发现优质的 AI Agent 技能

Headless browser automation using Podman + Playwright for scraping JavaScript-rendered pages.

Backup & Recovery Automation for OpenClaw using rClone

Sistema automatizado de backup y recuperación para OpenClaw usando rClone. Backups diarios a Google Drive con rotación de 20 días.

**Twitter/X data access and automation for autonomous agents. Powered by AIsa.**

Pull metrics from multiple sources, generate branded reports, and auto-deliver to clients. Built for agencies and freelancers who need consistent, professional reporting without manual work.

CamoFox MCP gives OpenClaw agents a production-ready anti-detection browser automation toolkit over MCP HTTP transport. It connects OpenClaw to CamoFox Browser so agents can browse, click, type, extract content, manage cookies/sessions, run stealth search workflows, and download resources without the high block rates common with standard automation stacks.

> **Author:** Community Contributors > > ⚠️ **DISCLAIMER — PERSONAL USE ONLY** > This skill is provided for **personal, non-commercial use only**. It automates your own LinkedIn account for personal productivity and engagement. Do NOT use this skill for spam, mass outreach, scraping other users' data, or any commercial automation service. Use responsibly and in accordance with [LinkedIn's User Agreement](https://www.linkedin.com/legal/user-agreement). The author assumes no liability for misuse o

OpenClaw skill for ML-powered DOM snapshots - 95% token reduction for browser automation

Browser automation powered by Playwright MCP server. Control Chrome, Firefox, or WebKit programmatically.

A comprehensive web automation skill for OpenClaw that provides 30+ browser actions including navigation, data extraction, form filling, screenshot capture, PDF generation, file handling, and advanced web scraping capabilities.

> **CRITICAL RULES — VIOLATIONS WILL BREAK THE WORKFLOW:** > > 1. **Never run midscene commands in the background.** Each command must run synchronously so you can read its output (especially screenshots) before deciding the next action. Background execution breaks the screenshot-analyze-act loop. > 2. **Run only one midscene command at a time.** Wait for the previous command to finish, read the screenshot, then decide the next action. Never chain multiple commands together. > 3. **Allow enough

> **CRITICAL RULES — VIOLATIONS WILL BREAK THE WORKFLOW:** > > 1. **Never run midscene commands in the background.** Each command must run synchronously so you can read its output (especially screenshots) before deciding the next action. Background execution breaks the screenshot-analyze-act loop. > 2. **Run only one midscene command at a time.** Wait for the previous command to finish, read the screenshot, then decide the next action. Never chain multiple commands together. > 3. **Allow enough