skills.rest
legacybridge-tech
legacybridge-techOFFICIAL
Explore all skills by this author →
GitHub

agent-browser

Automate browser navigation, element interaction, and data extraction via the agent-browser CLI.

6|Updated Oct 16, 2025
Search Tags:#data extraction#screenshots#browser automation#web testing#form filling#element refs
One-click install
npx skills add https://github.com/legacybridge-tech/claude-plugins --skill agent-browser-legacybridge-tech
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/legacybridge-tech/claude-plugins/tree/main/agent-browser/skills/agent-browser
Command: npx skills add https://github.com/legacybridge-tech/claude-plugins --skill agent-browser-legacybridge-tech

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill automates repetitive browser interactions, enabling reliable web navigation, form filling, and information extraction without manual clicks.

Core Features & Use Cases

  • Browser Navigation & Interaction: open URLs, click elements, fill inputs, and navigate back/forward.
  • Snapshot & Refs: generate element refs for robust interaction and automation across pages.
  • Data Extraction & Screenshots: capture page data and take screenshots for testing and documentation.
  • Use Case: QA automation to navigate to a login page, fill credentials, submit, and verify that the dashboard loads successfully.

Quick Start

Use the agent-browser to perform common tasks: agent-browser open https://example.com agent-browser snapshot -i agent-browser click @e1 agent-browser fill @e1 "sample text" agent-browser close

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 for web testing without manual clicks?▼

You can automate browser tasks for web testing by using a CLI to open URLs, fill forms, and click elements. This enables reliable navigation and data extraction without manual interaction.

What's the best way to extract data from multiple web pages and sessions?▼

The best way to extract data from multiple web pages is using browser automation with interactive snapshots and session management, allowing repeatable information collection across pages.

Can I fill out forms automatically during web navigation?▼

Yes, you can fill out forms automatically during web navigation by targeting specific element refs with input commands to enter text into form fields reliably.

How do interactive snapshots and element refs work for browser automation?▼

Interactive snapshots capture the current page state and generate element refs, which act as stable identifiers to click or fill elements robustly across different pages and sessions.

Do I need any special dependencies to run browser automation for testing?▼

No special dependencies are required beyond the agent-browser CLI itself. It handles navigation, element interaction, and screenshots without needing additional frameworks or external packages.

Can I take screenshots during web testing workflows?▼

Yes, you can take screenshots during web testing workflows to capture page data and document the state of the application for verification and reporting purposes.

Related Skills

Explore More Software Engineering Skills→
npc-livenpc-live
168

agent-browser

Automate browser interactions via Chrome/CDP using the agent-browser CLI.

Official
Intermediate
bryonjacobbryonjacob

web-qa-exploration

Automate exploratory web QA with Playwright and generate findings reports.

Community
Intermediate
MichelMokbelMichelMokbel

browser

Automate web browser interactions and data extraction using AI-optimized element references.

Community
Advanced
8b-is8b-is

agent-browser

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

Official
Advanced