Engineering TestingPlaywrightCoverage

Playwright Pro — Coverage

Analyze and improve Playwright test coverage.

$skillfish add ~skills/playwright-pro-coverage

Real Examples Get Started Models & Context

Real Conversations

See how the Playwright Pro — Coverage skill responds to actual requests. These are representative examples of what your AI agent will produce.

You

We're launching in 3 weeks. Which pages and flows have zero E2E coverage? Next.js App Router, about 30 routes.

Agent

Scanning your route structure and mapping against existing tests.

Coverage Matrix (30 routes):

Area	Route	Tests	Status
Auth	/login	6	Covered
Auth	/register	4	Covered
Auth	/forgot-password	0	Missing
Auth	/verify-email	0	Missing
Dashboard	/dashboard	5	Partial (no error states)
Dashboard	/dashboard/analytics	0	Missing
Billing	/billing	0	Missing
Billing	/billing/upgrade	0	Missing
Settings	/settings/profile	3	Covered
Settings	/settings/team	0	Missing
(20 more routes)	...	...	...

Coverage: 14/30 routes (47%) — 16 routes with zero tests

Prioritized Test Plan (3 weeks to launch):

Week 1: Critical

/billing + /billing/upgrade — 8 tests, use checkout templates
/forgot-password + /verify-email — 6 tests, use auth templates, quick

Week 2: High

/dashboard/analytics — chart loading, date filters; 5 tests
/settings/team — invite, remove, role change; 6 tests

Week 3: Medium

Remaining 8 lower-risk routes

Total gap: ~35 tests needed. Auto-generate Week 1 now using the billing and auth templates?

You

Our team spent last sprint writing Playwright tests. Before retrospective I want concrete numbers — how many flows do we cover now vs. 2 weeks ago? We have a test-reports/ directory with old reports.

Agent

Comparing current coverage against your last saved report.

Coverage Delta — Sprint 23 vs. Sprint 22:

Metric	Sprint 22	Sprint 23	Change
Routes with tests	14/30	22/30	+8 routes
Total tests	89	134	+45 tests
Critical flows covered	4/7	7/7	+3 critical
Auth coverage	67%	100%	+33%
Billing coverage	0%	80%	+80%
Settings coverage	33%	67%	+34%

New coverage added this sprint:

/forgot-password — 3 tests (full password reset flow)
/verify-email — 2 tests
/billing — 6 tests (including Stripe decline handling)
/billing/upgrade — 4 tests
/settings/team — 5 tests
3 missing Dashboard error states

Still uncovered (8 routes):

/onboarding/welcome-tour — medium priority
/notifications — medium
Static pages (/about, /pricing, /docs) — low, non-critical

All critical paths are now green. The 8 remaining routes are safe to defer to Sprint 24.

Save as test-reports/sprint-23-coverage.md?

Get Started

How to install and use this skill in your preferred environment.

Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase. Web-based AI can use the knowledge and frameworks, but won't have tool access.

Models & Context

Which AI models and context windows work best with this skill.

Recommended Models

Best

Claude Opus 4 Claude Sonnet 4 GPT-4.1 Gemini 2.5 Pro Grok 3 Kimi K2

Good

Claude Haiku 4.5 GPT-4.1 mini Gemini 2.5 Flash Grok 3 mini

Larger models produce more detailed, production-ready outputs.

Context Window

This skill's SKILL.md is typically 3–10 KB — fits in any modern context window.

8K Skill only

32K+ Skill + conversation

100K+ Skill + references + codebase

All current frontier models (Claude, GPT, Gemini) support 100K+ context. Use the full window for complex multi-service work.

Pro tips for best results

1

Be specific

Include numbers — users, budget, RPS — so the skill can size the architecture.

2

Share constraints

Compliance needs, team size, and existing stack all improve the output.

3

Iterate

Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.

4

Combine skills

Pair with companion skills below for end-to-end coverage.

Ready to try Playwright Pro — Coverage?

Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.