playwright

Automate end-to-end browser tests with Playwright and AI test agents.

2|1|Updated Feb 14, 2026
One-click install
npx skills add https://github.com/hamchowderr/braynee --skill playwright-hamchowderr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: playwright
Source: https://github.com/hamchowderr/braynee/tree/main/skills/playwright
Command: npx skills add https://github.com/hamchowderr/braynee --skill playwright-hamchowderr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you reliably create and maintain end-to-end browser tests for web apps without manually guessing selectors or debugging failures blindly.

Core Features & Use Cases

  • End-to-end CLI testing: Run Playwright tests across Chromium, Firefox, and WebKit, filter by titles/paths, and debug with UI and trace.
  • AI Test Agents authoring loop: Use Planner, Generator, and Healer to plan flows, generate verified specs, and repair failing locators/waits by rerunning against a real browser.
  • Recording and diagnostics: Record tests with codegen, inspect HTML reports, and open trace files to diagnose failures efficiently.
  • Use Case: You want to add an authentication flow test for a staging web app; you run codegen for initial coverage, then use Planner → Generator → Healer to produce stable, runnable specs and fix failures until the suite is green.

Quick Start

Ask to "set up Playwright agents in my project and then plan, generate, and heal E2E tests for the login page using npx."

Frequently Asked Questions about playwright

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

FAQPage Schema
How do I generate and heal E2E browser tests for web applications?

You can generate and heal E2E browser tests by using AI Test Agents to plan flows, generate verified locators and assertions, and repair failing tests by rerunning them against a real browser using trace files.

What's the best way to record end-to-end tests without manually guessing selectors?

The best way to record tests without guessing selectors is using codegen, which records user interactions in a browser to produce initial test coverage that can then be refined into stable, runnable specs by test agents.

How do I diagnose and repair failing Playwright tests efficiently?

You diagnose and repair failing Playwright tests by opening trace files and HTML reports to inspect failures, then using the Healer agent to automatically fix broken locators and waits by rerunning against a real browser.

Do I need npx to run Playwright tests across Chromium, Firefox, and WebKit?

Yes, you need npx to run Playwright tests because it ensures the project-resolved Playwright version is used for executing specs across Chromium, Firefox, and WebKit browsers.

Can I use AI agents to plan and create end-to-end test flows for a staging web app?

Yes, you can initialize AI test agents via init-agents to plan authentication flow tests, generate verified specs, and iteratively heal failures until your staging web app test suite is green.

Why does my E2E test fail after recording it with codegen?

E2E tests recorded with codegen often fail due to unstable locators or timing issues; you can fix these by running the Generator and Healer agents to produce verified locators and repair failures from real traces.