How to use the End-to-End Testing Reviewer agent skill

What the e2e-testing skill makes the agent do

An agent skill is a folder of instructions that an AI agent loads when your request matches the skill's description. This one covers the rule 'Implement end-to-end testing', which says that E2E tests verify your application from the user's perspective across all components.

Once the skill is active, the agent checks your codebase for E2E tests covering critical user journeys such as sign-in, checkout and form submission. It also checks whether those tests run automatically in CI and block merges when they fail. The focus is on whether the rule is continuously verified, not just written down in documentation.

When it finds gaps, the agent can suggest fixes using Playwright or Cypress and explain good practices such as stable selectors and the Page Object Model.

• Reviews E2E coverage of critical user journeys
• Checks CI workflows and enforcement points for failing tests that block regressions
• Suggests adding tests with Playwright or Cypress
• Explains selectors (data-testid attributes) and test organisation

Install the skill from the ZIP download

Download the ZIP for the e2e-testing skill from this page and unzip it. The skill folder contains SKILL.md and references/rule.md. Put the unzipped folder in one of these locations, depending on how you want to use it:

For personal use across projects, place it in ~/.claude/skills/. For a single project, place it in that project's .claude/skills/ folder so it applies only there.

Alternatively, in the Claude apps, open Settings, go to Capabilities, and upload the skill under Skills.

• Personal: ~/.claude/skills/e2e-testing
• Project: .claude/skills/e2e-testing inside your repository
• Claude apps: Settings → Capabilities → Skills → upload

Trigger the skill with natural requests

You do not need a special command. Describe what you want in plain language, using the kind of wording the skill's description covers: reviewing CI coverage, automated checks, or test strategy for end-to-end testing.

Be specific about the scope. Naming the project area or the flows you care about tends to produce a more useful review.

• Review this project for E2E test coverage of sign-in, checkout and form submission.
• Check whether our Playwright tests run in CI and block merges on failure.
• Explain E2E testing best practices for our test organisation and selectors.
• Add E2E tests for our critical user journeys using Playwright or Cypress.

What you need and what to expect

The skill lists no required tools, does not run scripts, and does not use the network. It is guidance-driven: it is a set of instructions plus a reference document, not a tool that runs tests itself. The agent reads your code and workflow files and reports what it finds.

Expect a review, not a formal audit. The output is informal and may miss gaps, so it is not suitable as evidence for projects that need formal compliance certification.

• No listed requirements
• No scripts included
• No network use
• Output is an informal review, not a test run

Tips for a useful review

Point the agent at the CI configuration as well as the test files, because the skill checks whether failures block regressions. Ask for exact gaps, such as a flow with no test or a workflow that does not fail the build.

The reference document covers the Playwright and Cypress examples in more detail. The sample code uses data-testid selectors such as [data-testid="email"], which are a good pattern to follow for stable tests.

• Include CI workflow files in the request
• Ask for specific flows rather than the whole app
• Use the reference examples as a starting point for new tests