agent-browser

agent-browser equips Claude with the ability to interact with web browsers, enabling automated testing, screenshot capture, and page validation. This skill extends Claude's capabilities to handle real-world web automation tasks directly within your workflow.

agent-browser is a browser automation tool that equips Claude with the ability to interact with web browsers for automated testing, screenshot capture, and page validation. It extends Claude's capabilities to handle real-world web automation tasks directly within your workflow, enabling you to automate browser interactions and web page testing without manual intervention.

AI-generated summary based on this skill's SKILL.md

★ 26 ⁮ 3 MIT updated 2026-02-10 by joneqian

Install

joneqian/claude-skills-suite/agent-brower · repository language: HTML

Manual (git clone) CLI (skillfed)coming soon

git clone https://github.com/joneqian/claude-skills-suite
cp -r claude-skills-suite/skills/agent-brower ~/.claude/skills/agent-brower

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

What is agent-browser and what can it do?

Can agent-browser fill forms and extract data from websites?

Yes, agent-browser supports filling forms and extracting data from websites as a core capability. You can use agent-browser to programmatically populate web forms with data and retrieve information from web pages, making it ideal for automated data collection and form submission workflows.

How does agent-browser help with automated website testing?

agent-browser enables automated website testing by allowing you to navigate and interact with web elements programmatically, take screenshots of web pages, and validate page content. You can test web applications with automated workflows, click and interact with web elements, and capture visual evidence of test results—all without manual browser interaction.

What are the main use cases for web scraping and form filling with agent-browser?

agent-browser supports web scraping and form filling for tasks such as extracting data from web pages, automating browser clicks, filling web forms automatically, and navigating websites programmatically. These capabilities make agent-browser suitable for data collection, automated testing, and workflow automation that requires real-time web page interaction.

Can agent-browser take screenshots of websites and capture web page content?

Yes, agent-browser includes screenshot automation functionality that allows you to take screenshots of websites and capture web page content. This capability is useful for visual testing, documentation, and validating that web pages render correctly during automated testing workflows.

What license does agent-browser use?

agent-browser is released under the MIT license, which is a permissive open-source license that allows you to use, modify, and distribute the tool freely with minimal restrictions.

SKILL.md

rendered from the published skill — quoted content, verbatim

Browser Automation with agent-browser

Installation

npm (recommended)

npm install -g agent-browser
agent-browser install  # Download Chromium

Quick start

agent-browser open &lt;url&gt;        # Navigate to page
agent-browser snapshot -i       # Get interactive elements with refs
agent-browser click @e1         # Click element by ref
agent-browser fill @e2 "text"   # Fill input by ref
agent-browser close             # Close browser

Core workflow

Navigate: agent-browser open <url>
Snapshot: agent-browser snapshot -i (returns elements with refs like @e1, @e2)
Interact using refs from the snapshot
Re-snapshot after navigation or significant DOM changes

Commands

Navigation

```bash agent-browser open <url> # Navigate to URL agent-browser back # Go back agent-browser forward # Go forward agent-browser

(truncated - see the full file via the links below)

Read as markdown · JSON record · Browse the source repository

File tree — 1 file

skills/agent-brower/SKILL.md

All skills by joneqian → Best browser automation skills for AI agents - SkillFed →