browsing-with-playwright

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

9|2|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/AbdullahMalik17/Hacathan_5 --skill browsing-with-playwright-abdullahmalik17
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browsing-with-playwright
Source: https://github.com/AbdullahMalik17/Hacathan_5/tree/main/.claude/skills/browsing-with-playwright
Command: npx skills add https://github.com/AbdullahMalik17/Hacathan_5 --skill browsing-with-playwright-abdullahmalik17

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Manual web browsing tasks like filling forms, clicking through pages, and scraping dynamic content are repetitive and error-prone. This Skill lets an AI agent drive a real browser through the Playwright MCP server to perform these interactions programmatically. ## Core Features & Use Cases - Full Browser Control: Navigate pages, click elements, type text, fill forms, select dropdowns, handle dialogs, and manage tabs using accessibility snapshot element references. - Data Extraction & Screenshots: Capture accessibility snapshots, take full-page screenshots, run JavaScript on the page, and inspect network requests and console messages. - Server Lifecycle Management: Helper scripts start, stop, and verify the Playwright MCP server with a shared browser context that persists state across calls. - Use Case: Automatically log into a web portal, fill out a multi-field support form, submit it, wait for the confirmation message, and save a screenshot of the result. ## Quick Start Start the Playwright MCP server with the start-server script, then use the browsing skill to navigate to a website and extract its page content.

Frequently Asked Questions about browsing-with-playwright

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

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

Start the server with bash scripts/start-server.sh, then call browser tools through scripts/mcp-client.py. Navigate to a URL, take a snapshot to get element refs, then click, type, or fill forms using those refs.

How to fill and submit a web form using Playwright?▼

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 submit set to true, then wait for confirmation text.

When should I use Playwright instead of curl for web content?▼

Use Playwright when pages require JavaScript rendering, login sessions, or user interaction like clicking and form submission. Use curl or wget only for fetching static content, since a full browser is unnecessary overhead for plain HTML.

Why does browser_click fail with element not found?▼

Element refs become stale after page changes, so run browser_snapshot again to get current refs before clicking. If the click still fails, try browser_hover first or increase wait time with browser_wait_for.

Why does browser state reset between Playwright MCP calls?▼

State resets when the server runs without the --shared-browser-context flag, giving each call a fresh browser context. Start the server with that flag, as the start-server.sh script does, to maintain state across calls.