browser

Name: browser
Availability: InStock
Author: fran0220

Automate web interactions and capture page state via the agent-browser CLI.

Updated Feb 23, 2026

Search Tags:#automation #browser #screenshot #form-filling #dom #web-interaction #chrome-session

Ready to run

npx skills add https://github.com/fran0220/jacoworks --skill browser-fran0220

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: browser
Source: https://github.com/fran0220/jacoworks/tree/main/vm-agent/skills/%E5%B7%A5%E5%85%B7/browser
Command: npx skills add https://github.com/fran0220/jacoworks --skill browser-fran0220

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates repetitive and fragile manual interactions with web pages so you can open pages, click and fill elements, take screenshots, inspect DOM state, and reuse existing browser login sessions without manual browser control.

Core Features & Use Cases

Automate opening pages, waiting for load conditions, clicking elements, typing, and filling forms for interactive workflows.
Capture visual evidence with snapshots and screenshots and extract text or run JavaScript in-page for inspection or debugging.
Use case: log into a user dashboard via the existing Chrome session, navigate to a report page, take an annotated screenshot, and extract the visible summary text.

Quick Start

Open the target URL using the agent-browser CLI, reuse my Chrome session if available, wait for the page to finish loading, take a screenshot, and extract the main page text.

Frequently Asked Questions about browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate form filling and web interaction on login-protected sites?▼

Automate web interaction on login-protected sites by reusing an existing Chrome session to open pages, wait for load conditions, click elements, and fill forms without manual browser control.

Can I take screenshots and inspect DOM state during browser automation?▼

Yes, you can capture screenshots and inspect DOM state during browser automation by running in-page JavaScript and extracting text to debug interactive workflows.

What's the best way to reuse an existing Chrome session for automated web tasks?▼

The best way to reuse an existing Chrome session is using the agent-browser CLI, which supports running in-page JavaScript, waiting for network idle, and emitting snapshots for interactive tasks.

Does browser automation support waiting for specific network conditions before proceeding?▼

Yes, browser automation supports waiting for network idle or specific condition triggers before proceeding with clicking elements, typing, or taking screenshots.

How do I extract visible text from a web page after navigating to a report?▼

Extract visible text from a web page by navigating to the report URL, waiting for the page to finish loading, and running in-page JavaScript via the agent-browser CLI to capture the summary text.

Are there limitations when automating interactive browser tasks with existing sessions?▼

Limitations of automating interactive browser tasks include dependency on existing Chrome session availability and the need for explicit condition triggers to handle dynamic page loads properly.