scroll-world

https://github.com/user-attachments/assets/b08e641e-985b-4bd4-83ff-6750272d0c37

An agent skill — for Claude Code, Codex, and any SKILL.md-compatible agent — that builds an immersive, scroll-scrubbed "fly through the world" landing page for any industry or brand — the kind where, as you scroll, a camera flies from outside each scene into its interior, then flows on to the next scene with no cuts. One continuous connected flight through a little generated world (think the Emons logistics site, applied to whatever you want).

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.

Codex & other agents — via the skills CLI

Using Vercel's skills CLI, which installs into Codex, Claude Code, Cursor, and 20+ other agents:

npx skills add oso95/scroll-world            # pick your agent(s) when prompted
npx skills add oso95/scroll-world -a codex   # or target Codex directly

In Codex, invoke it with $scroll-world (or /skills to browse), or just ask for a scroll-through world landing page.

Manually (drop-in skill)

Copy the skill folder into your agent's skills directory:

git clone https://github.com/oso95/scroll-world
cp -R scroll-world/skills/scroll-world ~/.claude/skills/   # Claude Code
cp -R scroll-world/skills/scroll-world ~/.codex/skills/    # Codex

Requirements

• The Higgsfield CLI, authenticated (higgsfield auth login), with credits.
• ffmpeg / ffprobe for frame extraction and encoding.
• Python 3 with Pillow (for the mobile portrait canvases; also the optional transparent-scene knockout).
• The Codex CLI (optional) — if present, the scene stills can be generated through Codex's built-in image_gen (the same GPT Image model), billed to a ChatGPT subscription instead of Higgsfield credits.

What it does

It leans on Higgsfield for the art: cohesive isometric diorama scenes (GPT Image 2 — via Higgsfield, or the Codex CLI on a ChatGPT subscription) and the camera flights themselves (Seedance or Kling image-to-video — only models that can frame-lock a seam), 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, the ordered scenes the camera visits, whether you want the mobile version (a second chain rendered natively in 9:16 portrait — composed for phones, not a crop of the landscape film), and the budget — render tiers and stills source shown with estimated credit costs, approved before anything generates.
2. Generates the assets — 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. Mobile opt-in renders a parallel portrait chain the same way, frame-locked against its own 9:16 renders.
3. Wires it up — a config-driven scroll engine that plays the whole chain as one flight, serving the portrait clips and posters automatically on phones.

What's in the skill

skills/scroll-world/
├── SKILL.md                    the procedure + the seam rule + gotchas
└── references/
    ├── prompts.md              intake checklist + every Higgsfield prompt template
    ├── pipeline.md             copy-paste batch scripts (generate → frames → connectors → encode)
    ├── scrub-engine.js         portable, config-driven scrub engine (blob-seek, lazy load, seam crossfade)
    ├── index-template.html     a minimal standalone page that mounts the engine
    └── knockout.py             background knockout for floating scenes

Notes

• Asset generation costs Higgsfield credits (~N image gens + ~2N-1 video gens for N scenes; the mobile chain doubles the video gens) and takes a while — the skill runs generations in the background and polls. Per-generation pricing isn't exposed by the CLI, so the skill calibrates against your live balance and states the estimated total before spending.
• The generated .mp4/.webp assets are produced per project; they're not shipped here.

Star History

License

MIT — see LICENSE.