webtricks-browser-qa-audit
Audit live websites using Playwright MCP for browser-based QA. Covers accessibility snapshots, screenshot verification, interactive element testing, and tier differentiation audits. Use after deploying web changes to verify they work. Tags: webtricks, QA, testing, playwright, audit.
Best use case
webtricks-browser-qa-audit is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Audit live websites using Playwright MCP for browser-based QA. Covers accessibility snapshots, screenshot verification, interactive element testing, and tier differentiation audits. Use after deploying web changes to verify they work. Tags: webtricks, QA, testing, playwright, audit.
Teams using webtricks-browser-qa-audit should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/webtricks-browser-qa-audit/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How webtricks-browser-qa-audit Compares
| Feature / Agent | webtricks-browser-qa-audit | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Audit live websites using Playwright MCP for browser-based QA. Covers accessibility snapshots, screenshot verification, interactive element testing, and tier differentiation audits. Use after deploying web changes to verify they work. Tags: webtricks, QA, testing, playwright, audit.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Browser-Based QA Audit — WebTricks
Use Playwright MCP to audit live deployed websites. Verify interactive elements work, content is correct, animations render, and tier differentiation functions properly.
## When to Apply
- After deploying changes to a live website
- When the user says something "doesn't work" or "is broken"
- Before presenting a site to a client
- When auditing tier/pricing functionality across multiple pages
## Audit Protocol
### Step 1: Full Slide/Page Audit
Navigate to the site and check EVERY page/slide systematically:
```
browser_navigate({ url: "https://site.vercel.app" })
browser_take_screenshot → Landing page
browser_snapshot → Get accessibility tree
// Navigate through all pages
browser_press_key({ key: "ArrowRight" }) // Next slide
browser_take_screenshot
browser_snapshot
// ... repeat for all pages
```
### Step 2: Interactive Element Verification
For each page, check:
1. **Are interactive elements real?** Check the accessibility tree for `<button>` vs `<span>`:
- `button "Foundation · $5K"` = REAL button ✅
- `text "Foundation $5K: 1 week"` with `cursor: auto` = FAKE, decorative ❌
2. **Do buttons respond to clicks?**
```
browser_click({ ref: "eXX", element: "Foundation tier button" })
browser_snapshot → Did the content change?
```
3. **Does hover work?**
```
browser_hover({ ref: "eXX", element: "Pipeline step node" })
```
### Step 3: Tier Differentiation Audit
For sites with tier selectors, verify EACH tier produces different content:
| Check | Method |
|-------|--------|
| Button is clickable | `browser_click` → verify response |
| Content changes | `browser_snapshot` before/after → compare |
| Count changes | e.g., "7 of 15" → "11 of 15" → "15 of 15" |
| Visual state changes | Cards lock/unlock, opacity changes |
| Correct labels | "Upgrade to Production" vs "Upgrade to Ecosystem" |
### Step 4: Viewport and Clipping Check
Common bugs to look for:
- **Buttons above viewport:** `items-center` on a tall page pushes top content above visible area
- **Scroll requirements:** Count how many items are visible without scrolling
- **Mobile vs desktop:** Check if elements hidden on mobile (`hidden md:flex`)
Use the accessibility snapshot to check element positions:
```yaml
# Look for negative positions or elements outside viewport
- button "Foundation" [ref=e42] [cursor=pointer]:
# Check if this appears in the visible area
```
### Step 5: Console Errors
```
browser_console_messages
```
Zero errors = clean. Any errors = report immediately.
## Report Template
For each page/slide:
```markdown
## Slide X: [Name]
**Screenshot:** [description]
**Interactive elements:** [list all buttons/toggles/tabs]
**Tier differentiation:** [None / Works / Broken — details]
### What's broken:
- [specific issue with evidence]
### What works:
- [confirmed working elements]
```
## Common Failures to Check
| Failure | How to Detect |
|---------|--------------|
| Fake buttons (spans not buttons) | Accessibility tree shows `text` not `button` |
| Tier selector doesn't change content | Snapshot before/after click is identical |
| Content clipped above viewport | Elements with negative top positions |
| Hardcoded "Upgrade to Production" | Still says "Production" when on Production tier |
| Scripted demo labeled "CONNECTED" | Misleading status badges |
| Internal metrics shown as client outcomes | "18K+ leads" when client has zero leads |
| Price comparison that backfires | Competitor appears cheaper in the comparison |
## Checklist
- [ ] Every slide/page audited with screenshot + snapshot
- [ ] All interactive elements verified (click, hover, type)
- [ ] Tier selectors tested on EVERY slide that has them
- [ ] Content changes confirmed per tier (not just visual)
- [ ] Viewport clipping checked (no hidden buttons)
- [ ] Console errors checked (zero expected)
- [ ] Report generated with per-slide findingsRelated Skills
webtricks-tier-pricing-ui
Build interactive tier-based pricing UI with lock/unlock states, progressive disclosure, and cross-slide consistency. Use when building pricing pages, tier selectors, or feature comparison grids. Tags: webtricks, pricing, tiers, SaaS.
webtricks-animated-pipeline
Build animated data flow pipelines with SVG circuits, traveling dots, and ambient animations using Framer Motion + SVG. Use when visualizing architecture, workflows, API pipelines, or any step-by-step data flow. Tags: webtricks, animation, pipeline, SVG, architecture.
nextjs-production-bug-audit
Use when reviewing a Next.js marketing site or app for production readiness, before go-live, or when users report visual or functional bugs. Covers 26-point checklist across CRITICAL, HIGH, MEDIUM, LOW severity.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
vercel-react-native-skills
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
ui-ux-pro-max
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.
tool-definition-patterns
Standards for defining AI agent tools based on Cline's system prompt patterns. Covers parameter typing, documentation, edit formats, safety mechanisms, and operational best practices.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code