← 返回 Skills 市场
lnj22

file-organizer

作者 lnj22 · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ⚠ suspicious
73
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install organize-messy-files-file-organizer
功能描述
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automatin...
安全使用建议
This skill is coherent for local file organization, but it will scan and (with your approval) move or rename files in whatever directories you point it at — so: 1) only run it on directories you trust the agent to access, 2) request and review the full proposed plan before allowing any mv/rename/delete operations, 3) back up important data (or test on a small folder) before large-scale changes, 4) prefer a dry-run / logging mode to verify actions and ensure preservation of timestamps, and 5) be cautious about sharing outputs that include filenames or paths if you use a cloud-hosted model (these reveal potentially sensitive metadata).
功能分析
Type: OpenClaw Skill Name: organize-messy-files-file-organizer Version: 0.1.0 The 'file-organizer' skill utilizes broad filesystem access and shell commands (find, mv, mkdir, md5) to manage and delete files across the user's home directory. While these capabilities are aligned with its stated purpose, the instructions in SKILL.md lack explicit input sanitization for user-provided directory paths, creating a potential risk for shell injection. According to the provided criteria, tools with high-risk capabilities (shell/file access) that are plausibly needed for their function should be classified as suspicious.
能力评估
Purpose & Capability
Name/description align with the runtime instructions: the SKILL.md uses standard filesystem commands (ls, find, du, file, md5, mv, mkdir) to analyze, suggest, and move files. Nothing requested (no env vars, no installs) is unexpected for a local file-organizing assistant.
Instruction Scope
Instructions instruct the agent to scan and operate on whichever directory the user selects (examples use ~, Downloads, Documents, etc.). The skill also says it will use 'content' to make decisions; the provided commands mainly inspect metadata and compute hashes, but an agent following these instructions could be asked to read deeper into files. The SKILL.md does require the agent to run filesystem-modifying commands (mv, mkdir) after explicit user approval and to log moves; it correctly emphasizes asking before deletes.
Install Mechanism
Instruction-only skill with no install spec and no code files. This is lowest-risk from an install perspective — nothing is written to disk by an installer.
Credentials
No environment variables, credentials, or config paths are requested (proportionate). However, the skill will read filenames, sizes, dates, and compute hashes across the chosen directories — this can expose sensitive filenames/metadata (and potentially file content if the agent is directed to inspect files for context).
Persistence & Privilege
always is false and the skill has no install or self-modifying behavior. It does not request persistent privileges or modify other skills' configs.
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 organize-messy-files-file-organizer
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /organize-messy-files-file-organizer 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
v0.1.0
Bulk publish from all-task-skills-dedup
元数据
Slug organize-messy-files-file-organizer
版本 0.1.0
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

file-organizer 是什么?

Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automatin... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 73 次。

如何安装 file-organizer?

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

file-organizer 是免费的吗?

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

file-organizer 支持哪些平台?

file-organizer 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 file-organizer?

由 lnj22(@lnj22)开发并维护,当前版本 v0.1.0。

💬 留言讨论