- Home
- Skills
- Testing & Debugging
- playwright-suite-skills
Works with the AI Agents you already use
Playwright Suite Skills
Automation suites often decay into a mess of brittle locators, inconsistent patterns, and trust-destroying "green" results that hide real bugs.
$5
playwright-suite-skills
Example session with this skill installed
The checkout tests are failing. Run the suite, triage the failures, and fix anything that is a test-side defect. Refer to .claude/test-profile.md for the run commands.
- Read your context and instructions
- Compiled the playwright-suite-
I have executed the test suite and triaged the results. There were 4 failures in total. 3 were identified as test-side defects due to updated DOM structures in the checkout flow, and 1 appears to be a genuine product bug where the 'Place Order' button remains disabled despite valid input.
Triage Report
| Test Case | Failure Category | Root Cause | Action Taken |
|---|---|---|---|
checkout-shipping.spec.ts | Test Defect | Locator button.next is now ambiguous. | Updated to getByRole('button', { name: 'Continue to Shipping' }). |
checkout-payment.spec.ts | Test Defect | Input ID card-num changed to cc-number. | Updated Page Object to use new ID. |
checkout-summary.spec.ts | Product Bug | Assertion failed: Total expected $100, received $0. | Reported to team; test remains red to track bug. |
checkout-auth.spec.ts | Test Defect | Session cookie name changed in dev environment. | Updated playwright.config.ts storage state logic. |
Next steps
- Review the applied locator fixes in
checkout-shipping.spec.ts. - Verify the product bug in the checkout-summary flow with the backend team.
- Run
npx playwright test --project=chromiumto confirm the three test-side fixes now pass.
Connects securely to your tools. The creator never sees your data.
About this skill
Automation suites often decay into a mess of brittle locators, inconsistent patterns, and trust-destroying "green" results that hide real bugs. This package provides 13 specialized skills for Playwright environments, designed to maintain suite health without imposing an external house style. It works by first probing your repository's unique conventions and then operating strictly within those bounds.
What it does
- Probes conventions by inspecting your Playwright config, directory layout, and locator habits to create a local profile.
- Audits changesets by reviewing PRs in order of consequence, prioritizing weakened assertions and secrets over style.
- Hardens locators by replacing positional CSS and XPath with role-based and accessible name selectors.
- Scaffolds tests across browser, API, and database layers while mirroring existing import paths and patterns.
- Triages red suites by classifying failures into product bugs versus test defects before suggesting fixes.
- Manages infrastructure by registering fixtures, writing page objects, and resolving the correct runner commands.
How it works
- Initialize by running the probe-conventions skill to generate a
.claude/test-profile.mdfile. - Execute tasks like
write-e2e-testorharden-locators, which automatically read the profile to ensure consistency. - Manage flow using clarify-scope for vague requests or handoff-notes for session persistence.
Frameworks & tools
Specifically designed for Playwright suites using TypeScript or JavaScript. Integrates with Claude Code and Cursor to interact with the local filesystem, shell, and git diffs.
Why this beats prompting it yourself
Generic prompts often suggest "best practices" that conflict with your team's existing code style, creating friction during PRs. These skills derive their rules from your actual code, ensuring every generated spec or locator looks like your team wrote it.
Use cases
- Auditing a pull request to ensure no assertions were accidentally widened or disabled.
- Converting a brittle suite filled with XPath selectors into one using stable roles.
- Quickly scaffolding new API client methods and corresponding request specs.
- Summarizing a complex debugging session into a handoff for another developer.
Known limitations
Requires an initial convention probe to function accurately. Does not support non-Playwright runners like Cypress or Selenium. Requires access to the local shell to run tests.
Requires an initial convention probe to function accurately. Does not support non-Playwright runners. Requires shell access to execute test runs and diffs.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Requires