Hook
A skill that turn any brand into a scrollable 3D world landing page - oso95/scroll-world
More breakout videos from this creator.
Scroll-world builds one of those Apple-style landing pages where the camera flies through a whole world as you scroll, no cuts, every scene flowing into the next. This skill generates the diorama scenes and camera flights with Higgsfield, renders each connector using the actual neighboring frames as its endpoints, so both sides of every seam are pixel-identical and the flight never breaks. Install Claude Code — as a plugin (recommended) /plugin marketplace add oso95/scroll-world /plugin install scroll-world@scroll-world Then just ask for a scroll-through world landing page, or invoke: /scroll-world What it does It leans on Higgsfield for the art: cohesive isometric diorama scenes (GPT Image 2) and the camera flights themselves (Seedance image-to-video), scrubbed by scroll position — the same technique behind Apple's scroll-through product pages. The camera genuinely moves; scroll only drives time. It's framework-agnostic: you get the Higgsfield pipeline, the prompt templates, and a portable vanilla-JS scrub engine that drops into plain HTML, Next.js, Vue, or a Python-served page — nothing assumes a stack. When invoked, the skill: 1. Interviews you — the subject/industry + pitch, a brand kit (import from a URL, hand it over, or have it proposed), art direction, and the ordered scenes the camera visits. 2. Generates the assets with Higgsfield — one still per scene, one "dive-in" camera clip per scene, and the connector clips that join consecutive scenes, generated from the actual rendered frames of their neighbours so every seam is frame-identical. 3. Wires it up — a config-driven scroll engine that plays the whole chain as one flight. What's in the skill skills/scroll-world/ SKILL.md references/ prompts.md pipeline.md scrub-engine.js index-template.html knockout.py the procedure + intake checklis copy-paste batc portable, confi a minimal stand background knoc Notes Asset generation costs Higgsfield credits (~N image gens + ~2N-1 video gens for N scenes) and takes a while — the skill runs generations in the background and polls. The generated .mp4 / .webp assets are produced per project; they're not shipped here.