Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
veithly avatar

Coollanding

  • 2 installs
  • 7 repo stars
  • Updated June 12, 2026
  • veithly/coollanding-skill

Compose a unique cinematic landing page by picking one of 8 style worlds and mixing 2-4 interaction mechanics, producing a different combination each time.

About

An anti-template landing-page skill that forces a distinct result each run by selecting a style world, composing mechanics, and inventing a signature interaction, with WebGL and asset-isolation tooling. A developer uses it to build reference-grade, immersive launch or portfolio sites.

  • 8 style worlds plus a mechanics library composed into a non-repeating combo
  • Reference-harvesting, WebGL/particle, and chroma-cutout asset scripts for parity

Coollanding by the numbers

  • 2 all-time installs (skills.sh)
  • Ranked #1,564 of 1,880 Design & UI/UX skills by installs in the Skillselion catalog
  • Data as of Jul 27, 2026 (Skillselion catalog sync)
npx skills add https://github.com/veithly/coollanding-skill --skill coollanding

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs2
repo stars7
Last updatedJune 12, 2026
Repositoryveithly/coollanding-skill

What it does

Compose a unique cinematic landing page by picking one of 8 style worlds and mixing 2-4 interaction mechanics, producing a different combination each time.

Files

SKILL.mdMarkdownGitHub ↗

CoolLanding

Premise

This skill does not produce one look. It produces a different look every time, by forcing the agent to:

1. Diagnose the brand, audience, and emotional target. 2. Pick one Style World from references/style-worlds.md (cinematic-dark, editorial-interference, ritual-craft, spatial-architecture, festival-kinetic, papercraft-tactile, luxury-alcove, generative-system). 3. Compose 2–4 Mechanics from references/mechanics-library.md that fit that world (not the same combo used last time). 4. Invent one Signature Mechanic that nobody else has — the one thing this brand owns. 5. Verify the result is unique, readable, and on-brand.

The output is never "the CoolLanding style". The output is a page only that brand could ship.

Read references/style-worlds.md, references/mechanics-library.md, references/composition-strategy.md, and references/anti-template-rules.md before composing. When the user asks for reference-grade parity or "as close as possible" animation, also read references/kinetic-parity.md (the entrance + pointer + scroll + local-state + renderer proof ladder). When you generate illustrations, also read references/asset-isolation.md and use the bundled asset scripts (scripts/asset_prompt.py, scripts/chroma_cut.py, scripts/preview_cutouts.py) for chroma-backdrop prompting, keying, autocrop, and halo review. When you build a WebGL/3D/particle hero, read references/webgl-animation.md (the GPU-particle + bloom + smooth-scroll recipe distilled from the reference sites' shipped code).

Workflow

1. Ground the brief

  • Read local repo instructions, AGENTS.md, README.md, nearby docs.
  • Inspect current stack, file structure, existing UI patterns.
  • If the user provides reference sites, capture real screenshots or DOM/style signals before designing.
  • If external libraries are needed, verify current official docs.

1.5 Harvest the reference websites before designing

When the user asks for reference-grade parity, do not design from memory. Build an evidence folder first.

  • Download what is publicly shipped: HTML, JS, CSS, visible images, screenshots, and bundle scans. In this repo the proven harvester is tools/research_refs.py, which writes research/refs/<site>/_page.html, _libs.json, _scan.json, _shaders.txt, screenshots, and saved bundles.
  • Scan bundles for rendering and choreography signals: THREE, WebGLRenderTarget, UnrealBloomPass, curlNoise, DataTexture, FBO, InstancedMesh, GLTFLoader, DRACO, Reflector, Lenis, ScrollTrigger, barba, Howler, AudioContext, Rive, Framer, and inline GLSL markers.
  • Probe behavior, not just files: screenshot at load, after pointer movement, after 5s, and after scroll. Record whether motion changes, scroll changes, canvas count, video count, fixed layers, font stack, and dominant layout grammar.
  • If a site blocks or serves no public assets (for example a gated luxury page), mark that as visual-only evidence; do not invent a tech stack.
  • Convert evidence into a mechanism inventory: hero anchor object, renderer, scroll clock, post-FX, typography scale, cursor behavior, asset strategy, and mobile fallback.
  • Use the inventory as source material only. Do not copy proprietary markup, minified code, branded copy, product objects, or trademarked visual signatures.

