← 返回 Skills 市场
Vision Analyzer
作者
kawummuwe-stack
· GitHub ↗
· v1.0.1
· MIT-0
114
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install vision-analyzer
功能描述
Analyze images using Ollama Cloud's Kimi K2.5 vision capabilities. Use when user wants to describe, understand, or get information about an image. Works with...
安全使用建议
This skill's code matches its description: it reads a local image and posts it (base64) to Ollama Cloud using OLLAMA_API_KEY. Before installing, verify the skill's provenance (source/homepage missing), confirm you are comfortable sending images (potentially sensitive) to Ollama, and only provide an API key with appropriate, limited scope or a throwaway key for testing. Also ask the publisher to update the registry metadata to declare OLLAMA_API_KEY as a required env var so the permissions are transparent.
能力评估
Purpose & Capability
The skill's name, SKILL.md, and script consistently state it uses Ollama Cloud's Kimi K2.5 model to analyze images — that purpose matches the implementation. However, the registry metadata lists no required environment variables while both SKILL.md and the script require OLLAMA_API_KEY; this metadata omission is an incoherence and reduces transparency. The source/homepage are also missing, which makes provenance unclear.
Instruction Scope
Runtime instructions are narrow and consistent: run the included Python script with a local image path and optionally a prompt. The script only reads the supplied image path and the OLLAMA_API_KEY env var, base64-encodes the image, and posts it to https://ollama.com/api/generate. This is within the stated purpose, but it does transmit the full image (and prompt) to a third party — a privacy exposure users should consider.
Install Mechanism
No install spec is provided (instruction-only plus a small Python script). Nothing downloads arbitrary code at install time and no archives or external install URLs are used. The script will run with the existing python runtime; this is low install risk.
Credentials
The script legitimately requires a single API key (OLLAMA_API_KEY) to call Ollama Cloud, which is proportionate to the stated function. However, the registry metadata incorrectly lists no required env vars — a transparency issue. Also, providing that API key grants the skill (and Ollama) access to any image data you send; users should confirm acceptable data handling and token scope before supplying sensitive images or reuse of high-privilege keys.
Persistence & Privilege
The skill is user-invocable, not always-enabled, and does not attempt to change system settings, other skills, or request elevated privileges. It does not persist credentials or modify other configs.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install vision-analyzer - 安装完成后，直接呼叫该 Skill 的名称或使用
/vision-analyzer触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.1
- 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
v1.0.0
Initial release of Vision Analyzer.
- Analyze images using Kimi K2.5 multimodal vision capabilities via Ollama Cloud API.
- Supports JPG, PNG, GIF, and WebP image formats.
- Use for describing, understanding, or extracting information from images, screenshots, or diagrams.
- Simple CLI script: provide image path and optional prompt for tailored analysis.
- Returns a natural language description of image content.
元数据
常见问题
Vision Analyzer 是什么？
Analyze images using Ollama Cloud's Kimi K2.5 vision capabilities. Use when user wants to describe, understand, or get information about an image. Works with... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 114 次。
如何安装 Vision Analyzer？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install vision-analyzer」即可一键安装，无需额外配置。
Vision Analyzer 是免费的吗？
是的，Vision Analyzer 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Vision Analyzer 支持哪些平台？
Vision Analyzer 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Vision Analyzer？
由 kawummuwe-stack（@kawummuwe-stack）开发并维护，当前版本 v1.0.1。
推荐 Skills