firefrost-gaming/claude-skills-reference

Files

Alireza Rezvani d33d03da50 feat: add playwright-pro plugin — production-grade Playwright testing toolkit (#254 )

Complete Claude Code plugin with:
- 9 skills (/pw:init, generate, review, fix, migrate, coverage, testrail, browserstack, report)
- 3 specialized agents (test-architect, test-debugger, migration-planner)
- 55 test case templates across 11 categories (auth, CRUD, checkout, search, forms, dashboard, settings, onboarding, notifications, API, accessibility)
- TestRail MCP server (TypeScript) — 8 tools for bidirectional sync
- BrowserStack MCP server (TypeScript) — 7 tools for cross-browser testing
- Smart hooks (auto-validate tests, auto-detect Playwright projects)
- 6 curated reference docs (golden rules, locators, assertions, fixtures, pitfalls, flaky tests)
- Leverages Claude Code built-ins (/batch, /debug, Explore subagent)
- Zero-config for core features; TestRail/BrowserStack via env vars
- Both TypeScript and JavaScript support throughout

Co-authored-by: Leo <leo@openclaw.ai>

2026-03-05 13:50:05 +01:00

906 B

Raw Blame History

Golden Rules

getByRole() over CSS/XPath — resilient to markup changes, mirrors assistive technology
Never page.waitForTimeout() — use expect(locator).toBeVisible() or page.waitForURL()
Web-first assertions — expect(locator) auto-retries; expect(await locator.textContent()) does not
Isolate every test — no shared state, no execution-order dependencies
baseURL in config — zero hardcoded URLs in tests
Retries: 2 in CI, 0 locally — surface flakiness where it matters
Traces: 'on-first-retry' — rich debugging artifacts without CI slowdown
Fixtures over globals — share state via test.extend(), not module-level variables
One behavior per test — multiple related expect() calls are fine
Mock external services only — never mock your own app; mock third-party APIs, payment gateways, email

906 B Raw Blame History

Golden Rules

906 B

Raw Blame History