skills.rest
GameDevFox
GameDevFoxCOMMUNITY
Explore all skills by this author →
GitHub

browser

Operate a real web browser to complete interactive user journeys.

Updated Mar 15, 2020
Search Tags:#browser automation#mcp#web scraping#form filling#playwright#screenshot#javascript rendering
One-click install
npx skills add https://github.com/GameDevFox/neko --skill browser-gamedevfox
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser
Source: https://github.com/GameDevFox/neko/tree/main/claude/skills/browser
Command: npx skills add https://github.com/GameDevFox/neko --skill browser-gamedevfox

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It enables reliable completion of real, interactive web tasks that cannot be done through plain browsing or raw fetching, such as clicking through flows, filling forms, or extracting content rendered by JavaScript.

Core Features & Use Cases

  • Real Browser Automation: Navigate to URLs, click links/buttons, type or fill inputs, submit forms, handle multi-step web flows, and verify results by re-checking the page state.
  • Rendered Content & Interaction Support: Works with JavaScript-heavy pages by using rendered accessibility snapshots and waits, including infinite scroll and dynamic modals.
  • Visual & Advanced Diagnostics: Capture screenshots for verification and use advanced capabilities (downloads, full-page screenshots, PDF export, cookies/storage, tracing, network interception) when needed.

Quick Start

Use the browser skill when you need to open and interact with a live website (for example, “go to https://example.com, click through the sign-up steps, fill the form, and take a screenshot of the confirmation page”).

Frequently Asked Questions about browser

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

FAQPage Schema
How do I automate filling forms and clicking through multi-step web flows?▼

Browser automation navigates a real web browser to complete interactive user journeys by clicking links, filling inputs, and submitting forms. It uses Playwright MCP controls with accessibility snapshots to target elements and verify page states after each action.

What is the best way to scrape JavaScript-generated content from dynamic web pages?▼

Scraping JavaScript-generated content requires a real browser that renders the page fully. It uses rendered accessibility snapshots and explicit waits for dynamic content, handling infinite scroll and dynamic modals to reliably extract interactive page data.

Can I capture screenshots or export PDFs during web browser automation?▼

Screenshots and PDF export are supported during browser automation. You can capture standard or full-page screenshots to verify page state, alongside advanced diagnostics like downloads, cookies, tracing, and network interception for comprehensive rendered outputs.

Does browser automation work with pages that require login, CAPTCHA, or MFA?▼

Browser automation handles login, CAPTCHA, consent, and MFA by performing a safe handoff to the user. When encountering these interactive barriers, it pauses the automated workflow to let the human user complete the verification step before resuming.

Do I need Playwright MCP controls to run interactive web workflows?▼

Playwright MCP browser controls are required for this browser automation. They provide the snapshot-first element targeting and explicit wait mechanisms needed to interact with rendered pages, navigate URLs, and manage dynamic content safely.

Related Skills

Explore More Software Engineering Skills→
joneqianjoneqian

Playwright (Automation + MCP + Scraper)

Automate browser tasks and extract rendered data using Playwright MCP.

Community
Intermediate
pynbj1001pynbj1001
2

Smart Browser

Extract JavaScript-rendered web page agendas and session data to Markdown and JSON.

Community
Intermediate
ericdahl-devericdahl-dev

setup-browser-cookies

Import cookies from real Chromium browsers into headless sessions for QA testing.

Official
Intermediate
szsip239szsip239
103

playwright-scraper-skill

Extract data from dynamic and Cloudflare-protected websites using Playwright scrapers.

Community
Advanced