Test Automation Engineer

What it does

Test Automation Engineer is a Cursor agent playbook named test-automator. AgenticKit installs it so a session can adopt this role instead of acting as a generic coding assistant.

The test-automator agent protects your SaaS against regression bugs. It writes fast unit tests, comprehensive API route test suites, and Playwright end-to-end browser tests for critical checkout and authentication journeys.

Creates Vitest unit tests, Playwright E2E suites, and mock fixtures. Test automation engineer for Cursor that writes unit tests with Vitest, end-to-end user journeys with Playwright, and mock API fixtures.

Why it exists

A pile of agent files is not a team. test-automator exists so one job, test automation engineer, has a written brief, required skills, and a stop condition.

It ships in the Engineering Kit. Skills it must read: Vitest Unit & Integration Testing; Playwright End-to-End Browser Testing; Strict TypeScript Standards & Type Safety. Commands that adopt this role: /e2e-suite: Playwright End-to-End Test Suite Generator; /ship: End-to-End Feature Pipeline Shipper; /fix: Automated Bug & Exception Debugger.

When to use it

• Covering critical user flows like checkout and signup with E2E tests
• Writing unit tests for complex business logic and calculations
• Setting up automated regression testing in GitHub Actions

When not to use it

• Do not ask test-automator to do a different role's job. If you need a launch post, switch agents.
• Do not keep the same chat after this agent has finished its artifact. Start a reviewer in a new thread.
• Do not invoke every agent in the kit for a small change.

Example workflow

1. Install the Engineering Kit so .cursor/agents/test-automator is on disk.
2. Run /e2e-suite: Playwright End-to-End Test Suite Generator, or start a chat and tell Cursor to adopt the test-automator role.
3. The agent should read: Vitest Unit & Integration Testing; Playwright End-to-End Browser Testing; Strict TypeScript Standards & Type Safety.
4. It produces the artifact for this role only, then stops.
5. A different agent or you review. Same-chat self-review is not a review.

Example usage

Example: "You are test-automator. Covering critical user flows like checkout and signup with E2E tests. Read testing-vitest before you edit."

Or let the pipeline invoke it: /e2e-suite: Playwright End-to-End Test Suite Generator.

Capabilities you should actually see: Vitest and Jest unit and integration test generation

Example output

• test-automator should leave files or a written verdict, not a vibe check. Vitest and Jest unit and integration test generation Playwright end-to-end automated browser test suites
• Engineering agents should touch the slice they were given (schema, route, test, or review note) and nothing else.

Best practices

• Vitest and Jest unit and integration test generation
• Playwright end-to-end automated browser test suites
• Mock database fixtures and MSW (Mock Service Worker) setups
• Automated code coverage reporting in CI pipelines
• One role per chat unless a command is explicitly orchestrating a sequence.

Common mistakes

• Using test-automator as a synonym for 'the Cursor agent'. It is a brief, not the product.
• Skipping the required skills and hoping the role name is enough.
• Letting the writer approve its own PR.
• Invoking this agent and three unrelated ones in the same prompt.