发现优质的 AI Agent 技能

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.

This skill provides a single Node CLI with subcommands:

Common browser automation workflows using the `browse` CLI. Each example demonstrates a distinct pattern using real commands.

Use the `weathercli` command to retrieve weather information for any location worldwide.

This skill uses the `pandoc` command-line utility to convert documents between numerous markup formats.

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

This skill translates natural language queries into `crunch-cli` CLI commands and formats outputs for various mediums.

This skill translates natural language queries into `crunch-cli` CLI commands and formats outputs for various mediums.

Translates natural language queries into `crunch-cli` commands. Supports profiles and output formatting for Slack, Telegram, Discord, or plain text.

Run installation commands only after explicit user approval.

Quick reference for all OpenClaw CLI diagnostic and troubleshooting commands.

Quick reference for all OpenClaw CLI diagnostic and troubleshooting commands.