agent-browser

Provides on-demand, batched, and scheduled delivery of news digests via email or RSS.

1|Updated Jan 20, 2026
One-click install
npx skills add https://github.com/sorafujitani/claudedot --skill agent-browser-sorafujitani
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/sorafujitani/claudedot/tree/main/skills/agent-browser
Command: npx skills add https://github.com/sorafujitani/claudedot --skill agent-browser-sorafujitani

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates browser interactions for web testing, form filling, screenshots, and data extraction. This enables users to navigate websites, interact with pages, fill forms, capture screenshots, test applications, and extract information from web pages.

Core Features & Use Cases

  • Automates browser interactions: navigate pages, click elements, fill forms, and capture screenshots across websites.
  • Snapshot and element references: generate and use element refs to interact reliably.
  • Parallel sessions: run multiple browser instances concurrently for cross-site testing.
  • Waits and synchronization: wait for elements, text, or network idle to ensure stability.
  • Get information and debugging: query page title, URL, texts, and element values; view console and errors.

Quick Start

Open a URL with the tool, take an initial snapshot to identify interactive elements, and begin interacting using the element refs.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate browser testing and form filling without writing complex scripts?

Automating browser testing and form filling is done by navigating to a URL, taking an initial snapshot to identify interactive elements, and interacting using generated element refs to reliably fill forms and capture screenshots.

How do I extract data from web pages using semantic locators?

Data extraction from web pages is handled by generating element snapshots and using semantic locators or element refs to reliably query page texts, titles, URLs, and element values across websites.

Can I run multiple browser sessions concurrently for cross-site web testing?

Yes, you can run parallel browser sessions concurrently to execute cross-site web testing, utilizing optional session management to handle multiple browser instances at the same time.

How do I wait for network idle or specific elements during web automation?

Waiting for network idle or specific elements during web automation is managed through built-in waits and synchronization commands that pause execution until elements, text, or network activity stabilize.

What is the best way to capture screenshots during automated web navigation?

Capturing screenshots during automated web navigation is accomplished by directing the browser to navigate pages and issuing a screenshot capture command to record the current state of the web application.

How do I get debugging information like console errors from an automated browser session?

Debugging information from an automated browser session is retrieved by querying the page title, URL, texts, and element values, and by viewing console logs and errors directly through the tool's commands.