skills.rest
xiaomochn
xiaomochnCOMMUNITY
Explore all skills by this author →
GitHub

browser-automation

Automate web browser navigation, element interaction, and JavaScript execution via HTTP API.

198|40|Updated Mar 6, 2026
Search Tags:#automation#navigation#web scraping#form filling#browser#http api
One-click install
npx skills add https://github.com/xiaomochn/AndroidForClaw --skill browser-automation-xiaomochn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser-automation
Source: https://github.com/xiaomochn/AndroidForClaw/tree/main/extensions/BrowserForClaw/skill
Command: npx skills add https://github.com/xiaomochn/AndroidForClaw --skill browser-automation-xiaomochn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates web browser interactions, allowing AI agents to navigate websites, fill forms, extract data, and perform other online tasks programmatically.

Core Features & Use Cases

  • Web Navigation: Open any URL and wait for pages to load.
  • Element Interaction: Click, type, hover, and select options within web pages using CSS selectors.
  • Data Extraction: Retrieve page content (text, HTML), screenshots, and cookies.
  • Use Case: An AI can use this skill to research product prices across multiple e-commerce sites, fill out online application forms, or monitor website changes.

Quick Start

Use the browser-automation skill to navigate to https://www.google.com and search for 'AI agents'.

Frequently Asked Questions about browser-automation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate web browser control for an AI agent?▼

Automate web browser control by using an HTTP API to send navigation, element manipulation, and JavaScript execution commands from your AI agent to a running browser instance. This enables programmatic interaction with web pages without manual input.

Can I use an HTTP API to fill out online forms automatically?▼

Yes, you can fill out online forms automatically by targeting web page elements with CSS selectors. The HTTP API allows your agent to type text, click buttons, and select options within any web form programmatically.

What is the best way to extract page content and cookies for web scraping?▼

Extract page content and cookies for web scraping by executing HTTP API commands to retrieve raw HTML, visible text, and session cookies. You can also capture screenshots to visually verify the extracted data.

Do I need a running browser instance to perform web navigation and interaction?▼

Yes, you need a running browser instance with an active HTTP server. The automation skill sends HTTP API requests to this server to execute navigation, element interaction, and data extraction tasks.

How do I handle authentication via cookies when automating browser tasks?▼

Handle authentication via cookies by retrieving and managing cookie data through the HTTP API. This allows your AI agent to maintain authenticated sessions across multiple web navigation and form filling workflows.

Are there limitations when using CSS selectors for element interaction?▼

Element interaction via CSS selectors requires accurately defined selectors for the target page. If the website structure changes dynamically or relies on shadow DOM, your web scraping and form filling automation scripts may fail to locate elements.

Related Skills

Explore More Software Engineering Skills→
steelan9199steelan9199
9

chrome-devtools-skill

Automate browser interactions and extract data via the Chrome DevTools Protocol.

Community
Advanced
alibabaalibaba
10.5k

pdf-extractor

Extract text, tables, and metadata from PDF documents into JSON.

Official
Intermediate
AllBeingsFutureAllBeingsFuture
9

browser-get-content

Extract page or element text from a webpage using an optional CSS selector.

Community
Basic
web-infra-devweb-infra-dev
286

Browser Automation

Automate web browser interactions using visual cues from screenshots.

Official
Intermediate