Resize, crop, convert, and optimize images using ImageMagick. Use when processing photos, converting formats (PNG/WebP), compressing size, or adding watermarks.
数据来源：ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一：命令行安装（推荐）
推荐（无需提前安装 clawhub）
npx clawhub@latest --dir ~/.claude/skills install vision或使用 clawhub CLI（需提前安装）
clawhub --dir ~/.claude/skills install vision⚠️ 需要 Node.js 18+，没有 Node？请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二：手动下载安装（无需 Node）
下载 ZIP，解压后将文件夹放到以下路径，重启 Agent 即可：
安装路径
~/.claude/skills/vision/💡解压后将文件夹放到上方路径，重启 Agent 即可生效
--- name: "Vision — Image Processing, Resize, Convert & Watermark" description: "Resize, crop, convert, and optimize images using ImageMagick. Use when processing photos, converting formats (PNG/WebP), compressing size, or adding watermarks." version: "3.5.0" author: BytesAgain homepage: https://bytesagain.com source: https://github.com/bytesagain/ai-skills tags: ["vision", "image-processing", "resize", "crop", "convert", "optimize", "exif", "watermark", "图像处理"] ---
Image processing toolkit powered by ImageMagick.
Just ask your AI assistant: / 直接告诉 AI 助手：
Resize an image.
bash scripts/script.sh resize --input photo.jpg --width 800
bash scripts/script.sh resize --input photo.jpg --percent 50Change image formats.
bash scripts/script.sh convert --input photo.png --to webp
bash scripts/script.sh convert --input photo.jpg --to pngCompress file size without losing quality.
bash scripts/script.sh optimize --input photo.jpg --quality 80Add text watermark to images.
bash scripts/script.sh watermark --input photo.jpg --text "© 2025" --position southeasthttps://bytesagain.com/feedback/ Powered by BytesAgain | bytesagain.com
安装 Vision 后，可以对 AI 说这些话来触发它
Help me get started with Vision
Explains what Vision does, walks through the setup, and runs a quick demo based on your current project
Use Vision to resize, crop, convert, and optimize images using ImageMagick
Invokes Vision with the right parameters and returns the result directly in the conversation
What can I do with Vision in my marketing & growth workflow?
Lists the top use cases for Vision, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/vision/ 目录（个人级，所有项目可用），或 .claude/skills/vision/（项目级）。重启 AI 客户端后，用 /vision 主动调用，或让 AI 根据上下文自动发现并使用。
Vision 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。
Vision 可免费安装使用。请查阅仓库了解许可证信息。
Resize, crop, convert, and optimize images using ImageMagick. Use when processing photos, converting formats (PNG/WebP), compressing size, or adding watermarks.
Vision 属于「Marketing & Growth」分类，该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my marketing & growth tasks using Vision
Identifies repetitive steps in your workflow and sets up Vision to handle them automatically