playwright

Automate browser interactions with Playwright using CLI commands and snapshots.

1|Updated Feb 11, 2026
One-click install
npx skills add https://github.com/dimitri-vs/elevate-agent-skills --skill playwright-dimitri-vs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: playwright
Source: https://github.com/dimitri-vs/elevate-agent-skills/tree/main/playwright
Command: npx skills add https://github.com/dimitri-vs/elevate-agent-skills --skill playwright-dimitri-vs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the guesswork of interacting with complex websites by providing a reliable, agent-friendly workflow for navigation, element targeting, and verification using Playwright.

Core Features & Use Cases

  • CLI-first browser automation: Use @playwright/cli for token-efficient flows, with a snapshot → reference → interact → verify loop.
  • Selective visibility & verification: Take screenshots and snapshots only when needed, while using eval for text extraction to avoid unnecessary context cost.
  • Auth persistence and session control: Use --persistent profiles for logged-in experiences, and use named sessions (-s=) for parallel subagents without state collisions.
  • Asset and artifact management: Direct snapshots/screenshots to .pw-tmp/ and clean up stale artifacts to keep projects tidy.
  • Fallback to MCP when appropriate: Use @playwright/mcp for short exploratory sessions that benefit from richer page understanding.

Quick Start

Use the playwright Skill to complete a login-and-dashboard task by running CLI commands to open the target page in headed mode, taking a snapshot to find stable element refs, performing the required clicks/fills, and then taking a verification snapshot or screenshot.

Frequently Asked Questions about playwright

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

FAQPage Schema
How do I automate web scraping on dynamic single-page applications with Playwright?

Automating web scraping on dynamic single-page applications with Playwright uses a snapshot-to-reference interaction pattern for reliable element discovery, text extraction via eval, and CLI-first execution to maintain token efficiency while navigating complex UI state changes.

Can I run parallel browser automation sessions for multiple subagents without state collisions?

You can run parallel browser automation sessions safely by assigning named sessions using the -s= flag, which isolates browser state and prevents collisions across concurrent subagent tasks within the same project environment.

Does Playwright CLI work better than MCP for long-running agent tasks?

Playwright CLI execution is better for long-running agent tasks because it is token-efficient, whereas the @playwright/mcp fallback is reserved for short exploratory sessions that benefit from richer page understanding.

How do I verify UI changes after filling out forms during browser automation?

To verify UI changes after filling out forms during browser automation, take a verification snapshot or screenshot after performing the required interactions, capturing the resulting page state to confirm the action succeeded.

How do I handle browser authentication persistence in Playwright automation?

Browser authentication persistence in Playwright automation is handled using the --persistent flag to maintain logged-in profiles across sessions, allowing agents to bypass repeated login flows for authenticated web tasks.