Skip to main content
ClaudeWave
Skill11.2k repo starsupdated 4d ago

safe-file-deletion

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.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/MemTensor/MemOS /tmp/safe-file-deletion && cp -r /tmp/safe-file-deletion/apps/openwork-memos-integration/apps/desktop/skills/safe-file-deletion ~/.claude/skills/safe-file-deletion
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

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

Multiple files (batched into one prompt):
```json
{
  "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.
backend-devSubagent

MemOS backend / library implementation sub-agent. Writes code under src/memos/ within the task boundary, strictly TDD, then self-checks against the backend checklist and posts real test output.

code-reviewerSubagent

Code-review sub-agent. Reviews MemOS diffs for contract consistency, Ruff / typing / optional-dependency handling, and test evidence; returns APPROVE or CHANGES_REQUESTED.

design-reviewerSubagent

Design-review sub-agent. Reviews design docs across the four dimensions of architecture, interface, performance, and security, covering MemOS's multi-memory / multi-storage backend constraints.

explorerSubagent

Read-only code exploration sub-agent. Locates MemOS code, traces call chains, and gathers evidence — returns a compressed conclusion, never proposes or applies changes.

integration-testerSubagent

MemOS integration-testing sub-agent. Authors and executes pytest cases under tests/ based on the task's requirements and design, and emits real test reports.

memos-localSkill

|

browserwing-adminSkill

Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.

browserwing-executorSkill

Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.