Skip to content
website-review logo

Website Review Workflow

website-review

Use this skill when performing QA reviews of the EVOLEA website (Astro frontend at localhost:4321), Admin Dashboard V2 (localhost:5175), or production sites (planted.com, admin.planted.com). Orchestrates visual inspection, console/network error detection, accessibility auditing, Core Web Vitals m...

mattnigh/skills_collection0installs24stars

SKILL.md

Full skill instructions

Website Review Workflow

This skill enables comprehensive QA workflows for EVOLEA web properties using Chrome DevTools MCP integration.

Prerequisites

  1. Chrome Debug Mode Running

    # Start Chrome with debug port (run once per session)
    scripts\chrome-debug.bat
    
  2. MCP Server Connected

    • Verify with /​mcp command - look for chrome-devtools server
    • If not connected, restart Claude Code (MCP servers load on startup)
  3. For Keystatic CMS

Target Sites

SiteURLAuth RequiredNotes
Local Devhttp://localhost:4321NoRun npm run dev
GitHub Pageshttps://cgjen-box.github.io/evolea-website/NoStatic deployment
Cloudflare Pageshttps://evolea-website.pages.devNoCloudflare deployment
Productionhttps://evolea.chNoCustom domain

Workflow Overview

+---------------------+     +---------------------+     +---------------------+
|  1. NAVIGATE &      |---->|  2. VISUAL          |---->|  3. CONSOLE/​NETWORK |
|     SCREENSHOT      |     |     INSPECTION      |     |     ERROR CHECK     |
+---------------------+     +---------------------+     +---------------------+
                                                                  |
+---------------------+     +---------------------+               |
|  6. GENERATE        |<----|  5. INTERACTIVE     |<--------------+
|     REPORT          |     |     TESTING         |               |
+---------------------+     +---------------------+               |
                                   ^                              |
                                   |            +-----------------+
                                   |            |
                            +------+------------v--+
                            |  4. ACCESSIBILITY &  |
                            |     PERFORMANCE      |
                            +----------------------+

Phase 1: Navigate and Screenshot

Goal: Capture initial page state across viewports

MCP Tools:

  • navigate_page(url) - Navigate to target URL
  • resize_page(width, height) - Set viewport size
  • take_screenshot() - Capture visual state
  • wait_for(selector, timeout) - Wait for page load

Viewport Sizes:

  • Desktop: 1440x900
  • Tablet: 768x1024
  • Mobile: 375x812

Example Workflow:

  1. Navigate to URL
  2. Wait for main content selector
  3. Screenshot desktop viewport
  4. Resize to tablet, screenshot
  5. Resize to mobile, screenshot

Phase 2: Visual Inspection

Goal: Analyze visual state and DOM structure

MCP Tools:

  • take_snapshot() - Capture DOM snapshot (accessibility tree)
  • evaluate_script(script) - Run DOM queries

Checks:

  • Layout renders correctly
  • Images load (no broken images)
  • Fonts load correctly
  • No overlapping elements
  • Responsive breakpoints work

Phase 3: Console and Network Error Check

Goal: Detect JavaScript errors and failed requests

MCP Tools:

  • list_console_messages() - Get all console output
  • get_console_message(id) - Get specific message details
  • list_network_requests() - Get all network activity
  • get_network_request(id) - Get request/​response details

Error Categories:

  • Critical: JavaScript exceptions, failed API calls (4xx/​5xx)
  • Warning: Console warnings, slow requests (>3s)
  • Info: Deprecation notices, third-party issues

Phase 4: Accessibility and Performance

Accessibility (WCAG 2.1 AA)

Automated Checks via evaluate_script:

// Check for missing alt text
document.querySelectorAll('img:not([alt])').length

// Check for form labels
document.querySelectorAll('input:not([aria-label]):not([id])').length

// Check for heading hierarchy
Array.from(document.querySelectorAll('h1,h2,h3,h4,h5,h6')).map(h => h.tagName)

Manual Checks:

  • Keyboard navigation works (Tab through page)
  • Focus states visible
  • Screen reader landmarks present
  • Touch targets >= 44px

Performance (Core Web Vitals)

MCP Tools:

  • performance_start_trace() - Begin recording
  • performance_stop_trace() - End recording
  • performance_analyze_insight() - Get analysis

Metrics to Check:

  • LCP (Largest Contentful Paint): < 2.5s good, < 4s needs improvement
  • INP (Interaction to Next Paint): < 200ms good, < 500ms needs improvement
  • CLS (Cumulative Layout Shift): < 0.1 good, < 0.25 needs improvement

Phase 5: Interactive Testing

Goal: Verify interactive elements work correctly

MCP Tools:

  • click(selector) - Click element
  • fill(selector, value) - Fill input
  • fill_form(fields) - Fill multiple form fields
  • press_key(key) - Keyboard input
  • hover(selector) - Hover state
  • handle_dialog(action) - Handle alerts/​confirms

Test Scenarios:

  • Navigation links work
  • Form submission works
  • Buttons trigger expected actions
  • Modal dialogs open/​close
  • Dropdowns/​selects function

Phase 6: Generate Report

Use TEST-REPORT-TEMPLATE.md to create structured report including:

  • Screenshots at each viewport
  • Console errors found
  • Network issues found
  • Accessibility issues
  • Performance metrics
  • Interactive test results
  • Overall pass/​fail status

Quick Commands

# Start local Astro dev server
npm run dev

# Start Chrome in debug mode
scripts\chrome-debug.bat

MCP Tools Reference (26 Total)

