skills.rest
mhbdev
mhbdevCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automate browser navigation, form filling, and data extraction via command-line interface.

Updated Aug 23, 2026
Search Tags:#testing#browser automation#web scraping#form filling#CLI tool#web interaction
One-click install
npx skills add https://github.com/mhbdev/git-pal --skill agent-browser-mhbdev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/mhbdev/git-pal/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/mhbdev/git-pal --skill agent-browser-mhbdev

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates browser interactions, allowing users to navigate websites, fill forms, click buttons, and extract data programmatically, eliminating the need for manual web browsing for repetitive tasks.

Core Features & Use Cases

  • Web Navigation: Open, close, and navigate between web pages.
  • Form Interaction: Fill text fields, select dropdown options, check boxes, and submit forms.
  • Data Extraction: Scrape text content, element attributes, and structured data from web pages.
  • Screenshots & PDFs: Capture full-page screenshots or save pages as PDFs.
  • Use Case: Automate the process of logging into a web application, filling out a complex registration form, and then scraping the confirmation details.

Quick Start

Use the agent-browser skill to open the website 'https://example.com' and take a full-page 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 form filling and scraping with a CLI tool?▼

Browser automation via a command-line interface allows AI agents to navigate websites, fill forms, click elements, and extract data programmatically. You use CLI commands to interact with web pages through element snapshots and refs, eliminating manual web interactions for repetitive tasks.

Can I capture full-page screenshots and save web pages as PDFs?▼

Yes, full-page screenshots and PDF generation are supported. The tool provides specific commands to render the current browser session state into image or PDF files for record-keeping and visual analysis.

How does element interaction work when navigating websites programmatically?▼

Element interaction relies on snapshots and refs. The tool captures a snapshot of the web page to identify interactive elements, assigns refs to them, and uses those refs in CLI commands to fill text fields, select dropdown options, or click buttons precisely.

What is the best way to manage browser sessions for repetitive web scraping?▼

Session management maintains browser state across multiple interactions. By keeping a session active, you navigate between pages and scrape sequential data without re-authenticating or losing your current browsing state during long automation workflows.

Do I need any additional dependencies to run browser automation tasks?▼

No additional dependencies are required. The Skill operates independently with its internal scripts and references, providing a complete environment for web navigation, data extraction, and form interaction without external package requirements.

Related Skills

Explore More Software Engineering Skills→
partme-aipartme-ai
610

agent-browser

Control web browsers via CLI for navigation, element interaction, and data extraction.

Official
Advanced
Wike-CHIWike-CHI
2

document-pro

Extract text, tables, and images from PDFs, DOCX, PPTX, XLSX, and plain text.

Community
Intermediate
antgroupantgroup
16

jina-reader

Extract web content as markdown and perform search-based grounding via the Jina AI Reader API.

Official
Intermediate
tedtv1007-ctrltedtv1007-ctrl

cloudflare-crawl

Fetch rendered HTML from dynamic websites via the Cloudflare Browser Rendering API.

Community
Intermediate