# The prompt

First give your agent the motion-ad 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 voice, images, music and sound effects; the skill works the same with all
of them, or with none (every scene is code). If you'd rather not set up separate AI accounts and API keys, HYVIRAL is
one option: connect it once (hyviral.com; in Claude.ai → Customize → Connectors → add `https://api.hyviral.com/mcp`)
and your agent gets voice, image, video, music and sound generation in one place.

---

Use the motion-ad skill to make a motion ad for my product.

- **Product:** [NAME - your product's name]
- **What it does, in one sentence:** [WHAT - e.g. "turns one prompt into a finished product video"]
- **Who it's for:** [AUDIENCE - e.g. "solo founders who launch every month"]
- **Their biggest frustration today:** [PAIN - e.g. "launch videos take a week and still look amateur"]
- **Three things it does or proves:** [1] / [2] / [3]
- **Real proof I can show:** [PROOF - links or files of things it really made, or "show the product's own screens"]
- **Brand:** [BRAND - colors as hex codes, a logo file or "no logo", fonts if you have them]
- **Format:** [FORMAT - 9:16 for Reels and TikTok, 16:9 for YouTube and X, or both]
- **Length:** [LENGTH - e.g. 25, 45, 60 or 90 seconds]
- **Structure:** [STRUCTURE - Launch, Name-early, Before and after, Three reasons, Feature drop, or "you choose"]
- **Call to action:** [CTA - organic: "Comment KEYWORD and I'll send it to you" with the keyword; or sponsored: the line,
  the button text and the URL]
- **Narrator:** [VOICE - e.g. "a soft, close, almost-ASMR voice, unhurried", or "my own cloned voice"]
- **Music:** [MUSIC - e.g. "sleek minimal electronic, warm sub, soft plucks, a lift at the reveal"]
- **AI tools:** [AI TOOLS - e.g. "whatever you already have set up", "HYVIRAL", "ElevenLabs for the voice and sound
  effects", or "none: animation only, I'll record the voice myself"]
- **Avoid:** [AVOID - e.g. no faces, no competitor names, no claims I can't back up]

Work in this order:

1. Write the script on the structure above, short lines, one accent word per line, and a call to action that matches
   the mode I chose.
2. Pick the beats, lay out the clock from estimated timings, render a silent animatic in my format(s), and show me
   the script, the beat sheet and the animatic. Wait for my OK.
3. Generate the voice, music, sound effects and any images or clips with the AI tools I named above. If I left that
   open, tell me which tools you'll use and wait for my OK.
4. Build every beat as code, place a designed sound on every move, fit the music to the cuts, mix voice first, render,
   and run every QA gate in the skill (sheets with the safe box, two identical renders, loudness, transcript, no gaps or
   stills).
5. Give me the MP4s, a cover frame and a ready-to-paste caption.