Input Automation

ToolPurpose
clickClick an element
dragDrag from one point to another
fillFill a form field
fill_formFill multiple form fields
handle_dialogHandle alert/​confirm/​prompt dialogs
hoverHover over an element
press_keyPress keyboard key
upload_fileUpload file to input

Navigation

ToolPurpose
close_pageClose current page/​tab
list_pagesList all open pages
navigate_pageNavigate to URL
new_pageOpen new page/​tab
select_pageSwitch to specific page
wait_forWait for element/​condition

Emulation

ToolPurpose
emulateEmulate device (mobile, etc.)
resize_pageSet viewport dimensions

Performance

ToolPurpose
performance_start_traceStart performance recording
performance_stop_traceStop and get trace data
performance_analyze_insightAnalyze performance metrics

Network

ToolPurpose
list_network_requestsGet network request history
get_network_requestGet specific request details

Debugging

ToolPurpose
take_screenshotCapture visual screenshot
take_snapshotCapture accessibility tree (DOM)
list_console_messagesGet browser console logs
get_console_messageGet specific console message
evaluate_scriptExecute JavaScript in page

Reference Documents

  • TESTING-MANUAL.md - Detailed test cases for each page type
  • TEST-REPORT-TEMPLATE.md - Report format
  • AUTH-SETUP.md - Production authentication setup
  • .claude/​skills/​EVOLEA-SKILL.md - Visual design reference

More skills from mattnigh

spring-framework-patterns logo
mattnigh/skills_collection

spring-framework-patterns

Comprehensive Spring Framework and Spring Boot best practices including dependency injection patterns, bean lifecycle and scopes, REST API development, Spring Data JPA, service layer design, Spring Security, testing strategies, caching, AOP, async processing, error handling, and common anti-patte...

24 0
View

TypeScript厳格モードによる型安全性設計を専門とするスキル。 📖 参照書籍: - 『Effective TypeScript』(Dan Vanderkam): 型設計 📚 リソース参照: - `resources/Level1_basics.md`: レベル1の基礎ガイド - `resources/Level2_intermediate.md`: レベル2の実務ガイド - `resources/Level3_advanced.md`: レベル3の応用ガイド - `resources/Level4_expert.md`: レベル4の専門ガイド - `resources/di...

24 0
View
deploying-cloud-k8s logo
mattnigh/skills_collection

deploying-cloud-k8s

Deploys applications to cloud Kubernetes (AKS/GKE/DOKS) with CI/CD pipelines. Use when deploying to production, setting up GitHub Actions, troubleshooting deployments. Covers build-time vs runtime vars, architecture matching, and battle-tested debugging.

24 0
View
moai-alfred-agent-guide logo
mattnigh/skills_collection

moai-alfred-agent-guide

19-agent team structure, decision trees for agent selection, Haiku vs Sonnet model selection, and agent collaboration principles. Use when deciding which sub-agent to invoke, understanding team responsibilities, or learning multi-agent orchestration.

24 0
View
mermaid-diagram-generator logo
mattnigh/skills_collection

mermaid-diagram-generator

Converts architecture descriptions, module specs, or workflow docs into Mermaid diagrams. Use when visualizing brick module relationships, workflows (DDD, investigation), or system architecture. Supports: flowcharts, sequence diagrams, class diagrams, state machines, entity relationship diagrams,...

24 0
View
pre-flight-check logo
mattnigh/skills_collection

pre-flight-check

INVOKE FIRST before any code work. Validates git workflow (branch, issue, worklog) and checks approach. Use at START of every task and END before completing. Prevents skipped steps.

24 0
View
browser-dev-tools logo
mattnigh/skills_collection

browser-dev-tools

This skill should be used when working with browser-rendered artifacts (i.e. Bun, React/React Native) to proactively validate that development work on localhost is being built appropriately and to support debugging browser-rendered content. Use this skill after making frontend changes to verify t...

24 0
View
lead-dev logo
mattnigh/skills_collection

lead-dev

Lead Développeur - Coordination technique opérationnelle, code review, mentoring et livraison. Pair de web-dev-process au niveau OPÉRATIONS.

24 0
View
worker-monitor logo
mattnigh/skills_collection

worker-monitor

Monitor Docker workers, RQ queue health, and auto-scale workers (max 4). Use when: checking job progress, monitoring queue depth, scaling workers up/down, diagnosing slow processing, or waiting for jobs to complete. Referenced by data-quality skill during reprocessing.

24 0
View
quality-advisor logo
mattnigh/skills_collection

quality-advisor

Proactive quality guidance system that monitors artifact creation and provides real-time feedback on documentation quality

24 0
View
bump-version logo
mattnigh/skills_collection

bump-version

This skill should be used when the user wants to bump the version number in the workspace. It updates versions across all pyproject.toml files (root, tde, and tda packages) and the CHANGELOG.md to keep them synchronized.

24 0
View

Popular AI tools

Kaiber logo
Video

Kaiber

Generate, edit, and beat-sync AI video with leading models in one workspace.

Paid
View
Vimcal logo
Productivity

Vimcal

The world's fastest calendar for remote work

Free
View

Transform Your Design with AI Designer by ImgCreator.ai

Freemium
View
Akool AI logo
Content & writing

Akool AI

Revolutionizing Video Production with AI-Powered Creativity

Paid
View

Extend an image past the frame and let AI fill the new aspect ratio.

Freemium
View
StarByFace logo
Security

StarByFace

Discover your celebrity doppelgänger with StarByFace!

Free
View
C

ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.

Freemium
View
Opus Clip logo
Coding & apps

Opus Clip

Opus.ai: Revolutionize Your Web Experience

Free
View