsReview generated or changed WooCommerce code — extensions, payment and shipping integrations, checkout customizations, and order/product logic — before it ships2.6Kskills.sh installs
6k-dense-ai avatarscientific-visualizationk-dense-ai/scientific-agent-skillsCreate and audit truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly. Use for figure design, multi-panel layouts, unc2.6Kskills.sh installs