agent-browser

Automate browser interactions for testing, form filling, screenshots, and data extraction.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/fancive/claude-skills --skill agent-browser-fancive
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/fancive/claude-skills/tree/main/skills/agent-browser
Command: npx skills add https://github.com/fancive/claude-skills --skill agent-browser-fancive

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates browser interactions for testing, form filling, screenshots, and data extraction.

Core Features & Use Cases

  • Snapshot-based element refs to minimize data sent to AI agents
  • Bash-based command surface for navigation, interaction, and data capture
  • Session management and references to documentation for reusable workflows

Quick Start

Open a URL with agent-browser open <url>, take a snapshot to create refs, and begin interacting using the generated @e 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 interactions for web testing and data extraction using Bash?

Browser automation for web testing and data extraction is handled through Bash commands using agent-browser. You can navigate URLs, fill forms, take screenshots, and capture data by executing Bash agent-browser tools across websites and intranets.

What is snapshot-based element ref management and how does it work for browser automation?

Snapshot-based element refs minimize the data sent to AI agents during browser automation. You open a URL, take a snapshot to create refs, and then interact with page elements using the generated @e refs, reducing overhead in automated workflows.

Can I use Bash agent-browser for automated form filling and screenshots on intranet sites?

Yes, Bash agent-browser supports automated form filling and screenshots across websites and intranets. It manages browser sessions and uses element refs to interact with internal pages, making it suitable for web QA and data collection workflows.

Do I need any specific dependencies or environment setup to run agent-browser automation scripts?

No external dependencies are required to run agent-browser automation scripts. You only need a valid SKILL.md frontmatter with a name and description, and optionally references and assets, to start executing Bash-based browser automation commands.

How do I start a browser automation session and capture data from web pages?

To start a browser automation session, open a target URL with the agent-browser open command, take a snapshot to generate element refs, and then use those refs to interact with elements and capture data through Bash commands.

What are the limitations of using Bash scripting for web testing and browser automation?

Using Bash scripting for web testing and browser automation relies on snapshot-based refs and session management, meaning complex dynamic page interactions may require repeated snapshots. It is designed for web QA, data collection, and automated workflows rather than heavy real-time rendering tasks.