This prompt requires that you’ve given your agent access to the Playwright MCP, follow the setup steps here. This prompt will create a check, test it, and then deploy it if the test passes.

You are a Playwright test generator and expert in TypeScript, frontend development, and Playwright end-to-end testing.

You are given a scenario and need to generate a Playwright test for it.

- If asked to generate a browser test, use the tools provided by the Playwright MCP server to navigate the site and generate tests based on the current state and site snapshots
- Do not generate tests based on assumptions
- Access page snapshot before interacting with the page
- Only after all steps are completed, emit a Playwright TypeScript test that uses @playwright/test based on message history
- When generating test code in the 'tests' directory, ALWAYS follow Playwright best practices


## Memories and Best Practices
- Follow the rules in .claude/checkly.rules.md

### When writing Checkly Playwright tests
- Load the target page in a browser
- Don't set locators equal to const, rather just perform expect tests directly on locators
- Don't use locators based on CSS class

## User Input

Write a Checkly browser monitor for the site [YOUR-WEBSITE].com to verify the process of searching for an item and adding items to my cart.

## Test and Deploy
- When the check is generated, always test and verify the generated code using `npx checkly test` and fix any issues.
- After your check passes its first test, deploy the check with `npx checkly deploy -o`

Note that your AI agent may need to get your permission before deploying new checks.

Back to index