agent-browser

Automate browser interactions for navigation, form filling, screenshots, and content extraction.

4|Updated Jan 30, 2026
One-click install
npx skills add https://github.com/Xueheng-Li/ai-tools-installation --skill agent-browser-xueheng-li
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Xueheng-Li/ai-tools-installation/tree/main/recommended_skills/agent-browser
Command: npx skills add https://github.com/Xueheng-Li/ai-tools-installation --skill agent-browser-xueheng-li

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the manual, error-prone steps of interacting with websites by providing a CLI-driven browser automation interface that navigates pages, fills forms, clicks controls, captures screenshots/PDFs, and extracts structured content so workflows run reliably and repeatably.

Core Features & Use Cases

  • Snapshot + refs: Compact interactive element refs (@e1, @e2, ...) let agents discover and act on page elements without shipping full DOMs.
  • End-to-end automation: Navigate, wait for network idle, fill forms, perform authenticated sessions, take screenshots, record video, export PDF, and profile performance for testing and scraping.
  • Session & device support: Named sessions, state save/load, proxy/CDP connectivity, headed/headless modes, and iOS simulator support enable authenticated workflows and parallel scraping or E2E test runs.
  • Use case: Log into a web app once, save auth state, run scheduled scraping of product pages to extract text and screenshots, and record a video for QA.

Quick Start

Open https://example.com/login, snapshot interactive elements, fill the username and password refs, click the submit button, wait for the dashboard to load, and save the session state to auth.json.

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 while reusing authenticated sessions?

Automate web scraping with persistent named sessions to log into a web app once, save the auth state, and run scheduled extraction of text and screenshots repeatably without manual re-authentication.

Can I run Playwright browser automation with proxy and CDP options?

Yes, Playwright and Chromium-compatible execution supports proxy and CDP options, enabling advanced connectivity for browser automation, parallel scraping, and end-to-end testing workflows.

How do I fill forms and click buttons using snapshot refs for E2E testing?

Fill forms and click buttons by taking a snapshot to generate compact interactive element refs like @e1 and @e2, allowing agents to discover and act on page elements without shipping full DOMs.

Does iOS simulator support require macOS with Xcode for mobile browser automation?

Yes, iOS simulator workflows for mobile browser automation require macOS with Xcode installed, enabling device-specific testing and visual debugging within the automation interface.

What's the best way to capture screenshots and export PDFs during web navigation?

Capture screenshots and export PDFs during web navigation by automating browser interactions with built-in visual debugging tools that also support video recording for QA and performance profiling.