skills.rest
ramshan00
ramshan00COMMUNITY
Explore all skills by this author →
GitHub

browser-use

Automate browser navigation, form filling, and data extraction via Playwright MCP.

Updated Feb 8, 2026
Search Tags:#screenshots#browser automation#mcp#web scraping#form filling#playwright#ui testing
One-click install
npx skills add https://github.com/ramshan00/hackaton --skill browser-use-ramshan00
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser-use
Source: https://github.com/ramshan00/hackaton/tree/main/Hackathon2-phase2/.claude/skills/browser-use
Command: npx skills add https://github.com/ramshan00/hackaton --skill browser-use-ramshan00

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @playwright/mcp, and includes scripts (resource) and references (resource) components.

What problem does it solve? Manual web interactions like filling forms, scraping pages, and testing UIs are repetitive and error-prone. This Skill lets an AI drive a real browser through the Playwright MCP server to perform these tasks programmatically. ## Core Features & Use Cases - Browser Automation: Navigate pages, click elements, type text, fill forms, select dropdowns, and handle tabs using accessibility snapshot references. - Data Extraction & Capture: Take screenshots, capture accessibility snapshots, run JavaScript on pages, and inspect network requests and console messages. - Server Lifecycle Management: Helper scripts start and stop the Playwright MCP server with shared browser context so state persists across calls. - Use Case: Automate an end-to-end login flow—navigate to a site, snapshot the page to find form fields, fill credentials, submit, wait for confirmation, and screenshot the result. ## Quick Start Ask the AI to start the browser server and navigate to a website, then fill out and submit a form on that page.

Frequently Asked Questions about browser-use

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

FAQPage Schema
How do I automate browser interactions with Playwright MCP?▼

Start the Playwright MCP server with the start-server.sh script, then call tools like browser_navigate, browser_snapshot, and browser_click through the mcp-client.py script. Use element refs from snapshots to target clicks and form fields.

How do I fill out and submit a web form programmatically?▼

Navigate to the page, run browser_snapshot to get element refs, then use browser_fill_form with field refs and values. Click the submit button or use browser_type with the submit option set to true.

Why does the browser lose state between Playwright MCP calls?▼

State is lost when the server runs without the --shared-browser-context flag, since each call then gets a fresh browser context. Start the server with that flag to maintain cookies, tabs, and page state across calls.

What should I do when a browser click fails or an element is not found?▼

Run browser_snapshot first to get current element refs, since refs change after page updates. If a click still fails, try browser_hover before clicking, or use browser_wait_for to wait for text to appear.

Can I run multi-step Playwright code in a single call?▼

Yes, the browser_run_code tool executes a JavaScript function receiving the Playwright page object, so multiple actions run atomically in one call. This is recommended for complex workflows that should be all-or-nothing.

Related Skills

Explore More Software Engineering Skills→
kachilu-inckachilu-inc
38

kachilu-browser

Automate browser navigation, form filling, and data extraction for AI agents.

Official
Advanced
RoentekRoentek
4

playwright

Capture screenshots, scrape rendered text, extract links, and generate PDFs from URLs.

Official
Intermediate
ShahfarzaneShahfarzane

browser-automation

Automate Chrome browser interactions via natural-language commands and Playwright.

Community
Advanced
ericwang915ericwang915
38

http_request

Perform HTTP requests to any API endpoint with custom headers and JSON payloads.

Community
Intermediate