← 返回 Skills 市场
578499893

clean-desktop

作者 578499893 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
331
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install clean-desktop
功能描述
自动分类移动桌面文件到图片、文档、压缩包文件夹,支持预览模式避免实际修改。
使用说明 (SKILL.md)

桌面清理大师\r

描述\r

自动整理用户桌面文件,按图片、文档、压缩包等类型分类归档。\r \r

工具\r

  • bash: 执行文件操作命令\r
  • read: 读取桌面文件列表\r \r

参数\r

  • dry_run: 布尔值,默认为true。如果为true,只预览不实际操作。\r \r

执行流程\r

  1. 获取桌面路径(Windows为~/Desktop,Mac/Linux为~/Desktop)\r
  2. 列出所有文件(排除.DS_Store和快捷方式)\r
  3. 按扩展名分类:\r
    • 图片:.jpg, .png, .gif → 移入桌面/图片文件夹\r
    • 文档:.pdf, .docx, .txt → 移入桌面/文档文件夹\r
    • 压缩包:.zip, .rar → 移入桌面/压缩包文件夹\r
  4. 生成操作报告,告知用户移动了哪些文件\r \r

安全提示\r

  • 操作前检查目标文件夹是否存在,不存在则自动创建\r
  • 不处理隐藏文件(以.开头的文件)\r
  • 不删除任何文件,只做移动操作\r
安全使用建议
This skill appears to do what it claims: preview or move files on your Desktop into folders by type. Before installing or enabling autonomous use, test it with dry_run=true and review the generated report; verify the Desktop path and localized folder names on your platform (Windows typically uses C:\Users\<User>\Desktop, not ~/Desktop). Ensure you have backups or use dry-run to avoid accidental moves, and confirm permissions for moving files. If you plan to allow autonomous invocation, be comfortable the agent can perform file moves when triggered — otherwise keep it user-invocable only.
功能分析
Type: OpenClaw Skill Name: clean-desktop Version: 1.0.0 The skill bundle requests high-risk capabilities (bash) to perform file operations on the user's desktop, which is a significant attack surface if filenames are not properly sanitized. Additionally, the bundle contains an entirely unrelated and detailed project planning document (project-planning.md) including SQL schemas for a web application, which is highly anomalous for a desktop cleanup utility and suggests either a packaging error or potential information leakage.
能力评估
Purpose & Capability
Name/description match the requested capabilities: classifying and moving desktop files by extension. There are no unrelated environment variables, binaries, or installs requested.
Instruction Scope
SKILL.md limits itself to listing and moving desktop files and generating a report, and includes a dry_run option. Minor issues: it assumes the Desktop path as ~/Desktop for Windows (which is inaccurate on many Windows systems), uses folder names in Chinese (may not exist), and doesn't specify exact shell commands or how shortcuts/symlinks are handled. These are implementation/portability gaps rather than scope creep or data-exfiltration.
Install Mechanism
No install spec or code is provided (instruction-only), so nothing will be downloaded or written to disk by an installer. Lowest-risk category for install behavior.
Credentials
No environment variables, credentials, or config paths are requested. The operations require only filesystem access to the user's Desktop, which is proportionate to the task.
Persistence & Privilege
always is false and there is no request to modify other skills or system-wide settings. The skill does not request permanent presence or extra privileges beyond moving files when invoked.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install clean-desktop
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /clean-desktop 触发
  4. 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
v1.0.0
Initial release of clean-desktop 1.0.0: - Automatically organizes desktop files into folders by type (Images, Documents, Archives). - Supports preview mode with dry_run parameter (doesn't actually move files unless set to false). - Ignores hidden files and shortcuts, and doesn't delete any files. - Ensures destination folders are created as needed before moving files. - Provides a report listing which files were moved.
元数据
Slug clean-desktop
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

clean-desktop 是什么?

自动分类移动桌面文件到图片、文档、压缩包文件夹,支持预览模式避免实际修改。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 331 次。

如何安装 clean-desktop?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install clean-desktop」即可一键安装,无需额外配置。

clean-desktop 是免费的吗?

是的,clean-desktop 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

clean-desktop 支持哪些平台?

clean-desktop 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 clean-desktop?

由 578499893(@578499893)开发并维护,当前版本 v1.0.0。

💬 留言讨论