browser

Controls a web browser to automate navigation, capture screenshots, and extract data.

3|Updated Nov 18, 2025
One-click install
npx skills add https://github.com/factory-ben/droid-browse --skill browser-factory-ben
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browser
Source: https://github.com/factory-ben/droid-browse/tree/main
Command: npx skills add https://github.com/factory-ben/droid-browse --skill browser-factory-ben

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

You need reliable, repeatable browser automation to open pages, perform multi-step actions, and extract structured information without manual clicking.

Core Features & Use Cases

  • Command live browsing: Supports navigate, act, extract, observe, screenshot, and close to complete common browsing workflows.
  • Natural-language interaction: Uses Stagehand to interpret instructions for clicking, navigation flows, and interaction goals.
  • Structured extraction: Optionally applies a JSON-to-Zod schema to return validated structured results.
  • Visual evidence: Captures screenshots after actions and returns the saved screenshot path to the user.
  • Real-world use case: Open a target website, click through to a specific item, extract key fields (e.g., title, date, and summary) into a structured response, and attach screenshots for review.

Quick Start

Ask the assistant: "Use the browser skill to navigate to https://news.ycombinator.com/ and screenshot the results."

Frequently Asked Questions about browser

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

FAQPage Schema
How do I automate web extraction and extract structured data from a live website?

Web extraction is automated by navigating to the target URL, using natural-language actions to interact with the page, and applying a JSON-to-Zod schema to return validated structured fields like titles and summaries.

Can I use natural language to control Chrome browser automation for multi-step interactions?

Yes, browser automation is driven by natural language instructions interpreted by Stagehand, allowing you to execute multi-step actions like clicking and navigating without manual scripting.

Do I need an Anthropic API key to perform AI-driven browser navigation and visual capture?

Yes, an Anthropic API key is required to power the AI-driven Stagehand control for executing browser navigation, observing page content, and capturing on-demand screenshots.

How do I take screenshots during web scraping and retrieve the saved file path?

Screenshots are captured after performing actions on the live page and saved to a configured directory, with the exact file path returned directly to the user for review.

What's the best way to observe a web page and suggest the next steps in a browsing workflow?

Using the observe command, the browser analyzes the current page state and suggests the next logical steps, helping guide complex web navigation and interaction workflows.

Does Chrome browser automation maintain a persistent profile across multiple sessions?

Yes, it manages a persistent local Chrome profile and CDP connection, ensuring that your browser state and session data remain consistent across multiple automation tasks.