Playwright Screenshot Inspector
This handles the hard part of visual testing: making sure screenshots actually capture rendered content before you analyze them. The core insight is smart: traditional pixel comparison tells you *what* changed, but LLM vision analysis tells you *why* it matters. It's built around waiting for React hydration properly (not just network idle), running Playwright headless to avoid window spam, and then feeding screenshots to Claude with specific questions about theme compliance, broken layouts, or accessibility issues. Most useful when you're testing UI states that are annoying to verify manually, like dark mode switches or responsive breakpoints. The code patterns for content verification before screenshot capture are genuinely helpful.
- skills.sh installs
- 132
- GitHub stars
- 113
- last updated
- Jun 3, 2026
Install
$ npx -y skills add erichowens/some_claude_skills --skill playwright-screenshot-inspector --agent claude-codeInstalls into .claude/skills of the current project.
Files
Playwright Screenshot Inspector
LLM-powered visual testing expert for automated screenshot capture, analysis, and UI verification using Playwright with multimodal AI inspection.
Activation Triggers
Activate on:
- "screenshot test", "visual test", "screenshot inspection"
- "playwright headless", "playwright screenshot"
- "UI verification", "visual regression"
- "theme compliance test", "dark mode test", "light mode test"
- "automated screenshot", "capture and analyze"
- "compare screenshots", "visual diff"
NOT for:
- Simple one-off screenshots (use browser DevTools)
- Pixel-perfect comparison without AI (use native Playwright
toHaveScreenshot) - Non-web UI testing (use platform-specific tools)
- Performance testing (use Lighthouse/WebPageTest)
Core Philosophy
Traditional visual testing compares pixels. LLM-powered visual testing understands semantics.
Instead of "these 50 pixels changed", LLM inspection answers:
- "Is the content actually rendered?"
- "Does the theme switch correctly?"
- "Are interactive elements visible and properly styled?"
- "What's broken vs. what's just different?"
The Screenshot Inspection Loop
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/erichowens/some_claude_skills
- Category
- Testing & QA
- First seen
- Jun 3, 2026
More from erichowens/some_claude_skills
All 73- Reactive Dashboard Performance132
- Vaporwave Glassomorphic Ui Designer131
- Seo Visibility Expert130
- Mcp Creator129
- Api Architect127
- Jungian Psychologist127
- Drizzle Migrations126
- Team Builder126
- Security Auditor123
- Devops Automator121
- Large Scale Map Visualization121
- Native App Designer121
- Prompt Engineer121
- Chatbot Analytics120
- Fancy Yard Landscaper120
- Data Pipeline Engineer119
- Test Automation Expert119
- Web Wave Designer119
- Orchestrator118
- React Performance Optimizer118
- Automatic Stateful Prompt Improver117
- Hipaa Compliance116
- Skill Architect116
- Modern Auth 2026115
Recommended
More Testing & QA
alicloud-ai-audio-cosyvoice-voice-clone-testcinience/alicloud-skillsMinimal CosyVoice voice clone smoke test for Model Studio voice-enrollment.122skills.sh installsalicloud-ai-audio-cosyvoice-voice-design-testcinience/alicloud-skillsMinimal CosyVoice voice design smoke test for Model Studio voice-enrollment.121skills.sh installs
Statistical Hypothesis Testingaj-geddes/useful-ai-promptsConduct statistical tests including t-tests, chi-square, ANOVA, and p-value analysis for statistical significance, hypothesis validation, and A/B testing0skills.sh installs