Official
Disciplined debugging loop. Reproduce, isolate, diagnose, fix.
DebugDiagnosisTroubleshooting
By use case
Top Testing & QA Skills
Webapp testing, Playwright flows, browser test runners, and automated QA passes.
12 skills indexed · ranked by composite score
Top 6 Testing skills
- 1.debug—Disciplined debugging loop. Reproduce, isolate, diagnose, fix.
- 2.testing-strategy—Layered test plan sized to the change's risk profile.
- 3.verify—Real feature verification — run the app, drive it, prove it works.
- 4.run—One-command app launch tailored to your project type.
- 5.webapp-testing—Test local webapps with Playwright. Generation, run, report — end-to-end.
- 6.tdd-skill—TDD with red/green/refactor as a concrete TypeScript walkthrough.
About Testing & QA
The best agent skill for testing and QA in 2026 is `verify` — it launches your project's dev server, drives the changed feature through a real browser, and returns screenshots and console logs as proof the change works, replacing the ritual of asking "did it work?" with observed behavior. Testing & QA Skills give agents the disciplined harness needed to actually verify a change works — not claim success because the types compile. The canonical Skill here is `verify`, which launches the project's dev server, drives the feature in a browser, and reports back with screenshots and console logs. Other top-ranked Skills handle test-strategy design, Playwright authoring, browser-automation flows, mocked vs. real-database integration testing, and structured test plans for new features.
These Skills shine on three workflows: pre-merge verification (run the app, click through the change, screenshot the result), test authoring (Playwright flows, API contract tests, snapshot tests), and broader test strategy (deciding what to test at what layer for a new feature). They are particularly valuable for UI changes where the agent cannot otherwise see what it built. The lesson from the community is brutal: type checking and `npm test` verify code correctness, not feature correctness. Real verification means running the app.
QA engineers, full-stack developers, and engineering teams shipping daily depend on these. Composite scoring here weights install ergonomics heavily — a verify Skill that requires twenty minutes of Playwright setup loses to one that auto-detects the project's dev command. Anthropic-authored Skills (verify, testing-strategy) and high-install Playwright Skills dominate the top of the ranking.
Ranked by score
Best Testing Skills
Skills that do testing well — ranked transparently.
Official
Layered test plan sized to the change's risk profile.
TestingStrategyCoverage
Code
Low1 min
Code
Low1 min
Official
Test local webapps with Playwright. Generation, run, report — end-to-end.
PlaywrightE2ETesting
Community
Vitest patterns: snapshots, mocks, parallel runs, in-source tests, coverage.
VitestUnit testingTypeScript
Code
Low2 min
Community
Deterministic web control. ref-based clicks/fills, no flaky selectors, parallel sessions.
BrowserAutomationAction-taking
Code
Medium4 min
Community
Playwright patterns: clicks, fills, waits, retries. The do-it-right defaults.
PlaywrightAutomation
Community
Puppeteer patterns: lifecycle, network interception, PDF generation, anti-flakiness.
PuppeteerNode.jsHeadless
Code
Medium3 min
Community
Cypress E2E with page objects, custom commands, network stubs, a11y checks.
CypressE2EFrontend testing
Code
Medium3 min
Community
Drive the iOS Simulator from the agent loop. Build and test iOS apps.
iOSSimulatorMobile
FAQ
Frequently asked
What does the verify Skill do?
It launches the project's dev server, navigates to the changed page, drives the feature using preview tools (click, fill, snapshot), and reports back with proof — screenshots, network logs, console output. It replaces the ritual of asking "did it work?" with observed behavior.
Do I need Playwright installed?
Not for verify — it uses Claude Code's built-in preview MCP. For authoring durable browser tests, the Playwright Skills set up the test runner and write the first specs.
How do testing Skills choose what to test?
The testing-strategy Skill walks the codebase and proposes a layered test plan — unit for pure logic, integration for boundaries, end-to-end for critical user flows — sized to the feature's risk profile.
Can these Skills run tests in CI?
They author the tests; CI runs them. Several Skills generate GitHub Actions configs that wire the new tests into the existing pipeline.
Mock the database or hit a real one?
The top-ranked Skills default to real databases for integration tests — mock/prod divergence is a well-known source of bugs that pass tests and fail production migrations. Unit tests stay mocked.
Other categories
Browse other use cases
Document ProcessingFrontend & UI DesignCode Quality & ReviewSecurity & AuditingDevOps & InfrastructureBrowser & Web AutomationData & AnalyticsMarketing & GrowthSEO & ContentVideo & MediaDiagrams & VisualizationAI/ML & Agent ToolingDatabases & SchemasCommunication & DocsWorkflow OrchestrationDomains & DNSWeb Hosting & DeploysPayments & BillingEmail & MessagingAPIs & Integrations