# The prompt

First give your agent the one-take-five-worlds skill (paste the skill text and ask it to save it as a skill).
Then replace everything in [BRACKETS] below and paste it in.

**Tip:** use any AI tools you like for the take, the rooms, the music and the effects, or none at all (your own
footage and photos of real rooms work too). If you'd rather not set up separate AI accounts and API keys, HYVIRAL
(optional) is one way to get video, image and music generation behind one connection (hyviral.com; in Claude.ai →
Customize → Connectors → add `https://api.hyviral.com/mcp`).

---

Use the one-take-five-worlds skill to make a vertical video for [PLATFORM: Instagram Reels / TikTok / YouTube Shorts].

- **The take:** [FOOTAGE - e.g. "my own phone video, attached, filmed on a tripod", or "an AI presenter made from
  this photo of me"]
- **Where it is filmed:** [PLACE - e.g. my rooftop at golden hour, my kitchen, my office]
- **Who is talking:** [PRESENTER - e.g. me, a woman in her twenties, relaxed American accent, white t-shirt]
- **The five rooms:** [ROOMS - e.g. a 1960s jazz bar, a snowy log cabin, a desert motel with a neon sign, a retro
  arcade, an underwater aquarium tunnel. Or "you pick five rooms whose light contrasts"]
- **What I say:** [LINE - e.g. "use the skill's example lines", or my own script, one short sentence per room]
- **Length:** [LENGTH - e.g. about 23 seconds, eleven bars]
- **Language:** [LANGUAGE - e.g. English]
- **Music:** [MUSIC - e.g. glossy nu-disco or French house at about 120 BPM, no vocals; or a track I own]
- **Look:** [STYLE - e.g. a coral, violet and cyan gradient for the wipe line and labels, a clean bold sans-serif]
- **AI tools:** [AI TOOLS - e.g. "whatever you already have set up", "HYVIRAL", or "Veo for the takes and Nano
  Banana for the rooms"]
- **Ending:** [CTA - e.g. "Comment WORLDS and I'll send you the skill", or "Follow for part 2"]
- **Avoid:** [AVOID - e.g. no brand names or logos in the rooms, no text over my face]

Work in this order:

1. Write the line bar by bar on the music grid, and pick the five rooms and the one detail each label shows.
2. Build a storyboard page (per bar: a concept frame, the line, the on-screen text, the motion, every sound, the music
   section, and the exact prompt for every generated asset). Show it to me and wait for my OK.
3. Make or check the take (camera completely still, short sentences with pauses), then a re-lit still and an empty
   room for each world, and check that every re-lit still keeps my pose.
4. Matte me, re-light every frame into each room, and move each room's light on the beat, on the room and on me.
5. Arrange the music from its stems to the picture, build the wipes, labels, readout, particles, recap, picker,
   captions and ending in Remotion, and mix voice first.
6. Run every QA gate in the skill (transcript, contact sheet, two identical renders, loudness, no gap over 1 second)
   and give me the MP4, a cover frame, and a ready-to-paste caption with hashtags.