闲社服务运行正常AI智能体自动化平台
客户端下载帮助中心服务商入驻
免费注册
技能集市 > AI智能 > minimax-cp
m

MiniMax搜索识图

技能标识：minimax-cp

使用 MiniMax Coding Plan API 进行网页搜索和图像理解。当用户要求搜索信息、查找资料、或者询问实时内容时使用搜索功能；当用户要求识图、分析图片、描述图片内容时使用 understand_image 功能。触发词：搜索、查找、search、look up、识图、分析图片、图片里是什么

作者：admin | 来源记录：ClawHub
下载
登记来源
ClawHub
版本
V 1.2.0
检测标记
后台标记通过
免费
免费获取
0
收藏
来源与检测标记为平台登记信息，并不代表已展示可复核的检测报告。使用前请核对版本、依赖和所需权限，建议先在隔离环境中运行。
概述
安装方式
版本历史

MiniMax搜索识图

MiniMax 网页搜索与图像理解

使用 MiniMax Coding Plan MCP 进行网页搜索和图像理解。

搜索

bash
python3 scripts/mmsearch.py <搜索关键词>

识图

bash
python3 scripts/mmvision.py <提示词> <图片路径或URL>

支持的图片格式：JPEG, PNG, WebP

示例：
bash

描述图片内容


python3 scripts/mmvision.py 描述这张图片 /path/to/image.png

提取图片中的文字

python3 scripts/mmvision.py 提取图片中的所有文字 https://example.com/image.jpg

分析图片内容

python3 scripts/mmvision.py 这张图片里有什么？ image.jpg

脚本说明

  • - scripts/mmsearch.py — 调用 websearch 工具
  • scripts/mmvision.py — 调用 understandimage 工具

依赖：

  • - uvx (Python 包运行器)
  • minimax-coding-plan-mcp
  • MINIMAXAPIKEY 环境变量（已内置在脚本中）

标签

skill ai

通过对话安装

以下为平台配置的接入选项，并非逐项实测通过。能否安装取决于客户端支持、技能来源和运行环境：

OpenClaw WorkBuddy QClaw Kimi Claude

方式一：安装 SkillHub 和技能

帮我安装 SkillHub 和 minimax-cp-1776184862 技能

方式二：设置 SkillHub 为优先技能安装源

设置 SkillHub 为我的优先技能安装源，然后帮我安装 minimax-cp-1776184862 技能

通过命令行安装

skillhub install minimax-cp-1776184862

下载

⬇ 下载 minimax-cp v1.2.0（免费）

文件大小: 3.82 KB | 发布时间: 2026-4-17 15:24

v1.2.0 最新 2026-4-17 15:24
Version 1.2.0

- 新增中文文档，详细说明了搜索与图像理解两大功能。
- 提供典型命令行用法示例，涵盖图片描述、文字提取、内容分析。
- 明确支持图片格式：JPEG、PNG、WebP。
- 列出了依赖项与 API Key 设置要点。
- 指明各脚本功能和触发词。

相关推荐

s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
返回顶部