agent-browser

Automate browser tasks for testing, form filling, and data extraction.

577|48|Updated Aug 4, 2025
One-click install
npx skills add https://github.com/FradSer/dotclaude --skill agent-browser-fradser
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/FradSer/dotclaude/tree/main/office/skills/agent-browser
Command: npx skills add https://github.com/FradSer/dotclaude --skill agent-browser-fradser

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Browser automation for testing, data extraction, and form filling can be inconsistent and hard to share. This skill standardizes the command set and reference patterns to streamline web automation tasks across teams.

Core Features & Use Cases

  • Centralized command reference for common actions (open, back, forward, snapshot, click, fill, test, and capture).
  • Reusable refs and snapshot-driven interactions to minimize AI context and improve reliability.
  • Support for multi-session isolation, screenshots, and optional video recording to document automation flows.

Quick Start

Use the agent-browser CLI to perform typical tasks: agent-browser open https://example.com agent-browser snapshot -i agent-browser click @e1 agent-browser fill @e1 "sample user" agent-browser screenshot ./example.png

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 form filling and testing consistently across sessions?

Browser automation for form filling and testing is standardized using a centralized command set with reusable refs and snapshot-driven interactions to ensure reliable execution across multiple isolated sessions.

What is the best way to handle interactive web elements during data extraction without consuming excessive context?

Interactive web elements are handled during data extraction using compact refs and page snapshots, minimizing AI context requirements while maintaining reliable interaction with target page elements.

How do I capture screenshots and record web automation flows for documentation?

Screenshots are captured using the capture command to save page states as PNG files, and optional video recording documents complete automation flows alongside multi-session isolation for comprehensive review.

Can I run multiple browser automation sessions simultaneously for different web apps?

Multiple browser automation sessions are supported with per-session isolation, allowing concurrent interaction with different web apps and static sites while maintaining independent state and safeguards.

Do I need any external dependencies to perform page navigation and interactive element handling?

No external dependencies are required; page navigation and interactive element handling rely entirely on built-in documentation, reference patterns, and templates to provide commands and safeguards.

What limitations exist when using snapshot-driven interactions for browser automation tasks?

Snapshot-driven interactions require valid element refs to execute actions reliably, meaning dynamic pages with rapidly changing DOM structures may need frequent snapshot refreshes to maintain accurate element targeting.