agent-browser

Automate browser navigation, element interaction, and data extraction via CDP.

Updated Oct 29, 2013
One-click install
npx skills add https://github.com/whywaita/dotfiles --skill agent-browser-whywaita
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/whywaita/dotfiles/tree/main/dot_codex/skills/agent-browser
Command: npx skills add https://github.com/whywaita/dotfiles --skill agent-browser-whywaita

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Web automation tasks often require manual, repetitive browser interactions for testing, form filling, and data extraction. This skill automates browser actions to perform common work tasks across multiple pages, increasing reliability and speed.

Core Features & Use Cases

  • Open and navigate pages: navigate to URLs, back, forward, reload, and close.
  • Snapshot and interact: snapshot interactive elements and interact with them via refs or semantic locators to perform clicks, fills, typing, etc.
  • Data extraction and validation: retrieve text, attributes, and page data, and wait for conditions.
  • Screenshots, debugging, and recordings: take screenshots, record sessions, and debug with console and errors.
  • Parallel sessions and templates: run multiple sessions, reuse state, and leverage templates.

Quick Start

Open a URL, snapshot elements, and begin automating browser tasks using agent-browser.

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 interactions for web testing and form filling?

Automate browser interactions using npx agent-browser with CDP integration to navigate pages, snapshot interactive elements, and perform clicks, fills, and typing for reliable web testing.

How does browser automation handle element refs and semantic locators?

Browser automation snapshots interactive elements and interacts with them via element refs or semantic locators, enabling precise clicks, fills, typing, and hover actions across repeatable sessions.

Can I run parallel browser automation sessions and reuse state?

Yes, browser automation supports running multiple parallel sessions, reusing state, and leveraging templates to execute web testing and data extraction tasks across repeatable sessions efficiently.

What's the best way to capture screenshots and debug web automation sessions?

Capture screenshots, record sessions, and debug web automation using built-in console and error utilities, applying to developers and testers who need reliable browser debugging.

How do I extract data and wait for conditions during browser automation?

Extract data and validate pages during browser automation by retrieving text, attributes, and page data, and applying wait conditions to ensure elements are ready before interaction.

Do I need any external dependencies to run browser automation with npx?

No external dependencies are required to run browser automation, as the skill operates via npx agent-browser and CDP integration, enabling navigation, snapshotting, and element interaction without setup.