← 返回 Skills 市场
Vision
作者
bytesagain4
· GitHub ↗
· v3.5.0
· MIT-0
4777
总下载
1
收藏
48
当前安装
18
版本数
在 OpenClaw 中安装
/install vision
功能描述
Resize, crop, convert, and optimize images using ImageMagick. Use when processing photos, converting formats (PNG/WebP), compressing size, or adding watermarks.
安全使用建议
Install if you want local ImageMagick-based image processing. Be careful with output paths because generated files can overwrite paths you choose, and treat the info command's EXIF output as private when working with personal photos.
能力评估
Purpose & Capability
The artifacts implement image resize, crop, format conversion, optimization, watermarking, and an image-info command using local ImageMagick/exiftool behavior; these capabilities are coherent for an image-processing skill.
Instruction Scope
Commands are user-directed and scoped to explicit input files and output paths. The script documents the info command, and the skill tags include exif, but the top-level command list does not clearly call out metadata inspection.
Install Mechanism
No installer, package mutation, hidden dependency fetch, or startup hook is present. The documented requirements are local bash and ImageMagick, with optional exiftool use if already installed.
Credentials
Reading selected image files and writing transformed outputs is proportionate. Metadata output may reveal camera model, date, and similar photo details, so users should avoid sharing info output from private photos.
Persistence & Privilege
The artifacts show no network calls, credential access, privilege escalation, background service, persistent storage, or agent behavior modification.
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 - 安装完成后，直接呼叫该 Skill 的名称或使用
/vision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
v3.5.0
Bilingual documentation and AI agent optimization
v3.4.2
v2.5 standard: Use-when desc, homepage, source, security fix
v3.4.1
manual
v3.4.0
Move ImageMagick dependency to description front (registry metadata fix)
v3.3.0
Major rewrite: domain-specific commands, Use-when description, security fixes, dependency declarations
v1.0.7
manual
v3.2.1
Add ImageMagick to Requirements
v3.2.0
Concise description (no truncation), add homepage+source metadata
v3.1.0
Security fix: safe env-var Python invocation; add Requirements section; fix description format
v3.0.1
Fix: add Requirements, fix description
v3.0.0
Major rewrite: domain-specific commands
v1.0.6
yaml-fix+quality
v1.0.5
yaml-fix+quality
v1.0.4
Quality upgrade
v1.0.3
Quality upgrade: custom functionality
v1.0.2
De-template, unique content, script cleanup
v1.0.1
Quality fix: cleaner docs, removed flags
v1.0.0
Initial release
元数据
常见问题
Vision 是什么？
Resize, crop, convert, and optimize images using ImageMagick. Use when processing photos, converting formats (PNG/WebP), compressing size, or adding watermarks. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 4777 次。
如何安装 Vision？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install vision」即可一键安装，无需额外配置。
Vision 是免费的吗？
是的，Vision 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Vision 支持哪些平台？
Vision 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？
由 bytesagain4（@xueyetianya）开发并维护，当前版本 v3.5.0。
推荐 Skills