mcpField
P
playwright-test

playwright-test

github.com/posthogTesting & quality40.5k217 installsUpdated today
Repository

About playwright-test

A skill for planning and implementing end-to-end Playwright tests for features. It requires UI-based assertions, repeated runs to check for flakiness, and a final completion report.

Key features

  1. 01Plan tests through browser exploration
  2. 02Assert on UI changes
  3. 03Implement tests using nearby patterns
  4. 04Debug failures until tests pass
  5. 05Repeat tests to detect flakiness

Use cases

  1. 01Designing an end-to-end feature test
  2. 02Verifying UI interactions
  3. 03Investigating failing Playwright tests
  4. 04Checking test stability across repeated runs

MCP support

The skill directs the agent to use Playwright MCP browser tools for exploration, including navigation, clicks, and screenshots.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/posthog/posthog --skill playwright-test

After installing, type/playwright-testin Claude Code to confirm it loaded.

Details

From the project README

Read @playwright/README.md for best practices, gotchas, and how to run tests.

Rules

  • Follow the best practices in the README strictly
  • After UI interactions, always assert on UI changes, do not assert on network requests resolving
  • Keep looping until all tests pass. Do not give up or ask the user for help. You must resolve every failure yourself.

Instructions

You are to plan an end to end playwright test for a feature.

Step 1: Plan the test(s) to be done.

Use the Playwright MCP tools (e.g., mcp__playwright__browser_navigate, mcp__playwright__browser_click, mcp__playwright__browser_screenshot) to interact with the browser and plan your tests.

After your exploration, present the plan to me for confirmation or any changes.

Step 2: Implement the test plan
  • Write the tests, making sure to use common patterns used in neighbouring files.
  • Run the tests with BASE_URL='http://localhost:8010' pnpm --filter=@posthog/playwright exec playwright test <file name> --retries 0 --workers 3
  • Debug any failures. Look at screen shots, if needed launch the playwright mcp skills to interact with the browser. Go back to step 1 after attempting a fix.
Step 3: Ensure no flaky tests

After all tests pass in the file, run with --repeat-each 10 added to the command. This will surface any flaky tests.

If any test fails across the 10 runs, treat it as a real failure: go back to Step 2, debug, fix, and re-run Step 3. Do not proceed to Step 4 until every run of every test passes.

Step 4: Report

Once all tests pass, output a single line: Testing Complete

Comments

Markdown supported