skills.rest
duotify
duotifyOFFICIAL
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate browser tasks via the agent-browser CLI for testing and data extraction.

252|52|Updated Mar 22, 2026
Search Tags:#automation#cli#session-management#web-testing#browser#data-extraction
One-click install
npx skills add https://github.com/duotify/GitHubClawToolkit --skill agent-browser-duotify
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/duotify/GitHubClawToolkit/tree/main/skills/agent-browser
Command: npx skills add https://github.com/duotify/GitHubClawToolkit --skill agent-browser-duotify

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automate browser-based tasks for AI agents by using the agent-browser CLI to open websites, fill forms, click elements, take screenshots, and scrape data.

Core Features & Use Cases

  • Open websites and navigate pages to automate testing, data extraction, and routine web tasks
  • Fill forms, click buttons, wait for page loads, capture screenshots, and extract text
  • Support multi-session work and authentication flows with snapshot-based refs and state persistence

Quick Start

Open a website, login, and capture a full-page screenshot.

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 tasks like form filling and clicking elements?▼

You can automate browser tasks by using the agent-browser CLI to open websites, fill forms, click elements, take screenshots, and scrape data. It supports automated testing, data extraction, and routine web workflows for AI agents.

Can I persist authentication and manage multiple browser sessions for web testing?▼

Yes, you can persist authentication and manage multiple browser sessions. The tool supports multi-session work and authentication flows using snapshot-based refs and state persistence to maintain contexts for web testing.

What is the best way to extract data and capture full-page screenshots from websites?▼

The best way to extract data and capture screenshots is using a CLI tool designed for browser automation. It allows you to navigate pages, wait for loads, extract text, and capture full-page screenshots for data extraction workflows.

Does this browser automation approach support workflow automation with persistent state?▼

Yes, this browser automation approach supports workflow automation with persistent state. It handles routine web tasks and automated testing scenarios by maintaining session contexts and authentication snapshots across runs.

How do I start automating web tasks with a CLI tool?▼

To start automating web tasks, you use the CLI to open a website, login, and capture a full-page screenshot. You can structure deterministic actions using optional scripts and references directories to support workflow automation.

Related Skills

Explore More Software Engineering Skills→
haxlyshaxlys

agentcore

Run agent-browser sessions on AWS Bedrock with AWS credential resolution.

Community
Advanced
alibabaalibaba
10.5k

pdf-extractor

Extract text, tables, and metadata from PDF documents into JSON.

Official
Intermediate
MaxSaietsMaxSaiets

tmux

Send keystrokes and read pane output to control tmux sessions programmatically.

Community
Intermediate
AshesOfTheUndeadAshesOfTheUndead

Agent Browser

Automate headless browser navigation, element manipulation, and data extraction via CLI.

Community
Advanced