skills.rest
flowkraft
flowkraftCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

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

75|8|Updated Dec 20, 2023
Search Tags:#automation#testing#CLI#browser#data-extraction#web-scraping
One-click install
npx skills add https://github.com/flowkraft/reportburster --skill agent-browser-flowkraft
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/flowkraft/reportburster/tree/main/asbl/src/main/external-resources/db-template/_apps/flowkraft/_ai-hub/.skills/agent-browser
Command: npx skills add https://github.com/flowkraft/reportburster --skill agent-browser-flowkraft

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates browser interactions to streamline testing, data extraction, and repetitive web tasks, reducing manual QA time and enabling reliable UI automation.

Core Features & Use Cases

  • Browser automation: Navigate, click, fill, and extract data across pages using a CLI tool.
  • Test automation & reproducibility: Create deterministic sessions with a session ID to replay actions.
  • Use Case: Build automated form submissions, data scraping workflows, and evidence capture across multiple websites.

Quick Start

Use agent-browser to start a session and interact with a test page. Example: agent-browser --session mysess open https://example.com agent-browser --session mysess snapshot -i agent-browser --session mysess click @e1 agent-browser --session mysess 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 web scraping and form filling across unknown websites?▼

Browser automation automates web scraping and form filling by navigating unknown websites using a CLI tool. You open a session, take snapshots, interact with elements by clicking and filling, and extract content across multiple pages.

Can I replay browser interactions deterministically for UI testing?▼

Yes, deterministic browser sessions support replaying interactions for UI testing. A session ID tracks actions like open, snapshot, fill, and click commands to ensure reproducible runs and clean resource management across test executions.

What's the best way to capture visual evidence during web testing?▼

Visual evidence capture during web testing is handled by taking snapshots within a browser session. You open a target URL and use the snapshot command to capture page visuals for reliable evidence collection.

Does CLI browser automation support multiple concurrent sessions?▼

CLI browser automation supports multiple sessions by assigning a unique session ID to each run. This workflow enables you to manage open, fill, click, and close operations across concurrent data extraction or testing tasks.

Why use a CLI session workflow for web data extraction instead of standard scripts?▼

A CLI session workflow provides deterministic runs and clean resource management for web data extraction. It isolates actions like open, snapshot, and click into discrete commands, ensuring reliable execution compared to standard scripts.

When should I avoid using CLI browser automation for testing?▼

You should avoid CLI browser automation when tasks require complex real-time user interaction rather than deterministic scripted sequences. It is designed for structured navigation, form filling, and data extraction across sessions, not interactive exploration.

Related Skills

Explore More Software Engineering Skills→
lidge-junlidge-jun
5

browser

Automate Google Chrome browser interactions for web automation tasks.

Community
Intermediate
nq-rdlnq-rdl

convert-file

Convert data files between formats using DuckDB COPY statements.

Official
Intermediate
az9713az9713

agent-browser

Utility for automating workflows and interactions in virtualized Linux/Windows desktops and servers.

Community
Intermediate
gbenckegbencke
5

obscura

Render JavaScript-heavy pages in a headless browser and extract text, HTML, links, or JSON.

Community
Intermediate