Classical Collage Web Design logo

Classical Collage Web Design

Community
krutikkkkkkkkk
classical-collage-web-design

Use when designing or building a website, landing page, Framer template, pitch visual or brand system in the "classical painting × modern tech" art direction (Renaissance / neoclassical oil paintings and marble ruins combined with laptops, phones, coins and quiet product UI, as on the Aureon fintech page and contralabs.com). Covers art direction, metaphor selection, image sourcing and AI prompts, halftone and texture techniques, exact design tokens, components, page blueprints, motion, copy voice, and Figma / Framer / Next.js build steps.

Overview

Publisherkrutikkkkkkkkk
Repositorycreative-ui
Skill nameclassical-collage-web-design
Stars
25
Forks
1
Bundled files
28
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 28 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by krutikkkkkkkkk on GitHub. Read the source before you install it.

Installation

Install the Classical Collage Web Design AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/krutikkkkkkkkk/creative-ui/tree/main/registry/skills/classical-collage-web-design
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/krutikkkkkkkkk/creative-ui.git /tmp/creative-ui
mkdir -p .claude/skills
cp -r /tmp/creative-ui/registry/skills/classical-collage-web-design .claude/skills/classical-collage-web-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Classical Collage Web Design in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Classical Collage Web Design on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Classical Collage Web Design is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Classical Collage × Modern Tech

An editorial web art direction. Old Master paintings, Greco-Roman ruins and marble are combined with modern objects and product UI: laptops, phones, gold coins, dashboards. The art carries the emotion and brand. The interface stays almost invisible: off-white paper, near-black ink, one accent and a light serif.

Two reference implementations define the two official variants:

VariantReferenceMoodBest for
Warm / "Aureon"Aureon fintech landing page (Figma concept)Sepia, ochre, antique gold, marble creamFintech, payments, wealth, legal, real estate, luxury, hospitality
Cool / "Contra"contralabs.com (built in Framer)Deep teal + mint with saturated reds/golds in the paintingsAI, research, creative tools, dev tools, agencies, education

How to use this skill

Work through these steps in order. Each one has a detailed reference file.

  1. Brief. Collect the product, audience, 3–6 key messages and the CTA. Pick the variant (warm or cool) with the decision table in references/01-art-direction.md.
  2. Metaphors. Give every section exactly one literal visual metaphor that acts out its headline. Use the metaphor bank in references/02-metaphor-bank.md.
  3. Art. Source or generate the images, cut them out, grade them to one palette and apply the halftone / texture treatments. See references/03-imagery-and-prompts.md and references/04-techniques.md.
  4. Tokens. Apply the colour, type, spacing, radius and shadow tokens from references/05-design-tokens.md. Ready-made files are in assets/tokens.css and assets/tailwind.preset.js.
  5. Components. Build from the specs in references/06-components.md. React/Tailwind versions are in assets/components/.
  6. Page. Assemble one of the blueprints in references/07-page-blueprints.md (fintech, AI/SaaS, agency/portfolio, D2C/product).
  7. Motion. Follow references/08-motion.md: slow, weighty, scroll-led.
  8. Copy. Write in the voice from references/09-copywriting.md.
  9. Build. Use references/10-build-figma.md, references/11-build-framer.md or references/12-build-nextjs.md. examples/landing.html is a working single-file demo.
  10. QA. Run every item in references/13-qa-checklist.md before handing anything over.

If the user only wants a quick concept (moodboard, single hero, art brief), do steps 1–3 and show the result. Don't build the whole system.


The ten rules (memorise these)

  1. One metaphor per section, and it must be literal. Scales mean evaluation, a keystone coin means foundation, a key means access. If the image could swap with another section's image and still work, it is decoration. Replace it.
  2. Anachronism is the hook. Classical figures use modern objects calmly, as if they always had them. Never make it a joke: no sunglasses on statues and no memes.
  3. Loud art, quiet UI. All saturation lives in the imagery. The UI uses neutrals plus at most one accent.
  4. Never tint the UI to match a painting. Paintings change from section to section; the UI palette does not.
  5. Light serif, tight leading. Display serif at weight 300–400, line-height 1.0, tracking −0.03 to −0.05em. Never bold a headline.
  6. Grotesk for function, mono for labels. Body, buttons and nav use a neutral grotesk. Eyebrows and data use mono or tracked small caps.
  7. Space is the luxury signal. At most two ideas per viewport. Section padding is 120–200px on desktop.
  8. One grade for every image. Colour-grade every painting to the variant's palette so the collage reads as one world.
  9. Modern objects must look modern. Render tech crisply (dark UI) or as black-and-white halftone. Never paint it in the oil style. The contrast is the point.
  10. Legally clean art only. Use public-domain paintings or original generated images. Never lift images from the reference sites or from living artists.

