# The prompt

First give your agent the on-air 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, music and sound effects; the skill works the same with all of them, or with none
(every scene is code, and the film works with no voice). If you'd rather not set up separate AI accounts and API keys, HYVIRAL
(optional) is one way to get them behind one connection (hyviral.com; in Claude.ai → Customize → Connectors → add
`https://api.hyviral.com/mcp`).

---

Use the on-air skill to make a vertical video for [PLATFORM: Instagram Reels / TikTok / YouTube Shorts].

- **What keeps them up:** [TOPIC - the hour and the worry, e.g. "overthinking at 3 a.m.", "Sunday night dread", "the night before a launch"]
- **The callers:** [CALLERS - three small, specific worries and the short answer to each, or "you write them"]
- **What they need to hear:** [MESSAGE - the one true thing the last caller needs, e.g. "nothing you decide at 3 a.m. is a real decision", or "you write it"]
- **In the window:** [WINDOW - "no person: a night city and one lit room, drawn in code", or "my own clip, attached"]
- **Length:** [LENGTH - e.g. about 35 seconds]
- **Voice:** [VOICE - e.g. "a warm late-night radio host", "my own voice", or "no voice: captions and sound only"]
- **Music:** [MUSIC - e.g. "the skill's late-night radio brief", or your own idea]
- **Ending:** [CTA - organic: "Comment KEYWORD and I'll send you THE THING", with the keyword and what you'll send; or sponsored: the line and the URL]
- **AI tools:** [AI TOOLS - e.g. "whatever you already have set up", "HYVIRAL", or "none: animation only, I'll record the voice myself"]
- **Avoid:** [AVOID - e.g. no real stations, no real people as callers, nothing that sounds like medical advice]

Work in this order:

1. Write the script on the skill's moves, with one line for each turn and what happens in the studio. Start from the message, then pick the callers it answers.
2. Build the plan, the clock and the frame, render a silent animatic, and show me the script, the scene sheet and the animatic. Wait for my OK.
3. Generate the voice, music and sound effects 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. Place a sound on every change, fit the music to the turn, mix voice first, render, and run every QA gate in the skill.
5. Give me the MP4, a cover frame and a ready-to-paste caption.