playwright-cli

Automate browser interactions for web testing, form filling, screenshots, and data extraction.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/takimoto-sketch/medica-agent --skill playwright-cli-takimoto-sketch
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: playwright-cli
Source: https://github.com/takimoto-sketch/medica-agent/tree/main/.claude/skills/playwright-cli
Command: npx skills add https://github.com/takimoto-sketch/medica-agent --skill playwright-cli-takimoto-sketch

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes manual browser work by enabling programmatic navigation, interaction, and data extraction so teams can test web applications, fill forms, capture screenshots, and scrape content reproducibly.

Core Features & Use Cases

  • Interactive browser control: Open browsers, navigate pages, click, type, press keys, manage tabs, and resize viewports.
  • Data capture & testing: Take snapshots and screenshots, generate Playwright test code, record traces and videos for debugging and audit.
  • Advanced workflows: Named sessions, persistent profiles, storage-state save/load, request mocking and route interception, run arbitrary Playwright code, and snapshot-based element referencing with guarded authentication handling.
  • Use Case: Automate a multi-tab scraping workflow that uses persistent sessions, mocks API responses for deterministic tests, records a trace for debugging, and exports extracted data.

Quick Start

Ask the agent to open a browser to https://example.com, take a snapshot, extract visible text and elements, and then close the browser.

Frequently Asked Questions about playwright-cli

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

FAQPage Schema
How do I automate browser interactions for web testing and scraping?

Automate browser interactions for web testing and scraping by programmatically opening browsers, navigating pages, clicking elements, typing text, and extracting visible data reproducibly across Chrome, Firefox, and WebKit.

Can I manage persistent sessions and storage states for multi-tab scraping?

Yes, you can manage persistent sessions and storage states for multi-tab scraping by using named sessions, saving and loading storage states, and maintaining persistent browser profiles across automated workflows.

What is the best way to debug automated UI testing workflows?

Debug automated UI testing workflows by capturing screenshots, recording traces, and generating videos of browser interactions to audit and reproduce multi-step automated form filling and navigation sequences.

Does Playwright support request mocking and route interception for deterministic tests?

Yes, Playwright supports request mocking and route interception to create deterministic tests by intercepting network routes and mocking API responses during automated browser interactions.

Why are credentials blocked during automated browser navigation?

Credentials are blocked during automated browser navigation due to built-in guards that prevent capturing credentials and navigating to authentication endpoints, ensuring secure automated web scraping and testing workflows.

How do I extract visible text and elements using snapshot-based references?

Extract visible text and elements using snapshot-based references by taking a page snapshot, referencing extracted elements programmatically, and running arbitrary Playwright code to capture the target data.