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 > vision-analyzer
v

视觉分析器

技能标识：vision-analyzer

|

作者：admin | 来源记录：ClawHub
下载
登记来源
ClawHub
版本
V 1.0.1
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

视觉分析器

视觉分析器

通过Ollama云API，利用Kimi K2.5多模态视觉能力分析图像。

使用场景

  • - 用户想知道图像中的内容
  • 描述截图或照片
  • 理解UI元素、图像中的文字
  • 分析表情包、图表、示意图

快速开始

bash
python3 ~/.openclaw/workspace/skills/vision-analyzer/scripts/vision_analyze.py <图片路径> [提示词]

示例

描述一张图片：
bash
python3 ~/.openclaw/workspace/skills/vision-analyzer/scripts/vision_analyze.py photo.jpg

提出具体问题：
bash
python3 ~/.openclaw/workspace/skills/vision-analyzer/scripts/vision_analyze.py screenshot.png 你看到了哪些UI元素？

常见图片存放位置

  • - 下载目录：/mnt/chromeos/MyFiles/Downloads/
  • 截图目录：/mnt/chromeos/MyFiles/Downloads/
  • 用户主目录：~/

配置

将你的Ollama API密钥设置为环境变量：

bash
export OLLAMAAPIKEY=你的API密钥

从ollama.com/settings获取你的API密钥

API配置

该技能使用Ollama云API，搭载Kimi K2.5模型。
API密钥从OLLAMAAPIKEY环境变量中读取。

支持的格式

  • - JPG/JPEG
  • PNG
  • GIF
  • WebP

输出

返回图像内容的自然语言描述。

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 vision-analyzer-1775729940 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 vision-analyzer-1775729940 技能

通过命令行安装

skillhub install vision-analyzer-1775729940

下载

⬇ 下载 vision-analyzer v1.0.1（免费）

文件大小: 2.51 KB | 发布时间: 2026-4-11 23:03

v1.0.1 最新 2026-4-11 23:03
- Added new documentation outlining how to analyze images with Ollama Cloud's Kimi K2.5 vision model
- Explained typical use cases, configuration steps, and supported image formats
- Provided command-line examples for running image analysis and asking targeted questions
- Clarified API key setup and expected output

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User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task.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