This connects Claude to MiniMax's image understanding API through their MCP server. You can analyze images from local paths or URLs by asking questions about them in natural language, like "describe what's in this image" or "what objects do you see here." The skill handles the full setup workflow including uvx installation, API key configuration through environment variables or a config file, and provides a Python script that communicates with the MCP server over stdio. It's aimed at Chinese developers based on the bilingual documentation and includes mirror options for PyPI package installation. Worth noting that you need a MiniMax subscription to use it, and the setup is a bit involved for first-time use though subsequent calls are straightforward.
npx -y skills add thincher/awsome_skills --skill minimax-understand-image --agent claude-codeInstalls into .claude/skills of the current project.
使用 MiniMax MCP 服务器进行图像理解和分析。
which uvx
如果不存在,安装 uv:
方法 1: 使用官方安装脚本(推荐)
curl -LsSf https://astral.sh/uv/install.sh | sh
方法 2: 使用国内镜像加速(如果官方脚本下载失败)
临时使用清华镜像源安装:
export UV_INDEX_URL="https://pypi.tuna.tsinghua.edu.cn/simple"
curl -LsSf https://astral.sh/uv/install.sh | sh
或者临时使用阿里云镜像源:
export UV_INDEX_URL="https://mirrors.aliyun.com/pypi/simple/"
curl -LsSf https://astral.sh/uv/install.sh | sh
uvx minimax-coding-plan-mcp --help
执行命令判断是否MCP服务器已安装, 如果安装了跳到步骤 2。
方法 1: 使用默认源安装
uvx install minimax-coding-plan-mcp
方法 2: 使用国内镜像加速(如果默认源下载失败)
临时使用清华镜像源:
export UV_INDEX_URL="https://pypi.tuna.tsinghua.edu.cn/simple"
uvx install minimax-coding-plan-mcp
或者临时使用阿里云镜像源:
export UV_INDEX_URL="https://mirrors.aliyun.com/pypi/simple/"
uvx install minimax-coding-plan-mcp
cat ~/.openclaw/config/minimax.json 2>/dev/null | python3 -c "import json,sys; d=json.load(sys.stdin); print(d.get('api_key', ''))"
如果返回非空的 API Key,跳到步骤 4。
echo $MINIMAX_API_KEY
如果返回非空的 API Key,跳到步骤 3.3
直接询问用户提供 MiniMax API Key。 如果未购买MiniMax,购买地址为: https://platform.minimaxi.com/subscribe/coding-plan?code=GjuAjhGKqQ&source=link
mkdir -p ~/.openclaw/config
cat > ~/.openclaw/config/minimax.json << EOF
{
"api_key": "API密钥",
"output_path": "~/.openclaw/workspace/minimax-output"
}
EOF
将图片放到可访问路径,例如:
~/.openclaw/workspace/images/图片名.jpg使用脚本调用 MCP 服务:
python3 {curDir}/scripts/understand_image.py <图片路径或URL> "<对图片的提问>"
示例:
# 描述图片内容
python3 {curDir}/scripts/understand_image.py ~/image.jpg "详细描述这张图片的内容"
# 使用 URL
python3 {curDir}/scripts/understand_image.py "https://example.com/image.jpg "这张图片展示了什么?"
| 参数 | 说明 | 类型 |
|---|---|---|
| image | 图片路径或 URL | string (必填) |
| prompt | 对图片的提问 | string (必填) |
脚本位置:{curDir}/scripts/understand_image.py
功能:
MINIMAX_API_KEY 读取 API Key,如果没有则从 ~/.openclaw/config/minimax.json 读取understand_image 工具错误处理:
juliusbrussee/caveman
mattpocock/skills
shadcn/improve
obra/superpowers
forrestchang/andrej-karpathy-skills
vercel-labs/skills