Log in
WorkflowBy HypernaturalVersion 4, updated

Website to claymation ad

hn/workflow-website-to-claymation-ad

Turn a company's website into a ~20 s claymation ad delivered at 16:9, 1:1 and 9:16: five stylized toy-world shots animated on H3 Max, a narrator and a music bed, then kinetic titles, a logo lockup, benefit chips, a proof stat and an end card in the company's own font, colours, logo and CTA button. Every fact comes from the site. A worked conceptual-ad treatment in clay: a five-beat script, one locked style still, native 9:16 redraws instead of crops, one test clip before the batch, the cut on the voice's word times, and the titles shown live before the render. About $5 of model spend. For outreach gift videos, agency demos and brand promos made from nothing but a URL; for a faceless explainer over the product's real screenshots, use workflow-product-explainer-video.

SKILL.md

The person gives you a company's website (or one product or community page). You deliver a ~20 s ad in a warm claymation toy world at 16:9, 1:1 and 9:16: five shots, a narrator, a music bed, and titles in the company's own brand ending on its own CTA button. One URL in, six files out (each aspect with and without titles), for about $5 of model spend.

This is a worked treatment of a conceptual product or brand film. Use it when a warm toy-world story in clay fits the brief; the steps below own this recipe's sequence. The shape, agreed before anything is spent: 20 s, five shots of about 4 s, one narrator, about 48 spoken words, no real people: a toy hero and metaphors carry the product. Rounds and deliverables follow the core skill.

Steps

  1. Brand and facts (guide-capture-a-brand, route A; guide-pull-product-highlights, website route).
  2. Script and shot list: the five-beat generated-world ad (llm-write-an-ad-script: pain with a number → the place → what you get → proof → the site's CTA), the pain line per llm-write-a-hook, one metaphor per beat and a recurring toy hero (llm-pick-a-visual-metaphor). Gate: the script, the five-line shot list and the price, before any spend.
  3. The look on shot 1 (style-claymation; guide-pick-a-stylized-look, Process): two takes of shot 1 at 16:9 in the clay line. Gate: the pick locks the look and the hero.
  4. The other four stills on edit from the locked still, the action in the middle third of every frame, a recurring prop given its earlier still as a reference. Gate: a review_choose per shot, all in the same turn.
  5. Vertical and square (guide-pace-a-short-for-social, Several aspects): each picked still redrawn as a native 9:16 (nano-banana-restage-for-new-aspect), the 1:1 a crop of the 16:9 shifted per shot. Gate: review_approve with the five redraws as items.
  6. Animate one, then the rest (h3-max-image-to-video, the clay video phrase, 768P, 4 s): one test shot, Gate: its motion; then the other nine (five 16:9, five 9:16) at once.
  7. Voice and bed, together: three narrators on the whole script (guide-voice-a-script, A narrator for a short), "upbeat, conversational, not salesy"; one bed planned on the five shots (elevenlabs-generate-music, Fit the bed to the cut). Gate: the voice and the bed, in the same turn.
  8. The base cut, per aspect (ffmpeg-cut-clips-to-a-voiceover: the bed ducked, the clips at about 0.18), then −16 LUFS (ffmpeg-normalize-loudness). This untitled cut is rev1.
  9. Titles (hn4a-compositor-brand-ad-titles), one spec per aspect: the hook stack on the pain line, the brand's lockup on its name, chips on what you get, the proof stat, an accent line on every other line, the end card with the site's CTA button. Gate: the live spec (hn4a-compositor, Live spec, then render), the three specs as items; then check the rendered frames at the logo and the end card.
  10. Deliver per the core skill: the untitled and the titled cut, three files each; for an outreach or gift video, the note that goes with it (llm-draft-a-gift-video-note).

Choices this workflow makes

  • Claymation, stylized, never photoreal, and no real people: a toy hero and metaphors carry the product, so nothing on screen claims to be the real team or app.
  • Three aspects from the first still: the action in the middle third, native 9:16 redraws (a 9:16 crop is 608 px wide; a redraw is about $0.07 a shot).
  • Designed titles, not captions (hn4a-compositor-brand-ad-titles, Rules that worked).

Dead ends

  • Karaoke captions: tried and dropped; they read as subtitles.
  • A laptop drew a real manufacturer's logo despite the prompt: the take without it was picked rather than editing it out.
  • A dropped connection on a parallel still: the file had usually landed. Look in the folder before re-running.
  • The VO overran the cut into the end card; ending the last title early left a gap. The title runs until the CTA word.

Worked example

Globex, a recipe-planning web app, from its homepage alone. 16:9 1920×1080, 1:1 1080×1080 and 9:16 1080×1920, 20 s, 24 fps. Brand: Brand Sans 400/600, a near-black background, one warm orange accent on links, a pill CTA "Start planning". One hero (a small clay cook) and a recurring tiny robot helper.

ShotBeatPictureRoute
1PainThe cook at a cluttered table, a tower of bookmarksnano banana 2.1, 2 takes; picked take locks the look
2The placeWorkshop doors swing open on a warm room2.1 edit from shot 1
3What you getGlowing recipe blocks snap into a weekly chain; the robot helps2.1 edit, robot still as a reference
4ProofThe cook serves a full table2.1 edit
5CTAThe cook and robot wave by the open doors2.1 edit; end card in the lower third

Each still redrawn as native 9:16; the 1:1 crop shifted on shots 3 and 5. Ten 4 s clips on H3 Max 768P after one test. Three voices auditioned on the whole script, 18.5–20 s each; the picked take used unedited. Note on the first titled pass: the karaoke captions read as subtitles, so they were replaced by designed titles.

Spend: stills about $1.25 (including the redraws), animation about $3.60, voice and music about $0.20: about $5. The cut, titles and renders were free.

Related workflows

FAQs

Turn a company's website into a ~20 s claymation ad delivered at 16:9, 1:1 and 9:16: five stylized toy-world shots animated on H3 Max, a narrator and a music bed, then kinetic titles, a logo lockup, benefit chips, a proof stat and an end card in the company's own font, colours, logo and CTA button. Every fact comes from the site. A worked conceptual-ad treatment in clay: a five-beat script, one locked style still, native 9:16 redraws instead of crops, one test clip before the batch, the cut on the voice's word times, and the titles shown live before the render. About $5 of model spend. For outreach gift videos, agency demos and brand promos made from nothing but a URL; for a faceless explainer over the product's real screenshots, use workflow-product-explainer-video.

Install Hypernatural Desktop, a free Mac app, and connect it to Claude Code, Codex or Claude Desktop. Then describe the video you want and your agent finds the workflow itself, or paste this page's link (https://hypernatural.ai/skill/hn/workflow-website-to-claymation-ad) and it installs hn/workflow-website-to-claymation-ad and follows it.

It runs Nano Banana 2.1, MiniMax H3 Max, ElevenLabs voice and ElevenLabs music. Hypernatural Desktop has every one of them built in, so there are no API keys to set up, though you can bring your own.

The workflow is free. You only pay for the AI generations it runs, and your agent shows you the price of every batch before it spends anything. Editing, captions and titles run on your Mac at no cost.

It calls 18 smaller skills for its steps, including Style claymation, Pick a stylized look and Capture a brand. Each one is listed on this page, and your agent loads them as the job needs them.

Yes. Ask your agent to adjust it for your job, or to save its own version. You can publish your version under your own handle so anyone can install it.

Go make something cool.

Install the app, open your agent, describe the video. That's the whole onboarding.

Sticker HypernaturalSticker BannerSticker TVBoy