The implementation target is 90% perceived effect parity, not code parity. Judge against:

  • first-viewport impact and single anchor object,
  • actual render layer parity (WebGL/canvas/DOM/SVG as appropriate),
  • scroll and pointer cause/effect,
  • typography scale and crop behavior,
  • material/texture quality,
  • entrance ritual,
  • mobile fallback,
  • console cleanliness and nonblank canvas checks.

2. Diagnose the brand

Answer these out loud before touching code (use AskQuestion if any are unclear):

  • Product category: physical product, SaaS, event, portfolio, real estate, agency, service, manifesto, etc.
  • Brand archetype: heritage / challenger / playful / operational / luxury / artisan / system / studio.
  • Audience temperature: cold/skeptical, warm/curious, hot/converted, technical, mainstream.
  • Emotion target: awe, intrigue, joy, exclusivity, trust, energy, calm, momentum.
  • One-sentence promise: what the first viewport must communicate before the user scrolls.
  • Performance ceiling: heavy WebGL OK, or must stay lean?
  • Reference vibe: which 1–2 worlds from the catalog feel closest? (Do not pick more than 2.)

3. Pick exactly one Style World

From references/style-worlds.md, pick the lead world. The lead world controls color logic, type system, layout grammar, motion grammar, asset strategy, and the dominant feeling. You may borrow at most one minor accent from a second world, but the page must read as one world.

If two worlds tie, run the uniqueness check:

  • Which world has the agent used least recently in this codebase / chat?
  • Which world creates the strongest contrast with what competitors do?
  • Which world rewards the brand's one-sentence promise best?

Then commit. Do not blend three worlds into a "safe average".

4. Compose 2–4 Mechanics

From references/mechanics-library.md, pick 2–4 mechanics that amplify the world.

  • Worlds suggest a default mechanic shortlist — read them.
  • One mechanic must be the hero mechanic (carries the first viewport).
  • The others are supporting mechanics (used in 2nd / 3rd / footer sections).
  • Never copy the exact combination listed as a reference site's signature. Re-arrange. Re-time. Re-color.

5. Invent one Signature Mechanic

The page must have one thing no reference has. Examples:

  • A custom cursor that becomes the product's icon when hovered.
  • A scroll bar that is the product itself (e.g., a knife blade, a bracelet link).
  • A loader that types out the user's location/IP city.
  • A 3D hero where the camera follows the actual time of day at the user's locale.
  • A footer that prints a generated postcard the user can save.

Write the Signature Mechanic in one sentence before implementing.

6. Generate or create assets

  • Bitmap visuals: use image generation, copy final assets into the project, never leave them in the generator's output folder.
  • Isolate every illustration. A subject inside a visible rectangle, a halo, or a fake "transparency checkerboard" reads as a cheap template. Floating, shadowed, separated elements are what make reference sites feel premium.
  • Never matte a subject out of a busy scene (rembg/SAM on a full studio shot halos and eats into the subject — 误伤). Instead, generate the asset on a uniform high-contrast chroma backdrop, then key that one color out. Pick the backdrop hue to be absent from the subject (green by default; magenta/violet when the subject contains green or many bright colors). Follow references/asset-isolation.md for the backdrop table, prompt template, the color-distance + gated-despill keyer, and the CSS to present cutouts as floating objects.
  • Use scripts/asset_prompt.py to produce the image-generation prompt, scripts/chroma_cut.py to key and autocrop the generated source, and scripts/preview_cutouts.py to review the cutout over dark/cream/kraft backgrounds before placing it in the page.
  • 3D assets: use Blender exports (.glb), keep file size low (texture atlas, draco compression).
  • Avoid external stock unless the user explicitly allows them.
  • Prefer 1–3 strong assets over many weak decorations.

7. Build the first screen as the experience

  • Make the first viewport the actual product/brand signal, not a marketing preamble.
  • Full-bleed or unframed layouts; do not put the hero inside a decorative card.
  • Let a hint of the next section appear on common desktop and mobile viewports.
  • Keep nav and CTAs usable even when the visual layer is intense.

