Communitygithub.com

diorama-promo-video

Make vertical 9:16 short-form promo videos (Instagram Reels, TikTok, YouTube Shorts) in the "miniature diorama" style — chunky clay block mascots on a tiny game-show stage, a taped paper headline banner, a scoreboard counter, word-by-word captions on torn paper scraps, film grain, and a "comment LINK" call to action — rendered with Remotion from a simple JSON script. Use this whenever the user wants a reel/short/TikTok/promo/explainer video for an AI tool, Claude skill, prompt, app, service, template or digital product, wants a video "like this one" / "seperti video ini", asks for a "comment LINK for the link" style video, or says things like "buatkan video reels", "bikin video promosi", "video konten untuk IG", or wants an existing video (explainer, edukasi, fun fact, history, tutorial) "restyled" / "diubah dengan gaya" this look, even if they don't mention Remotion or the diorama style.

What is diorama-promo-video?

diorama-promo-video is a Claude Code agent skill that make vertical 9:16 short-form promo videos (Instagram Reels, TikTok, YouTube Shorts) in the "miniature diorama" style — chunky clay block mascots on a tiny game-show stage, a taped paper headline banner, a scoreboard counter, word-by-word captions on torn paper scraps, film grain, and a "comment LINK" call to action — rendered with Remotion from a simple JSON script. Use this whenever the user wants a reel/short/TikTok/promo/explainer video for an AI tool, Claude skill, prompt, app, service, template or digital product, wants a video "like this one" / "seperti video ini", asks for a "comment LINK for the link" style video, or says things like "buatkan video reels", "bikin video promosi", "video konten untuk IG", or wants an existing video (explainer, edukasi, fun fact, history, tutorial) "restyled" / "diubah dengan gaya" this look, even if they don't mention Remotion or the diorama style.

Works with✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/uhandani/Skill-video-nocodealex/tree/HEAD/diorama-promo-video

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Diorama promo video

Produces a ~30–50 s vertical video (1080×1920, 30 fps) in the style of the viral "5 Claudes roast your LinkedIn" reel: a little stage with block characters acting out what a product does, scene by scene, while captions pop word by word. Everything is driven by one file, src/video.json, in a Remotion project built from assets/template/.

Read references/style-guide.md for why the format works (pacing, typography, narrative arc) and references/scene-types.md for every JSON field.

Workflow

1. Get the brief (ask only for what's missing)

  • What is promoted and the concrete things it does (outputs, numbers, steps).
  • CTA keyword people comment (default LINK) and whether it's free.
  • Language of voiceover/captions — match the user (Indonesian request → Indonesian script unless they say otherwise). Banners can stay English if the user prefers that "IG look".
  • Voiceover: do they have a recording? If not, the video still works with captions only; offer to write a script they can record, then sync it later (step 5).
  • The "prop" on the desk (profile, website, resume, store…) — sensible defaults exist.
  • Palette: monochrome grayscale is the default ("palette": "mono"). Use "warm" only if the user asks for color; individual tokens can be overridden in theme.

2. Write the script first, as a table

Follow the arc in the style guide: hook → mechanism → pain → outputs → transformation → payoff → proof → free → easy → CTA. 9–12 scenes, one sentence each, ~2.7 words/s so a scene lasts 2.5–4.5 s. For each scene choose a scene type that shows the sentence (a sentence about "five opinions" → lineup with five signs and an auto counter). Show the table (banner | voiceover | scene type) to the user and adjust before building — changing a table is cheap, re-rendering is not.

3. Build the project

bash <skill-dir>/scripts/new_video.sh <project-dir>      # copies template + npm install

Then write <project-dir>/src/video.json from the approved script. Start from the example already in that file (it recreates the reference reel) — keep its shape.

Practical limits that keep layouts clean: banner ≤ 30 characters, signs 1–2 words, card lines ≤ ~25 characters and ≤ 7 lines, list ≤ 4 items, ≤ 5 characters in hero.

4. Check it visually before the full render

node <skill-dir>/scripts/preview_sheet.mjs <project-dir>   # → out/sheet.jpg, one frame per scene

Look at the sheet (Read the image). Check: banner not clipped, captions don't cover the key prop, counters show the right numbers, nothing overflows the card. Fix video.json and re-run. This takes seconds; a full render takes minutes.

5. Voiceover sync (when there is audio)

Put the audio in <project-dir>/public/ and run:

pip install faster-whisper   # once, if missing
python3 <skill-dir>/scripts/word_timings.py <project-dir> voiceover.mp3 --lang id

This writes word timings into video.json (captions, voiceover); scene cuts then land exactly where each sentence starts. Background music: put it in public/ and set "music": "file.mp3" (volume 0.12 default). Without audio, timings are estimated from text.

6. Render and deliver

bash <skill-dir>/scripts/render.sh <project-dir> out/video.mp4

render.sh falls back to a local Chrome/Chromium when Remotion can't download its own browser (common in sandboxes). A 45 s video takes a few minutes. Deliver the MP4, and also write the post caption in the reference pattern: Comment "LINK" and I'll DM you the link to … Comment "LINK" for the link. #…

For live tweaking the user can run npx remotion studio inside the project.

Restyling an existing video

When the user gives a video and asks for it "in this style", keep their story and voice and replace only the visuals:

  1. bash <skill-dir>/scripts/caption_strips.sh <video> <work-dir> — extracts the audio (voiceover.m4a) and tiles the caption band every 0.5 s with timestamps, plus an overview.jpg. If whisper works, word_timings.py is faster; when it doesn't (no model download), read the strips: the highlighted word in each strip is the one being spoken at that timestamp, which gives word timings to ±0.25 s. Check the band position on a probe frame first — a wrong crop shows only slivers of text.
  2. Cut the transcript into beats where the original changes visuals or topic (the overview shows this). One beat = one scene, 3–8 s.
  3. Choose a scene type that shows each beat. Explainers lean on board (symbols, "A → B", crossing out wrong answers), timeline (dates, people), card (definitions, quotes, highlighted terms), before-after with rewrite:false + stamp ("MITOS", "FAKE"), spotlight (a person/the reveal), and cta for the closing comment prompt.
  4. Write video.json with "voiceover" and a "captions" array of {word,start,end} (absolute seconds, in order). Each scene's text must contain exactly that scene's words in order — scenes are timed from where their first word starts. A small Python script that holds start word|start word|… per scene and emits both is the least error-prone way. assets/examples/restyle_asal_usul_x.py is a complete worked example (a 90 s Indonesian explainer on why algebra uses x, 16 scenes) — copy its structure.
  5. Preview sheet → fix → render as usual. Banners can be in the video's language.

Customizing beyond JSON

  • Colors/cast: palette, theme and characters in video.json. In mono everything is forced to grayscale, so a custom theme color only matters for its lightness.
  • New visual beat: add a scene type (steps at the end of references/scene-types.md).
  • Animate only with useCurrentFrame() + interpolate/spring; CSS transitions/animations don't render in Remotion. Keep y 1440–1620 free for captions.

Originality

The template's mascots, set and props are generic and original. Keep it that way: don't copy another creator's characters, logos or footage into the video; real brand names may appear as text (e.g. "LinkedIn") when describing what the product works with.

Related Skills