website-preview
Take screenshots and interact with the rendered Jekyll website
Install
mkdir -p .claude/skills/website-preview && curl -L -o skill.zip "https://mcp.directory/api/skills/download/2004" && unzip -o skill.zip -d .claude/skills/website-preview && rm skill.zipInstalls to .claude/skills/website-preview
About this skill
Website Preview
Render the Jekyll site locally, take screenshots, and verify design changes visually using ChromeDriver and browser automation.
When to use this skill
Use this skill when:
- Modifying CSS, SCSS, or any styling files
- Editing HTML layouts (
_layouts/) or includes (_includes/) - Making changes that affect visual appearance
- The user asks to see how changes look
- You need to verify a design change worked correctly
- Working on any front-end aspects of the website
Invoke this skill proactively after making visual changes to the site.
How to use this skill
Step 1: Check Prerequisites
Before taking screenshots, verify both Jekyll and ChromeDriver are running.
Check Jekyll server:
curl -s -o /dev/null -w "%{http_code}" http://localhost:4000/ 2>/dev/null || echo "not running"
If not running (not 200), start it in background:
bundle exec jekyll serve --host 0.0.0.0 &
Wait a few seconds for it to build.
Check ChromeDriver:
cat /tmp/chromedriver_port 2>/dev/null || echo "not running"
If not running, start it:
./browser.sh chromedriver
This finds Chrome automatically and starts ChromeDriver on a free port.
Step 2: Take Screenshots
Use ./browser.sh for browser automation:
./browser.sh start http://localhost:4000/
./browser.sh screenshot /tmp/preview.png
./browser.sh dark
./browser.sh screenshot /tmp/preview-dark.png
./browser.sh mobile
./browser.sh screenshot /tmp/preview-mobile-dark.png
./browser.sh light
./browser.sh screenshot /tmp/preview-mobile-light.png
./browser.sh desktop
./browser.sh nav http://localhost:4000/2026/course-shell/
./browser.sh screenshot /tmp/course-shell.png
./browser.sh stop
Mode commands (dark, light, mobile, desktop) persist until changed.
Step 3: View Screenshots
After taking a screenshot, use the Read tool to view it:
Read /tmp/preview.png
Inspecting Elements
Execute JavaScript to query the page:
./browser.sh js "document.querySelector('nav').getBoundingClientRect()"
After Making Changes
After modifying CSS/HTML:
- Jekyll will auto-rebuild (watch for "Regenerating:" in Jekyll output)
- Refresh:
./browser.sh nav http://localhost:4000/ - Take a new screenshot to verify changes
Common Pages to Check
- Homepage:
http://localhost:4000/ - Current year index:
http://localhost:4000/2026/ - Lecture page:
http://localhost:4000/2026/course-shell/ - About page:
http://localhost:4000/about/
ChromeDriver Lifecycle
Keep ChromeDriver running across multiple previews during a session. Only kill it when no more browser interactions are expected.
./browser.sh stop- Ends the browser session (optional between screenshots)./browser.sh kill- Stops ChromeDriver entirely (only when done with all design work)
You do not need to run ./browser.sh kill after each preview. Start ChromeDriver once at the beginning and leave it running.
Troubleshooting
Jekyll not rebuilding: Run bundle exec jekyll build manually
ChromeDriver errors: Kill and restart
./browser.sh kill
./browser.sh chromedriver
Session errors: Stop any existing session first
./browser.sh stop
You might also like
flutter-development
aj-geddes
Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.
drawio-diagrams-enhanced
jgtolentino
Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.
ui-ux-pro-max
nextlevelbuilder
"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). 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."
godot
bfollington
This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.
nano-banana-pro
garg-aayush
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
fastapi-templates
wshobson
Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.
Related MCP Servers
Browse all serversPuppeteer is a browser automation studio server for LLMs, enabling web page interaction, screenshots, and testing with S
Enhance software testing with Playwright MCP: Fast, reliable browser automation, an innovative alternative to Selenium s
MCP server for full computer use on Windows. Control mouse, keyboard, take screenshots, manage windows, and automate des
Unlock browser automation studio with Browserbase MCP Server. Enhance Selenium software testing and AI-driven workflows
Automate desktop tasks with Computer Control: mouse, keyboard, screenshots, OCR & window management. Power Automate Desk
DebuggAI enables zero-config end to end testing for web applications, offering secure tunnels, easy setup, and detailed
Stay ahead of the MCP ecosystem
Get weekly updates on new skills and servers.