AgentStack
SKILL verified MIT Self-run

Frontend Playwright

skill-petbrains-mvp-builder-frontend-playwright · by petbrains

Visual QA gate for frontend code. ALWAYS use before delivering any UI changes - navigate, screenshot, verify console is error-free. Use for: responsive testing across viewports, form/interaction testing, debugging hydration and render issues. Catches visual bugs before users see them.

No reviews yet
0 installs
12 views
0.0% view→install

Install

$ agentstack add skill-petbrains-mvp-builder-frontend-playwright

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Frontend Playwright? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Frontend Playwright

Browser automation for visual verification. Self-check UI before delivering.

When to Use

  • After creating/modifying components → verify render
  • Before delivering code → final QA check
  • Debugging UI issues → see actual browser state
  • Responsive testing → check mobile/tablet/desktop

Process

NAVIGATE → VERIFY → FIX → DELIVER

1. Start dev server: npm run dev
2. browser_navigate → open page
3. browser_take_screenshot → visual check
4. browser_console_messages { onlyErrors: true } → MUST BE EMPTY
5. Fix issues if any → repeat
6. Deliver when clean

Tools Quick Reference

Navigation:
  browser_navigate:      { url: "http://localhost:3000" }
  browser_resize:        { width: 375, height: 812 }
  browser_wait_for:      { time: 2 } | { text: "Success" }
  browser_close:         {}

Inspection:
  browser_snapshot:           # Get element refs for interactions
  browser_take_screenshot:    { filename: "check.png", fullPage: true }
  browser_console_messages:   { onlyErrors: true }  # CRITICAL
  browser_network_requests:   {}
  browser_evaluate:           { function: "() => ..." }

Interaction:
  browser_click:   { element: "Submit button", ref: "e5" }
  browser_type:    { element: "Email input", ref: "e3", text: "user@example.com" }
  browser_hover:   { element: "Menu item", ref: "e8" }

Pre-Delivery Checklist

MUST PASS before delivery:
  ✓ browser_take_screenshot → looks correct
  ✓ browser_console_messages { onlyErrors: true } → EMPTY
  ✓ browser_network_requests → no 4xx/5xx
  ✓ Mobile viewport (375px) works

Common Workflows

Quick Verification

browser_navigate → browser_take_screenshot → browser_console_messages { onlyErrors: true }

Responsive Test

browser_resize { width: 375, height: 812 }  → screenshot
browser_resize { width: 768, height: 1024 } → screenshot
browser_resize { width: 1440, height: 900 } → screenshot

Form Test

browser_snapshot              # get refs
browser_type { ref, text }    # fill fields
browser_click { ref }         # submit
browser_wait_for { text }     # wait for result
browser_console_messages      # check errors

Common Console Errors

"Hydration mismatch":
  → Server/client render different
  → Fix: 'use client', useEffect for browser-only code

"Cannot read property of undefined":
  → Data not loaded
  → Fix: optional chaining, loading states

"Failed to fetch":
  → API error
  → Check: browser_network_requests for details

Viewport Sizes

Mobile:     { width: 375, height: 812 }   # iPhone
Tablet:     { width: 768, height: 1024 }  # iPad
Laptop:     { width: 1366, height: 768 }
Desktop:    { width: 1440, height: 900 }
Full HD:    { width: 1920, height: 1080 }

References

  • [tools.md](references/tools.md) — Full MCP tools documentation with all parameters
  • [workflows.md](references/workflows.md) — Ready-to-use verification scenarios

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.