agent-browser

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

41|14|Updated May 16, 2017
One-click install
npx skills add https://github.com/uzh-bf/klicker-uzh --skill agent-browser-uzh-bf
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/uzh-bf/klicker-uzh/tree/main/.github/skills/agent-browser
Command: npx skills add https://github.com/uzh-bf/klicker-uzh --skill agent-browser-uzh-bf

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates browser interactions for web testing, form filling, screenshots, and information extraction, reducing manual repetitive tasks.

Core Features & Use Cases

  • Browser automation: navigate pages, interact with elements, capture screenshots, and collect data across websites.
  • QA & demonstrations: create repeatable test flows and visual demos for stakeholders.
  • Use Case: automate sign-in workflows, form submissions, and data gathering from multiple pages to build reports.

Quick Start

Use the agent-browser tool in a Bash environment to open pages, snapshot page structure, interact with elements by refs, and capture results. Example commands:

  • agent-browser open https://example.com
  • agent-browser snapshot -i
  • agent-browser fill @e1 "your-input"
  • agent-browser click @e1
  • agent-browser screenshot ./s1.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 interactions for web testing and data extraction?

You can automate browser interactions by running the agent-browser tool in a Bash environment to navigate pages, fill forms, capture screenshots, and extract data across multiple websites for QA testing or report building.

Can I use browser automation to fill out forms and capture screenshots on any website?

Yes, browser automation supports form filling and capturing screenshots on websites by opening the URL, snapshotting the page structure, interacting with elements using their references, and saving the output to a file like a PNG image.

What is the best way to create repeatable QA test flows and visual web demonstrations?

To create repeatable QA test flows and visual web demonstrations, use a browser automation tool to script navigation and interaction sequences, capturing screenshots and data collection results for stakeholder review.

Do I need a specific environment to run web automation scripts for data collection?

Yes, you need a Bash environment to run the web automation scripts. The tool operates within Bash to execute commands for opening pages, snapshotting structures, interacting with elements, and extracting data.

How does browser automation handle element interaction during web page navigation?

Browser automation handles element interaction by taking a page snapshot, identifying interactive elements by their references, and executing commands to fill inputs or click targeted elements to navigate or submit data.

What are the limitations of using bash-based browser automation for web testing?

Bash-based browser automation requires running specific commands sequentially for each interaction, meaning complex dynamic page changes may need multiple snapshots to accurately locate elements before filling forms or extracting data.