8. Implement kinetic systems

  • Use CSS variables for color, spacing, type scale, motion timings — switching worlds should be possible by swapping a data-world attribute and a variable bundle.
  • For reference-grade work, install a kinetic director before polishing visuals: one scoped loop that writes normalized pointer, local scroll, chapter, and entry values into each world. Follow references/kinetic-parity.md; a static lookalike is not enough.
  • Add canvas/WebGL/procedural layer only when the world demands it. If you add one, it must carry data via uniforms (mouse, scroll, time, pulse).
  • A flat full-screen fragment-shader gradient is not a hero. The reference sites get their "wow" from a known recipe: GPU particles (curl-noise FBO ping-pong) → HDR multi-pass bloom → filmic composite, clocked by Lenis smooth scroll driving GSAP/camera, with motion made frame-rate-independent, rendered off the main thread where possible, and gated by a feature-detect → fallback. Implement from references/webgl-animation.md (verified stacks + real GLSL) and the gpgpu-curl-particles / hdr-bloom-postfx / offscreen-worker-render mechanics.
  • Custom cursor, magnetic buttons, parallax, scroll progress, ticker text, hover distortion: each must have a purpose tied to the world's grammar.
  • Respect prefers-reduced-motion; always cap DPR and pause the loop when offscreen.

9. Verify visually

  • Run the app in a browser.
  • Capture desktop and mobile screenshots for every section.
  • Check that generated images load, canvas pixels are nonblank, text does not overlap, buttons fit, scrolling works, no console errors.
  • For isolated assets, composite each cutout over its real world background (dark/cream/kraft) and render in real headless Chromium — the IDE preview caches images and hides fringes. Target ≥90% of the reference's separation quality. See references/asset-isolation.md §5.
  • Inspect the output yourself before claiming success.
  • Run the anti-template audit in references/anti-template-rules.md.
  • If the brief compared the page to reference sites, run a motion proof: screenshot before/after pointer, before/after scroll, active-state DOM assertions, nonblank canvas checks, and console capture. In the CoolFE demo this is python tools/verify_motion.py; in other repos, build the same checks locally. Do not claim "reference-grade" from static screenshots alone.

Reference Sites the Skill Was Trained On

The catalog is informed by these eight reference sites. The agent must not copy any of them — only inherit their mechanisms.

#SiteWorldSignature mechanism
1Sidewavecinematic-darkWebGL2 black void, single luminous origin, loading ritual
2Active Theorycinematic-darkSparse DOM, ASCII/data texture, runtime asset stage
3Blit Studioeditorial-interferenceHuge cropped wordmark, white field, custom cursor, media collisions
4Remote Ritualsritual-craftSaturated panels, sticker UI, calendar/desktop metaphors
5AIR Centerspatial-architecture2D↔3D↔2D RenderTarget transitions, water reflector, panoramic glass
6Razorpay Sprint 26festival-kinetic100+ scroll/click triggers, chapter index (01/A…), B2B-as-consumer storytelling
7Aimee's Papercraftpapercraft-tactileCharacter-led scrollytelling, baked 2D illustrations on 3D geometry
8Cartier Watches & Wondersluxury-alcoveSix dreamlike 3D rooms per product, hidden gestures, Web Audio score

Each row maps to a chapter in references/style-worlds.md and a tested mechanism in references/mechanics-library.md. Their real, verified front-end stacks (captured by downloading and scanning the shipped bundles) are tabulated in references/webgl-animation.md §1 — e.g. Sidewave is a Unity→WebGL export, Blit Studio runs Three.js + Lenis + Howler, Active Theory uses GPGPU curl-noise particles + UnrealBloom in an OffscreenCanvas worker, and Remote Rituals is no-code Framer with zero custom WebGL. Inherit mechanisms, not markup.

Quality Bar

  • Every visual asset must have a job.
  • Motion must clarify state, depth, or rhythm — never decoration alone.
  • The page must remain readable at mobile widths.
  • Avoid generic AI aesthetics: stock gradients, vague glassmorphism, repeated rounded cards, filler badges, decorative purple/blue blobs.
  • Report generated asset paths, implementation files, and verification commands.
  • The result must pass the uniqueness test: a critic should not be able to say "this is the CoolLanding skill output". They should say "this is the brand".

Related skills

Design & UI/UXuibranding

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.