browserwing

Control browsers via HTTP API to navigate, interact, and extract web data.

Updated Feb 20, 2026
One-click install
npx skills add https://github.com/kbtime/openclaw-workspace --skill browserwing
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browserwing
Source: https://github.com/kbtime/openclaw-workspace/tree/main/skills/browserwing
Command: npx skills add https://github.com/kbtime/openclaw-workspace --skill browserwing

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automate complex browser interactions and data extraction without manual UI testing, reducing time to insight and increasing reliability of web workflows.

Core Features & Use Cases

  • HTTP API driven browser control: navigate pages, interact with elements (click, type, select), take screenshots, run JavaScript, and perform batch operations.
  • Data extraction & accessibility: obtain text, attributes, and accessibility snapshots for QA, scraping, and auditing.
  • Batch workflows: chain multiple actions in sequence to automate end-to-end web tasks across apps and environments.

Quick Start

Navigate to a URL and extract the page title and all hyperlink targets.

Frequently Asked Questions about browserwing

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

FAQPage Schema
How do I automate browser interactions and extract data from web pages via HTTP?

Browser automation via HTTP API allows you to automate browser control to navigate, interact, and extract data from web pages by sending HTTP requests to a configurable executor URL with header-based authentication.

Can I run JavaScript and take screenshots during web scraping workflows?

Yes, you can run JavaScript and take screenshots during web scraping workflows. The HTTP API supports executing JavaScript on web pages and capturing screenshots alongside navigation, clicking, typing, and text extraction operations.

What do I need to set up before using an HTTP API for browser automation?

To use HTTP API browser automation, you need a configurable executor URL and header-based authentication credentials configured. These prerequisites allow the API to securely process navigation, interaction, and data extraction commands.

How do I chain multiple browser actions together for end-to-end web testing?

You can chain multiple browser actions together for end-to-end web testing using batch workflows. This feature sequences multiple operations like navigate, click, type, and extract to automate complex tasks across modern web apps.

Does browser automation support accessibility auditing and snapshots?

Yes, browser automation supports accessibility auditing and snapshots. The HTTP API can obtain text, attributes, and accessibility snapshots from web pages, enabling QA testing, scraping, and auditing across modern web apps.

What's the best way to extract page titles and hyperlink targets from a URL?

The best way to extract page titles and hyperlink targets is using the HTTP API to navigate to a URL and extract the desired data. This automated approach reduces manual UI testing time and increases workflow reliability.