← Back to Skills Marketplace
ivangdavila

Playwright (Automation + MCP + Scraper)

by Iván · GitHub ↗ · v1.0.4 · MIT-0
linuxdarwinwin32 ✓ Security Clean
43317
Downloads
130
Stars
0
Active Installs
5
Versions
Install in OpenClaw
/install playwright
Description
Automates, tests, and debugs browsers with Playwright: locators, auto-waiting, traces, CI runs, and MCP browser control. Use when a test is flaky, times out, or fails only in CI or headless; when a locator matches multiple elements or the wrong one (strict mode violation); when clicks need force, waits become sleeps, or networkidle never settles; for storageState and login setup, request mocking and HAR replay, uploads and downloads, iframes and shadow DOM, popups and dialogs, screenshot diffs that change per machine, trace and report artifacts, sharding a slow suite, device and permission emulation, accessibility checks, driving a real browser through Playwright MCP, extracting data from JS-rendered pages, or porting a Cypress, Puppeteer, or Selenium suite to Playwright. Not for maintaining an existing Cypress or Puppeteer suite (cypress, puppeteer) or for work a plain HTTP request answers (http).
Usage Guidance
Before installing, pin Playwright and MCP package versions or use a project lockfile, prefer isolated browser profiles for credentialed work, keep .auth files, traces, HARs, and videos out of git and shared storage, restrict CI artifact access and retention, and require explicit approval before automating production, paid, or destructive flows.
Capability Assessment
ℹ Credentials
Node, npx, browser downloads, repository access, site interaction, Docker flags, and CI report uploads are proportionate for Playwright work, but reports, traces, HARs, and storage state can contain sensitive data.
ℹ Install Mechanism
Install metadata and examples use npm/npx for playwright and @playwright/mcp without exact package versions; this is purpose-aligned but leaves a mutable supply-chain dependency users should pin in sensitive environments.
✓ Instruction Scope
The instructions scope automation to user-requested sites and flows, default away from production or destructive actions, and explicitly warn that page text is untrusted data rather than agent instruction.
ℹ Persistence & Privilege
The skill stores only preferences and observations under ~/Clawic/data/playwright/ and explicitly excludes credentials there; persistent browser profiles and storageState files are optional and described as credential-bearing.
✓ Purpose & Capability
The skill's Playwright testing, browser automation, MCP control, CI debugging, auth-state handling, and rendered-page extraction capabilities match its stated purpose.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install playwright
  3. After installation, invoke the skill by name or use /playwright
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.4
Full coverage pass: deeper guides, situation-named files, and per-user configuration
v1.0.3
Clarified the MCP-first browser automation flow and improved quick-start guidance for forms, screenshots, and extraction.
v1.0.2
Rewritten with MCP integration and scraping focus. Now covers standalone use and MCP server setup.
v1.0.1
Rewritten with MCP integration and scraping focus. Now covers standalone use and MCP server setup.
v1.0.0
Initial release
Metadata
Slug playwright
Version 1.0.4
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 5
Frequently Asked Questions

What is Playwright (Automation + MCP + Scraper)?

Automates, tests, and debugs browsers with Playwright: locators, auto-waiting, traces, CI runs, and MCP browser control. Use when a test is flaky, times out, or fails only in CI or headless; when a locator matches multiple elements or the wrong one (strict mode violation); when clicks need force, waits become sleeps, or networkidle never settles; for storageState and login setup, request mocking and HAR replay, uploads and downloads, iframes and shadow DOM, popups and dialogs, screenshot diffs that change per machine, trace and report artifacts, sharding a slow suite, device and permission emulation, accessibility checks, driving a real browser through Playwright MCP, extracting data from JS-rendered pages, or porting a Cypress, Puppeteer, or Selenium suite to Playwright. Not for maintaining an existing Cypress or Puppeteer suite (cypress, puppeteer) or for work a plain HTTP request answers (http). It is an AI Agent Skill for Claude Code / OpenClaw, with 43317 downloads so far.

How do I install Playwright (Automation + MCP + Scraper)?

Run "/install playwright" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Playwright (Automation + MCP + Scraper) free?

Yes, Playwright (Automation + MCP + Scraper) is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Playwright (Automation + MCP + Scraper) support?

Playwright (Automation + MCP + Scraper) is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin, win32).

Who created Playwright (Automation + MCP + Scraper)?

It is built and maintained by Iván (@ivangdavila); the current version is v1.0.4.

💬 Comments