Shot list generator: a table with shot, duration, visual, audio and overlay
An agent prompt that turns any script into a numbered shot table a camera operator or a video model can follow: one visual, one audio line and one text overlay per row, durations that add up.
Turn the script below into a shot list. Output a markdown table with these columns, in this order: Shot | Duration (s) | Visual | Audio | Text overlay. Rules: - One row per shot. A shot is one camera position or one screen state; a new screen or a new angle is a new row. - Duration is a whole number of seconds. The column must sum to {total length in seconds}. - Visual: shot size (wide / medium / close-up / screen recording of {app}) plus one action, in under 15 words. - Audio: the exact words spoken over this shot, or 'music only', or 'natural sound'. Every sentence of the script must appear in exactly one row. - Text overlay: max 6 words, or 'none'. Never repeat the audio word for word; the overlay carries the number or the name, the audio carries the sentence. - Mark the hook row and the CTA row in the Shot column (H and CTA). After the table, list what needs to be recorded or generated, one line per asset, with the shot numbers it serves. Script: {paste script}
In Claude Code, paste the prompt as a message, or run /video-promo which does this end to end.
Steps
- Paste the script with its timings. Without a total length the durations drift upward.
- Check that the duration column sums to the target before recording anything; agents round up.
- Save the table beside the clips as shots.md; it is the edit decision list when you assemble.
Example
| Shot | Duration (s) | Visual | Audio | Text overlay |
|---|---|---|---|---|
| H | 3 | Close-up, phone screen scrolling a camera roll fast | “Hours of video. Zero films.” | none |
| 2 | 7 | Screen recording: dragging a folder in, a progress bar | “You shot it. Then it sat there.” | 1,400 clips |
| 3 | 5 | Screen recording: the scene list appears, thumbnails fill in | “It finds the thirty seconds worth watching.” | On device |
Tips
- Ask for the overlay column even when you plan no text. It forces one idea per shot, which is what makes a cut feel fast.
- For generated video, feed each Visual cell into the 7-part prompt structure; the table is already one beat per shot.
| works with | Claude Code: Runs as a skill or a prompt in the terminal; can read your files and write the result. · Claude: Paste into claude.ai or the Claude app. · ChatGPT: Paste into ChatGPT; works with any GPT model. · Any LLM: Model-agnostic: Gemini, Mistral, a local model. |
| skill | npx skills add fortunto2/solo-factory/video-promo · source |
| cost | Free. No API, no key. |
| status | Unverified: written from the technique, not yet run end to end by us. |
| license | CC BY 4.0 for the text here; skills are MIT. |
| updated | 2026-11-01 |
| for agents | shot-list-table-generator-prompt.md |
Related
The 30-45 second promo script: hook, problem, demo, CTA with timings
A fill-in script template for a vertical product promo: four blocks with second counts and a 75-100 word narration budget, so the video ends before the viewer scrolls.
The 7-part prompt structure for text-to-video
A fill-in template that gives any video model the seven things it needs: subject, action, setting, camera, light, style and sound. Fewer vague words, fewer wasted generations.
B-roll shot list from a transcript: the table to film or generate from
An agent prompt that reads a transcript and returns a shot table (timestamp, line, shot, source: have / film / generate) for a camera or a video model, grouped so each location is filmed once.
Forced reasoning before scripting: goal, hook type, demo moments, emotion arc
Four questions an agent must answer in writing before it writes a line of script. Skips the generic promo every model produces when asked for one directly.
Ask an agent to turn a script into a numbered generation shot list
A prompt for Claude or ChatGPT that converts a 30-second script into 6-8 shot prompts in the 7-part structure, ready to paste into a video model one by one.
Write the cut as a script, not a timeline: the JSON storyboard prompt
An agent prompt that writes the edit of real footage as a small JSON file: which sentences, which cover shots, what the cold open is. A complaint becomes a one-line edit, and the render repeats.