skills.rest
nytafar
nytafarCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate browser navigation, form filling, and data extraction via CLI.

Updated Aug 23, 2026
Search Tags:#browser automation#web scraping#web interaction#headless chrome#webdriver#ai agent tool
One-click install
npx skills add https://github.com/nytafar/fmr-next --skill agent-browser-nytafar
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/nytafar/fmr-next/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/nytafar/fmr-next --skill agent-browser-nytafar

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates web browser interactions, allowing AI agents to navigate websites, fill forms, extract data, and perform complex online tasks programmatically.

Core Features & Use Cases

  • Web Navigation: Open URLs, navigate back/forward, reload pages.
  • Form Interaction: Fill text fields, select dropdowns, check boxes, click buttons.
  • Data Extraction: Scrape text, HTML, attributes, and structured data from web pages.
  • Screenshots & PDFs: Capture full-page screenshots or save pages as PDFs.
  • Use Case: An AI agent needs to book a flight. It uses agent-browser to open the airline's website, fill in the departure and arrival dates, select seats, and complete the booking process.

Quick Start

Use agent-browser to open the website 'https://example.com' and take a screenshot.

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 interaction and form filling for an AI agent?▼

Web scraping for structured data extraction is handled through commands that scrape text, HTML, and attributes from web pages. The tool supports advanced browser features like network interception and viewport emulation to reliably extract data from dynamic web content.

Can I use headless Chrome to capture full-page screenshots and generate PDFs?▼

Headless Chrome supports full-page screenshot capture and PDF generation through dedicated commands. You can programmatically save web pages as images or documents while managing authentication and session state during the capture process.

Does browser automation handle authentication and session management for web pages?▼

Browser automation handles authentication and session management natively. It maintains session state across multiple navigations, allowing AI agents to log in, manage cookies, and interact with authenticated pages without losing context between commands.

What is the best way to control browsers for AI agents programmatically?▼

The best way to control browsers for AI agents is using a command-line interface designed for programmatic automation. This approach enables agents to execute web navigation, form interaction, and data extraction tasks through a robust set of structured commands and options.

Related Skills

Explore More Software Engineering Skills→
konneh-hubkonneh-hub

vercel-sandbox

Run headless Chrome browser automation inside Vercel Sandbox microVMs.

Community
Advanced
abdullah1854abdullah1854
1

chrome-data-extract

Generate JavaScript snippets to extract structured data from HTML tables, forms, and lists.

Community
Intermediate
jg-chalk-iojg-chalk-io

moai-core-rules

Define governance rules for Alfred's 3-layer architecture and TRUST quality gates.

Community
Advanced
Prorise-coolProrise-cool
24

web-scraping-playbook

Analyze website rendering and anti-scraping mechanisms to plan data extraction strategies.

Community
Intermediate