scroll-world

Files (6)

• SKILL.md
• index-template.html · references/
• knockout.py · references/
• pipeline.md · references/
• prompts.md · references/
• scrub-engine.js · references/

SKILL.md (first lines)

# scroll-world

Produces a landing page where **scroll drives a camera**: it dives from outside a scene
into its interior, then flies out and into the next scene, continuously, with no visible
cuts. The visuals are AI-generated — stills via Higgsfield (or Codex), the video chain
via **Monid by default** (pay-per-clip Seedance 2.0; Higgsfield credits as fallback) —
and the page just scrubs pre-rendered video by scroll position. This is the same technique behind Apple's scroll-through product
pages — the camera genuinely moves, scroll only drives time.

**What you generate:** N scene stills → N "dive-in" camera clips → N-1 "connector" clips
that join consecutive scenes seamlessly → a portable scrub engine that plays the whole
chain as one flight.

**The one rule that makes or breaks it:** seams must be *frame-identical*. Read
[The seamless chain](#step-5--the-seamless-chain-the-critical-part) before generating any
connector. Getting this wrong is the single most common failure and produces a visible
"pop" between scenes.

Do not assume a frontend framework. The scrub engine in `references/scrub-engine.js` is
self-contained vanilla JS (it builds its own DOM + injects its own CSS into a container
you give it), so it drops into plain HTML, Next.js, Vue, a Python-served page, anything.
The value of this skill is the Higgsfield pipeline, the prompts, and the seam method —
not the framework.

---

## Step 0 — Bootstrap

1. **Monid CLI — the default video-chain backend.** Check `monid --version`,
   `monid keys list` (active key) and `monid balance` — the chain is billed per
   clip in USD (Step 1.7 has the numbers; a 1080p N=6 chain ≈ $27). If the CLI is
   missing or the balance can't cover the chain, say so and fall back to
   rendering the chain on Higgsfield credits instead — same model, same
   pipeline, different biller (Step 4 → Monid backend).
2. **Higgsfield CLI — still required even on the Monid path**: it renders the
   scene stills (`gpt_image_2`) and is the home of the `kling3_0` NSFW fallback
   and the fallback chain. If `higgsfield` is not on `$PATH`, install per the
   `higgsfield-generate` skill. If `higgsfield workspace list` fails auth, ask the user
   to run `higgsfield auth login` (interactive OAuth — you cannot run it) and, if needed,
   `higgsfield workspace set <id>`. Confirm credits cover the stills (~N image
   gens) — plus `(2N-1)` video gens if the chain falls back here.
3. **ffmpeg / ffprobe** on `$PATH` (frame extraction + encoding).
4. **An image tool** for background knockout if you want floating scenes: PIL
   (`python3 -c "import PIL"`), or `cwebp`/`sips`. Optional — see Step 3.
5. **(Optional) Codex CLI** — if `codex` is on `$PATH` (≥ 0.125) and
   `codex login status` reports a ChatGPT login, the scene stills can be generated
   through Codex's built-in `image_gen` (the same gpt-image-2 model) billed to the
   user's ChatGPT subscription instead of Higgsfield credits — offer it at
   Step 1.7, command in Step 2. Absence just removes the option.
6. Caveats: macOS ships **bash 3.2** (no `declare -A`); don't use associative arrays in
   scripts. Higgsfield generations take **3–8 min each** — always run them detached
   (background) and poll, never a foreground blocking call. Reference-by-job-UUID is
   rejected by media flags — pass **local file paths** to `--image/--start-image/--end-image`.
   Video models differ in accepted params (e.g. Kling has no `--resolution`) and in whether
   they support start/end-image conditioning at all — before batching, confirm the chosen
   model's schema with `higgsfield model get <job_type>` and see the Step 4 model table.

---

## Step 1 — Interview the user

The **subject is the user's to state — ask it as an open question in plain prose**, never a
fabricated multiple-choice. A made-up list of industries biases them and reads as you
deciding their business for them; let them answer in their own words (their real business,
a client's, or any idea). Reserve structured multiple-choice (`AskUserQuestion` in Claude
Code; a plain either/or question elsewhere) for the genuinely
enumerable, lower-stakes choices below — art direction, camera style, and brand-kit
approach — and even
there, signal they can go their own way ("Other"). Ask only what you can't sensibly
default. Cover:

1. **Subject** (ask openly, not multiple-choice) — "What should this world be about? Your
   business, a client's, or any idea — a word or a sentence is fine." Capture the
   industry/product + a one-line pitch (e.g. "a bubble tea company, from leaf to last
   sip"), and a brand name if they have one; otherwise you'll propose one below.
2. **Brand kit** — offer three paths, pick one:
   - Import from a URL: `higgsfield marketing-studio brand-kits fetch --url <site> --wait`
     (pulls name, colours, tone). Then read it back with `brand-kits list --json`.
   - The user hands you palette + name + tone directly.
   - You propose a palette + name and let them approve.
   Capture **4–6 named hex values**, a display name, and a tone word or two.
3. **Art direction** — default is "soft matte low-poly **clay diorama**, isometric,
   tilt-shift miniature, warm light." Offer alternatives (flat papercraft, glossy toy,
   claymation, neon night). Whatever is chosen becomes the shared **style preamble**
   reused verbatim in every scene prompt (this is what makes the world cohesive).
4. **Camera style — ALWAYS ask; it's the film's personality, not a technical
   detail.** Ask by feel (`AskUserQuestion` in Claude Code; a plain question
   elsewhere) and record the answer as `CAMERA`. The options map to the Step 4
   architectures — Step 4 then *implements* the choice, it never re-decides it:
   - **"Fly through the world"** — the camera dives into each scene, pulls up and
     out, and hops across the miniature world to the next; angles change
     constantly, big expressive aerial moves (this is the flagship-demo look).
     → Architecture B. Recommend as the default for diorama/miniature art
     directions.
   - **"One continuous walkthrough"** — a single forward flight that glides
     through each scene straight into the next, never pulling back; expressive
     but always-forward moves per scene (camera grammar table). → Architecture A.
     Recommend as the default for grounded/photoreal art directions.
   - **"Locked isometric glide"** — the camera keeps one fixed angle for the whole
     film, Emons-style; the world slides past/toward it, no rotation, no reveals.
     → Architecture A + the locked-iso clause in every leg prompt (prompts.md).
   State the trade-off in one line each (B reverses direction at seams — charming
   in miniature, jarring in realism; locked-iso is the calmest and cheapest to
   re-roll; walkthrough sits between).
5. **The journey (sections)** — the ordered scenes the camera flies through. Propose a
   set derived from the subject's own value chain and let the user edit. 5–7 works well.
   Boba example: farms → pearl kitchen → flagship shop → delivery → community plaza →
   the hero product. Each section needs: a short subject description (what's IN the
   diorama), an eyebrow, a headline, one line of body, and 0–3 tag pills. The last
   section is usually the hero product + the CTA.
6. **Mobile version — ALWAYS ask this; never silently generate both.** Ask as a
   two-option choice (`AskUserQuestion` in Claude Code; a plain question elsewhere):
   *"Want a mobile-optimized version too? The mobile version is a second camera chain
   rendered natively in **9:16 portrait** — composed for phones, not a crop of the
   landscape film — which roughly doubles the Higgsfield credit spend (state the
   estimated number)."*
   Options: "Desktop only" / "Desktop + mobile (native 9:16 — ~2× credits)". The
   credit cost must be stated to the user, not just implied.
   What the answer gates:

From Kevin-Zhouu/OpenAtlas, MIT.

More from Kevin-Zhouu/OpenAtlas