跳到正文
cccskills
免费在 GitHub 公开

safe-file-deletion

Adds an explicit permission step before an agent deletes files or directories. It covers shell commands and deletion scripts, groups multiple files into one request, and requires the agent to stop when permission is denied.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Enforces explicit user permission before any file deletion. Activates when you're about to use rm, unlink, fs.rm, or any operation that removes files from disk. MUST be followed for all delete operations.

查看安装方法

适用场景

  • Confirming permission before deleting files
  • Reviewing multiple deletions in one request
  • Adding approval steps to cleanup scripts

包含的文件(1)

  • SKILL.md1.1 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Safe File Deletion

Rule

Before deleting ANY file, you MUST:

  1. Call request_file_permission with operation: "delete"
  2. For multiple files, use filePaths array (not multiple calls)
  3. Wait for response
  4. Only proceed if "allowed"
  5. If "denied", acknowledge and do NOT delete

Applies To

  • rm commands (single or multiple files)
  • rm -rf (directories)
  • unlink, fs.rm, fs.rmdir
  • Any script or tool that deletes files

Examples

Single file:

{
  "operation": "delete",
  "filePath": "/path/to/file.txt"
}

Multiple files (batched into one prompt):

{
  "operation": "delete",
  "filePaths": ["/path/to/file1.txt", "/path/to/file2.txt"]
}

No Workarounds

Never bypass deletion warnings by:

  • Emptying files instead of deleting
  • Moving to hidden/temp locations
  • Using obscure commands

The user will see a prominent warning. Wait for explicit approval.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Lets an agent ask for clarification, preferences, or approval through an on-screen dialog. Questions can offer single or multiple choices and custom text input, giving the agent a user response to guide its next step.

中文简介正在准备中。当前显示英语简介。

  • Clarifying an ambiguous task
  • Choosing how to organize files
  • Confirming deletion or email sending
MemTensor/MemOS1.2万2026年10月17日 更新

Configure and manage BrowserWing to create, save, and replay browser automation scripts. Use AI exploration to generate repeatable workflows, export scripts as SKILL.md files for agents, and diagnose service or execution problems.

中文简介正在准备中。当前显示英语简介。

  • Setting up BrowserWing and its AI model connection
  • Generating reusable scripts through AI website exploration
  • Exporting browser scripts as SKILL.md files
MemTensor/MemOS1.2万2026年10月17日 更新

Automate browser tasks through BrowserWing's HTTP API, from navigation and form filling to extracting search results. Inspect page structure to identify controls, capture screenshots, and run multiple actions in sequence.

中文简介正在准备中。当前显示英语简介。

  • Filling and submitting web forms
  • Extracting search results and links
  • Capturing screenshots and inspecting page structure
MemTensor/MemOS1.2万2026年10月17日 更新

Automate website navigation, form filling, data extraction, and web app checks while keeping page state between scripts. Use a new Chromium session or connect to an existing Chrome session through an extension.

中文简介正在准备中。当前显示英语简介。

  • Completing workflows in an existing signed-in Chrome session
  • Filling forms and extracting website data
  • Checking web app behavior and capturing screenshots
MemTensor/MemOS1.2万2026年10月17日 更新

Set up, configure, update, and troubleshoot persistent memory for OpenClaw agents. The plugin stores conversations locally and supports automatic recall, task summaries, reusable skills derived from successful tasks, and a visual memory manager.

中文简介正在准备中。当前显示英语简介。

  • Setting up persistent memory for OpenClaw
  • Updating or troubleshooting the memory plugin
  • Choosing local or external memory search models
MemTensor/MemOS1.2万2026年10月17日 更新

Use MemOS Local to find past conversations, preferences, and decisions, then retrieve original messages or task context. The skill also guides sharing memories and reusable procedures with local agents or a configured team.

中文简介正在准备中。当前显示英语简介。

  • Find preferences and decisions from past conversations
  • Read original messages and surrounding dialogue
  • Share memories with local agents or a team
MemTensor/MemOS1.2万2026年10月17日 更新

查看 MemTensor 的全部技能

报告此技能的问题