Fast defaults (when the user gives no constraints)

  • Variant: cool for AI/SaaS/creative, warm for money/luxury/physical.
  • Fonts: Source Serif 4 (display), Inter (body/UI) and JetBrains Mono (labels). All are free on Google Fonts.
  • Hero: eyebrow // CATEGORY, a two-beat headline ending in a full stop, one-sentence sub, a dark pill CTA plus an outline pill, and one hero artwork.
  • Sections: Hero → logo strip → intro + product shot on a painting → 4 stacked feature cards → scroll story → stats → testimonial → closing CTA → dark footer.
  • Motion: 700ms, cubic-bezier(0.22, 1, 0.36, 1), fade-up 16px, sticky stacking cards and parallax thumbnails.

Anti-patterns (reject these)

  • Blue/purple gradients, glassmorphism, neon glows, 3D blobs and emoji icons
  • Bold or condensed serif headlines, or more than two typefaces plus a mono
  • Mixing the warm and cool variants on one site
  • Statues or paintings with no link to the copy ("classical vibe" filler)
  • Dense, multi-panel dashboard screenshots. Show one focused widget at a time.
  • Cartoonish AI art, plastic skin, or text and garbled letters inside generated images
  • Stock-photo people alongside the paintings
  • Fast, springy or bouncy animation

File map

SKILL.md                         ← you are here
references/
  01-art-direction.md            concept, variant decision, mood, art direction brief template
  02-metaphor-bank.md            80+ headline→image metaphors by industry
  03-imagery-and-prompts.md      sourcing, licensing, AI prompt system, grading recipes
  04-techniques.md               halftone, data-text texture, dot grid, cut-out collage, floating UI
  05-design-tokens.md            colour, type scale, spacing, radius, shadow, grid (measured values)
  06-components.md               every component with exact specs and states
  07-page-blueprints.md          4 full page blueprints, section by section
  08-motion.md                   timing, easing, scroll choreography, reduced motion
  09-copywriting.md              voice, headline formulas, label system, examples
  10-build-figma.md              Figma file setup, styles, layers, export
  11-build-framer.md             Framer setup, effects, scroll transforms, CMS, template packaging
  12-build-nextjs.md             Next.js + Tailwind + Framer Motion implementation
  13-qa-checklist.md             pre-ship checklist
assets/
  tokens.css                     CSS variables for both variants
  tailwind.preset.js             Tailwind preset
  halftone.css                   halftone + paper + data-texture utilities
  components/                    React + Tailwind components
examples/
  landing.html                   single-file demo page (no external images needed)

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Classical Collage Web Design AI skill do?

Use when designing or building a website, landing page, Framer template, pitch visual or brand system in the "classical painting × modern tech" art direction (Renaissance / neoclassical oil paintings and marble ruins combined with laptops, phones, coins and quiet product UI, as on the Aureon fintech page and contralabs.com). Covers art direction, metaphor selection, image sourcing and AI prompts, halftone and texture techniques, exact design tokens, components, page blueprints, motion, copy voice, and Figma / Framer / Next.js build steps.

Why use Classical Collage Web Design on TypingMind?

Because you install it once and use it with any model. Classical Collage Web Design is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Classical Collage Web Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/krutikkkkkkkkk/creative-ui/tree/main/registry/skills/classical-collage-web-design. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Classical Collage Web Design?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Classical Collage Web Design?

As many as you like. As long as a model supports skills, you can use Classical Collage Web Design with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Classical Collage Web Design AI skill free?

Yes. It is published on GitHub by krutikkkkkkkkk under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