visual-qa
Complete visual QA - screenshots with full-page scroll to trigger animations, then analyze with Claude. Run after CSS/template changes.
Best use case
visual-qa is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. Complete visual QA - screenshots with full-page scroll to trigger animations, then analyze with Claude. Run after CSS/template changes.
Complete visual QA - screenshots with full-page scroll to trigger animations, then analyze with Claude. Run after CSS/template changes.
Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.
Practical example
Example input
Use the "visual-qa" skill to help with this workflow task. Context: Complete visual QA - screenshots with full-page scroll to trigger animations, then analyze with Claude. Run after CSS/template changes.
Example output
A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.
When to use this skill
- Use this skill when you want a reusable workflow rather than writing the same prompt again and again.
When not to use this skill
- Do not use this when you only need a one-off answer and do not need a reusable workflow.
- Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/visual-qa/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How visual-qa Compares
| Feature / Agent | visual-qa | 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?
Complete visual QA - screenshots with full-page scroll to trigger animations, then analyze with Claude. Run after CSS/template changes.
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
# Visual QA Skill Automated visual testing that properly handles GSAP animations by scrolling through the entire page before capturing screenshots. ## Usage Ask Claude to run visual QA: - "Run visual QA on the CSR site" - "Take screenshots of all pages and analyze them" - "Check the visual state of the website" ## What This Skill Does 1. **Full-Page Scroll** - Scrolls through entire page in increments to trigger all GSAP/ScrollTrigger animations 2. **Multi-Device Screenshots** - Desktop (1920px), Tablet (768px), Mobile (375px) 3. **Parallel Processing** - Uses Haiku sub-agents to analyze multiple pages simultaneously 4. **Visual Analysis** - Reviews screenshots for issues ## Pages Tested | Page | URL | |------|-----| | Home | https://csrdevelopment.com/ | | About | https://csrdevelopment.com/about/ | | Portfolio | https://csrdevelopment.com/portfolio/ | | Contact | https://csrdevelopment.com/contact/ | | Privacy Policy | https://csrdevelopment.com/privacy-policy/ | | Terms | https://csrdevelopment.com/terms-of-service/ | ## Screenshot Script Location: `/root/.claude/skills/visual-qa/screenshot.py` ### Single Page ```bash python3 /root/.claude/skills/visual-qa/screenshot.py --url https://csrdevelopment.com/about/ ``` ### All Pages ```bash python3 /root/.claude/skills/visual-qa/screenshot.py --all ``` ### Output Screenshots saved to: `/home/dev/screenshots/` ## Parallel Analysis with Haiku When running full visual QA, launch multiple Haiku agents to analyze different pages simultaneously: ``` Agent 1: Analyze Home + About screenshots Agent 2: Analyze Portfolio + Contact screenshots Agent 3: Analyze Legal pages screenshots ``` ## Visual QA Checklist ### All Pages - [ ] Header visible and logo centered - [ ] Menu button works - [ ] Footer links present - [ ] No horizontal scroll - [ ] Text readable at all sizes ### Home Page - [ ] Hero video/image loaded - [ ] Hero text visible (not opacity 0) - [ ] Property cards show with images - [ ] Animations completed ### About Page - [ ] Team member photos loaded (not placeholders) - [ ] Bio text visible - [ ] Images have grayscale filter ### Portfolio - [ ] Property grid displays - [ ] Status badges visible - [ ] Different images for each property ### Contact - [ ] Form fields visible - [ ] Contact info displayed - [ ] Submit button styled ### Property Detail - [ ] Hero image loaded - [ ] Property details sidebar - [ ] Inquiry form present
Related Skills
visual-design-foundations
Apply typography, color theory, spacing systems, and iconography principles to create cohesive visual designs. Use when establishing design tokens, building style guides, or improving visual hierarchy and consistency.
ui-visual-validator
Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use PROACTIVELY to verify UI modifications have achieved their intended goals through comprehensive visual analysis.
azure-resource-visualizer
Analyze Azure resource groups and generate detailed Mermaid architecture diagrams showing the relationships between individual resources. USE FOR: create architecture diagram, visualize Azure resources, show resource relationships, generate Mermaid diagram, analyze resource group, diagram my resources, architecture visualization, resource topology, map Azure infrastructure DO NOT USE FOR: creating/modifying resources (use azure-deploy), security scanning (use azure-security), performance troubleshooting (use azure-diagnostics), code generation (use relevant service skill)
high-end-visual-design
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.
pitch-deck-visuals
Investor pitch deck structure with slide-by-slide framework, visual design rules, and data presentation. Covers the 12-slide framework, chart types, team slides, and common investor turn-offs. Use for: fundraising decks, investor presentations, startup pitch, demo day, grant proposals. Triggers: pitch deck, investor deck, startup pitch, fundraising deck, demo day, pitch presentation, investor presentation, seed deck, series a deck, pitch slides, startup presentation, vc pitch, investor meeting
data-visualization-tool
Chart and visualization generation for DBX Studio. Use when a user wants to visualize data — bar charts, line graphs, pie charts, scatter plots, etc.
scientific-visualization
Create publication figures with matplotlib/seaborn/plotly. Multi-panel layouts, error bars, significance markers, colorblind-safe, export PDF/EPS/TIFF, for journal-ready scientific plots.
schema-visualizer
Generate database schema diagrams, ERDs, and documentation from database schemas.
visual-engine-skill
Extend and apply the Visual Experience Engine across landing pages, inspiration galleries, and demos using safe, persona-aware animations and layouts. Use when adding or modifying visual experiences.
d3js-visualization
Professional data visualization creation using D3.js with support for interactive charts, custom visualizations, animations, and responsive design. Use for: (1) Creating custom interactive charts, (2) Building dashboards, (3) Network/graph visualizations, (4) Geographic data mapping, (5) Time series analysis, (6) Real-time data visualization, (7) Complex multi-dimensional data displays
ascii-visualizer
Creates beautiful ASCII art visualizations for plans, architectures, workflows, and data. This skill should be used when explaining system architecture, creating implementation plans, showing workflows, visualizing comparisons, or documenting file structures. NOT for code syntax highlighting or markdown tables. User explicitly loves ASCII art - use liberally for visual communication.
fiftyone-embeddings-visualization
Visualize datasets in 2D using embeddings with UMAP or t-SNE dimensionality reduction. Use when users want to explore dataset structure, find clusters in images, identify outliers, color samples by class or metadata, or understand data distribution. Requires FiftyOne MCP server with @voxel51/brain plugin installed.