Playwright Browser Automation
General-purpose browser automation with Playwright for testing pages, forms, responsive design, and UX validation
Install
Quick install
npx skills add https://github.com/lackeyjb/playwright-skillnpx skills add lackeyjb/playwright-skill --agent claude-codenpx skills add lackeyjb/playwright-skill --agent cursornpx skills add lackeyjb/playwright-skill --agent codexnpx skills add lackeyjb/playwright-skill --agent opencodenpx skills add lackeyjb/playwright-skill --agent github-copilotnpx skills add lackeyjb/playwright-skill --agent windsurfMore install options
Shorthand — useful for multi-skill repos:
npx skills add lackeyjb/playwright-skillManual — clone the repo and drop the folder into your agent's skills directory:
git clone https://github.com/lackeyjb/playwright-skill.gitcp -r playwright-skill ~/.claude/skills/Playwright Browser Automation
General-purpose browser automation with Playwright for testing pages, forms, responsive design, and UX validation
What is it?
A general-purpose browser automation skill that enables Claude to write and execute custom Playwright scripts for your specific needs. Unlike pre-built testing frameworks, Claude dynamically generates tailored automation code on-the-fly for any task - from simple page tests to complex multi-step flows. The browser runs visibly by default for easy debugging and verification.
How to use it?
The skill follows a conversational workflow:*
Describe Your Need - Simply tell Claude what you want to test or automate (e.g., "Test the homepage", "Check if the contact form works", "Verify the signup flow")
*
Auto-Detection - The skill automatically detects running development servers on your machine. If testing an external site, Claude will ask for the URL.
*
Code Generation - Claude writes custom Playwright code tailored to your specific request and saves it to /tmp/playwright-test-*.js
*
Execution - The script executes via a universal executor (run.js) that handles proper module resolution. The browser opens visibly by default so you can watch the automation in real-time.
*
Results - View console output, screenshots, and any captured data. Test files are automatically cleaned from /tmp by your OS.
No configuration files, no pre-built tests - just natural language requests that Claude transforms into working automation code.
Key Features
- Custom code generation - Claude writes fresh Playwright scripts tailored to your exact request, not limited to templates
- Visible browser by default - Watch automation execute in real-time with
headless: falsefor easy debugging - Auto-detects dev servers - Automatically finds and tests your local development server
- Zero module resolution errors - Universal executor ensures proper module access without configuration
- Progressive API documentation - Concise SKILL.md with full API reference loaded only when needed
- Safe temp file management - Scripts written to /tmp and auto-cleaned by your OS
- Works with any site - Test local development servers or external websites
- Comprehensive helpers - Optional utility functions available for common tasks when neededView on GitHub
GitHub Stats
StarsForksLast UpdateAuthorlackeyjbLicenseMITVersion4.0.0Categories
Developer ToolsTestingTags
playwrightbrowser-automatione2e-testingweb-testingautomationFeatures
💻 Code ExecutionRelated Skills
More from Developer ToolsiOS Simulator Skill
21 production-ready scripts for iOS app testing, building, and automation with semantic UI navigation200Conor LuddyDeveloper ToolsTesting00
Auto Write Tests
Automated test writing orchestration system that discovers test infrastructure, analyzes code changes, and dispatches parallel agents to write comprehensive test coverage433NeoLabHQTestingDeveloper Tools00
Auto Fix Tests
Systematic failing test repair orchestration with auto-discovery, parallel agent fixes, and full verification, emphasizing fixing tests without modifying business logic433NeoLabHQTestingDeveloper Tools00
---
Source: https://github.com/lackeyjb/playwright-skill
Author: lackeyjb
License: https://opensource.org/licenses/MIT
GitHub Stars: 180
Tags: playwright, browser-automation, e2e-testing, web-testing, automation
SKILL.md source
--- name: Playwright Browser Automation description: General-purpose browser automation with Playwright for testing pages, forms, responsive design, and UX validation --- # Playwright Browser Automation General-purpose browser automation with Playwright for testing pages, forms, responsive design, and UX validation What is it? A general-purpose browser automation skill that enables Claude to write and execute custom Playwright scripts for your specific needs. Unlike pre-built testing frameworks, Claude dynamically generates tailored automation code on-the-fly for any task - from simple page tests to complex multi-step flows. The browser runs visibly by default for easy debugging and verification. ## How to use it? The skill follows a conversational workflow: * Describe Your Need - Simply tell Claude what you want to test or automate (e.g., "Test the homepage", "Check if the contact form works", "Verify the signup flow") * Auto-Detection - The skill automatically detects running development servers on your machine. If testing an external site, Claude will ask for the URL. * Code Generation - Claude writes custom Playwright code tailored to your specific request and saves it to `/tmp/playwright-test-*.js` * Execution - The script executes via a universal executor (`run.js`) that handles proper module resolution. The browser opens visibly by default so you can watch the automation in real-time. * Results - View console output, screenshots, and any captured data. Test files are automatically cleaned from /tmp by your OS. No configuration files, no pre-built tests - just natural language requests that Claude transforms into working automation code. ## Key Features * Custom code generation - Claude writes fresh Playwright scripts tailored to your exact request, not limited to templates * Visible browser by default - Watch automation execute in real-time with `headless: false` for easy debugging * Auto-detects dev servers - Automatically finds and tests your local development server * Zero module resolution errors - Universal executor ensures proper module access without configuration * Progressive API documentation - Concise SKILL.md with full API reference loaded only when needed * Safe temp file management - Scripts written to /tmp and auto-cleaned by your OS * Works with any site - Test local development servers or external websites * Comprehensive helpers - Optional utility functions available for common tasks when neededView on GitHub ### GitHub Stats StarsForksLast UpdateAuthorlackeyjbLicenseMITVersion4.0.0 ### Categories Developer ToolsTesting ### Tags playwrightbrowser-automatione2e-testingweb-testingautomation ### Features 💻 Code Execution ## Related Skills More from Developer Tools ### iOS Simulator Skill 21 production-ready scripts for iOS app testing, building, and automation with semantic UI navigation 200Conor LuddyDeveloper ToolsTesting00 ### Auto Write Tests Automated test writing orchestration system that discovers test infrastructure, analyzes code changes, and dispatches parallel agents to write comprehensive test coverage 433NeoLabHQTestingDeveloper Tools00 ### Auto Fix Tests Systematic failing test repair orchestration with auto-discovery, parallel agent fixes, and full verification, emphasizing fixing tests without modifying business logic 433NeoLabHQTestingDeveloper Tools00 --- **Source**: https://github.com/lackeyjb/playwright-skill **Author**: lackeyjb **License**: https://opensource.org/licenses/MIT **GitHub Stars**: 180 **Tags**: playwright, browser-automation, e2e-testing, web-testing, automation
Related skills 6
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use...
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
grill-with-docs
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
minimal-run-and-audit
RigorPilot trusted execution and reporting skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end...
polish
Performs a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great.
critique
Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, automated anti-pattern detection, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.