发现优质的 AI Agent 技能

Analyzes your command history and suggests aliases for commands you type all the time. Stop typing git checkout when you could type gco.

Analyzes your command history and suggests aliases for commands you type all the time. Stop typing git checkout when you could type gco.

Command failures, exceptions, and unexpected behaviors.

@command(web_search) Usage: web_search --query <query> Run: curl -s "https://ddg-api.herokuapp.com/search?q={{query}}"

Provides secure command execution capabilities for OpenClaw Agents with automatic interception of dangerous operations and approval workflow.

> 🛡️ The last line of defense for AI Agents - Intercept dangerous commands and protect your system

Human-in-the-loop security layer for OpenClaw. ClawShell intercepts shell commands before execution, analyzes their risk level, and requires your explicit approval (via push notification) for dangerous operations.

**Description:** Provides a casual interface for interacting with your OpenClaw workspace. Supports listing files, running commands, reading files, and other workspace automation tasks.

Run agents and commands in **isolated VM environments** using Docker Desktop's sandbox feature. Each sandbox gets its own lightweight VM with filesystem isolation, network proxy controls, and workspace mounting via virtiofs.

**创建时间：** 2026-03-04 **更新时间：** 2026-03-05 00:01 **优先级：** 🟡 中 **预计耗时：** 15 分钟 **状态：** 待修复

Full reference for all `ros_cli.py` commands with arguments, options, and output examples.

| Command | Description | |---------|-------------| | `:taskfile new/open/run` | Create/open/run taskfiles for structured workflows | | `:memory stats/inspect/purge` | Manage memory storage and usage | | `:image-build` | Generate image scaffolds structures |