skills.rest
eastreams
eastreamsOFFICIAL
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate web page navigation, interaction, and data extraction via Chrome DevTools Protocol.

641|104|Updated Mar 5, 2026
Search Tags:#automation#cli#scraping#ai-agent#browser#screenshot#form-filling
One-click install
npx skills add https://github.com/eastreams/loong --skill agent-browser-eastreams
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/eastreams/loong/tree/main/skills/agent-browser
Command: npx skills add https://github.com/eastreams/loong --skill agent-browser-eastreams

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Interacting with websites programmatically is tedious and error‑prone for AI agents that need to navigate pages, fill forms, click buttons, or extract data. This Skill provides a reliable browser automation interface so agents can perform web tasks without manual coding.

Core Features & Use Cases

  • Command‑line Automation: Use agent-browser commands to open URLs, take screenshots, capture PDFs, and record videos.
  • Form Interaction & Data Extraction: Snapshot pages to obtain element references, then fill inputs, click elements, or extract text and structured data.
  • Session & Authentication Management: Persist cookies, use profiles, or load saved authentication states for repeated logins.
  • Use Cases: Automated testing of web apps, data scraping for research, filling online forms, generating visual reports, or controlling web‑based dashboards from AI workflows.

Quick Start

Ask the AI to open a website and capture a screenshot using the agent-browser tool.

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 button clicking for an AI agent?▼

Automate web form filling and button clicking by using the agent-browser CLI to snapshot pages for element references, then issue commands to fill inputs and click elements. This drives Chrome/Chromium through the Chrome DevTools Protocol.

Can I take screenshots and capture PDFs during web scraping automation?▼

Yes, you can take screenshots and capture PDFs during web scraping automation. The tool executes via the agent-browser CLI to open URLs, record videos, and capture visual reports while extracting structured data from web pages.

How does browser automation handle session cookies and authentication states?▼

Browser automation handles session cookies and authentication states by persisting cookies, using profiles, or loading saved authentication states. This enables repeated logins and continuous web page navigation without manual re-authentication.

What is the best way to extract structured data from web pages using an AI agent?▼

The best way to extract structured data from web pages is to snapshot pages for element references, then use the agent-browser CLI to drive Chrome/Chromium via the DevTools Protocol for reliable text and data extraction.

Do I need any browser dependencies installed to use this web automation tool?▼

You need Chrome or Chromium installed to use this web automation tool. The CLI drives the browser directly through the Chrome DevTools Protocol, requiring no additional external dependencies to perform page navigation and interaction.

Why use a command-line interface for AI agent web automation instead of manual coding?▼

Use a command-line interface for AI agent web automation to interact with websites programmatically without manual coding. It provides a reliable browser automation interface to perform web tasks like filling forms and scraping content error-free.

Related Skills

Explore More Software Engineering Skills→
BenAIOSBenAIOS

agent-browser

Automate Chrome browser interactions and web scraping via CDP.

Official
Advanced
Pans0020Pans0020

markdown-exporter

Convert Markdown content into DOCX, PPTX, XLSX, PDF, HTML, IPYNB, MD, CSV, JSON/JSONL, XML, and extracted code files.

Community
Advanced
cribclawcribclaw

agent-browser

Automate web browsing, element interaction, and data extraction via CLI.

Community
Advanced
dushyantkhosladushyantkhosla

browser-tools

Automate web interactions via Chrome DevTools Protocol with Puppeteer.

Community
Advanced