build-website
Skill0 starsChanged 45 days agoMITView on GitHub
Build premium static websites using the PRISM framework (6-phase process). Use when asked to build, design, or create a website or landing page. For interactive apps with databases and auth, use build-app instead.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- CodeWithJV/agent-skillstheir own version, first seen Jun 10, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- CodeWithJV/agent-skills★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository24 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analystSkill
- build-appSkill
- business-setupSkill
- content-pipelineSkill
- content-writerSkill
- email-assistantSkill
- email-digestSkill
- ksuite-setupSkill
- meeting-prepSkill
- memorySkill
- odooSkill
- plugin-builderSkill
- qfieldcloudSkill
- qgisSkill
- quarto-slidesSkill
- research-leadSkill
- researchSkill
- r-sessionSkill
- schedulerSkill
- scrum-masterSkill
- skill-creatorSkill
- task-managerSkill
- weekly-reviewSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 45
Write the copy for each section (headlines, body, CTAs)
- Distinctive: line 74
Every animation must serve a purpose (guide attention, provide feedback)
- Distinctive: line 75
Never animate just because you can
- Very specific: line 76
Always provide prefers-reduced-motion fallback
- Distinctive: line 92
Add interactions and animations
- Distinctive: line 109
Never use stock placeholder content — write real copy or ask for it
- Distinctive: line 110
Every section must earn its place — if it doesn't serve the user journey, cut it
- Distinctive: line 113
Prefer CSS animations over JS where possible (GPU-accelerated)
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Build Website — PRISM Framework
Build premium static websites that look custom-designed, not template-generated.
When to Use
- Landing pages
- Portfolio sites
- Business websites
- Marketing pages
- Product launch pages
NOT for: Apps with databases, user auth, dashboards → use build-app instead.
The PRISM Framework
Phase 1: Position
Establish message, audience, and goal clarity before touching code.
Ask the user:
- What is this website for? (product, service, portfolio, event)
- Who is the primary audience?
- What's the single most important action a visitor should take? (CTA)
- What tone should it convey? (professional, creative, technical, playful)
- Are there any websites you admire or want to reference?
Read: context/my-business.md and context/my-voice.md for brand context.
Output: Clear creative brief with: audience, goal, CTA, tone, references.
Phase 2: Rough
Structure and hierarchy planning. No code yet.
- Define the page sections (hero, features, testimonials, CTA, footer)
- Write the copy for each section (headlines, body, CTAs)
- Plan the visual hierarchy (what draws the eye first, second, third)
- Map the user journey (land → scan → engage → convert)
Output: Section-by-section wireframe in markdown with copy.
Phase 3: Identity
Design system definition.
- Typography — Choose 2 fonts: heading (personality) + body (readability)
- Colors — Primary, secondary, accent. Dark/light modes.
- Spacing — Consistent scale (4px base, 8, 16, 24, 32, 48, 64, 96)
- Components — Button styles, card styles, section patterns
- Design tokens — Define as CSS custom properties
Output: Design system as CSS variables and component specifications.
Phase 4: Sensation
The "wow" layer that separates premium from template.
- Micro-interactions — Button hovers, scroll reveals, focus states
- Scroll animations — GSAP ScrollTrigger for section entrances
- Visual effects — Glassmorphism, gradients, grain textures, shadows
- Typography animation — Text reveals, counter animations
- Performance budget — Keep FCP under 1.5s, LCP under 2.5s
Rules:
- Every animation must serve a purpose (guide attention, provide feedback)
- Never animate just because you can
- Always provide
prefers-reduced-motionfallback
Phase 5: Make
Build the website.
Stack:
- Astro (static site generator)
- Tailwind CSS (utility-first styling)
- GSAP (animations)
- Vanilla JS (no heavy frameworks for static sites)
Build order:
- Scaffold Astro project
- Implement design tokens as Tailwind config
- Build sections top-to-bottom (hero first)
- Add interactions and animations
- Responsive design (mobile → tablet → desktop)
- Dark mode (if specified)
Phase +Measure
Quality assurance.
- Performance — Lighthouse score > 90 on all metrics
- Accessibility — WCAG 2.1 AA compliance, keyboard navigation, screen reader testing
- SEO — Meta tags, Open Graph, structured data, sitemap
- Responsive — Test at 320px, 768px, 1024px, 1440px
- Cross-browser — Chrome, Firefox, Safari minimum
- CTA effectiveness — Is the primary action obvious and easy?
Rules
- Never use stock placeholder content — write real copy or ask for it
- Every section must earn its place — if it doesn't serve the user journey, cut it
- Mobile-first responsive design
- Performance is non-negotiable — no heavy libraries for simple effects
- Prefer CSS animations over JS where possible (GPU-accelerated)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

