Your agent writes and runs real Playwright scripts to test pages, forms, sign-up flows and layouts, with screenshots of what it saw.
by lackeyjb· Web & browserUnclaimed · Yours? Claim it
4 images
About
Playwright Skill is lackeyjb's Agent Skill for general-purpose browser automation, also packaged as a Claude Code plugin. Instead of calling a fixed set of browser tools, your agent writes a real Playwright program for the job (loops, assertions, several browser contexts, network interception, screenshots or video), runs it with the skill's executor, and reports back with console output and screenshots. What you can do with it - Test a page, a form or a whole flow such as sign-up or log-in - Take screenshots at mobile and desktop sizes to check responsive design - Fill in and submit forms, click through the navigation, try the search - Check for broken links, images that don't load and form validation - Keep the script and run it again later How it works - For local work it first finds the dev servers running on your machine, and asks which one when there are several. - It writes the script to a temp folder (or your project, if you ask) and runs it with its own executor, so Playwright loads wherever the skill is installed. - The browser is visible by default. It runs headless when you ask, or when there's no display. - Its full Playwright API reference loads only when a task needs it. How to install it In Claude Code, run /plugin marketplace add lackeyjb/playwright-skill, then /plugin install playwright-skill@playwright-skill. With the skills CLI: npx skills add lackeyjb/playwright-skill --skill playwright-skill --global --yes. Then run npm run setup in the skill's folder, which installs Playwright and Chromium. Good to know - Needs Node.js 20 or later. - No sign-in: it runs on your machine. - For simple interactive browsing the maker points to Microsoft's Playwright CLI or Playwright MCP. This skill is for when the automation script itself is worth keeping. - A community project by lackeyjb, MIT licensed. It isn't an official Microsoft or Playwright project.
Once it’s added
“Test the homepage.”
“Check if the contact form works.”
“Verify the signup flow.”
“Take screenshots of the dashboard in mobile and desktop.”
“Check for broken links.”
“Fill out the registration form and submit it.”
Before you add it
Reads only
Pages in a real browser, on your dev server or any URL · Console output, failed requests and screenshots
Makes changes · your agent can ask first
Playwright scripts, in a temp folder or your project · Clicks and form submissions on the pages it tests
From people who use it
Step by step
Nothing new reaches your agent until a person has looked at it.
No reviews yet. Used Playwright Skill? Say how it went.
Write a reviewRuns on your machine.
Runs on your machine.
/plugin marketplace add lackeyjb/playwright-skill /plugin install playwright-skill@playwright-skill
Scanned and passed · checked 47 min ago
Plugins people install alongside Playwright Skill.
Scanned on every change, and again when our rules improve.
Claude CodeSupported
OpenClawSupportedTell us and a person on the trust team will look at it. Or email [email protected].
Nobody has shared how they use Playwright Skill yet.
Security scan
Passed
Safe to install in every agent it supports. Claude plugins.
Plugins people install alongside Playwright Skill.
Hand web tasks to a Browser Use agent in a cloud browser: it browses sites, fills in forms and pulls out the data you asked for.
ByteDance's local MCP server that lets your agent drive a real browser: open pages, click, fill in forms, read pages and take screenshots.
Microsoft's MCP server for browser automation with Playwright: your agent navigates, clicks and fills in pages from structured snapshots.
Plans and builds scraping pipelines with Firecrawl or local Python, and won't hand over the data until it passes a validation check.
