'Watch me use it': a 30-second product demo with no pitch and one real task
The demo that converts because it is a task, not a feature tour: one thing the viewer wants done, done on camera, in real time where possible. The prompt forbids adjectives and plans the text.
Write a 'watch me use it' demo script for {product} doing {one task the viewer wants done}. The format works because the viewer judges the product by watching it do a thing they need, so the script contains no adjectives about the product, only what happens on screen. Rules: - One task, start to finish. Not three features. - Real time where it is under 15 s; a labelled speed-up ('4x') where it is longer. Never cut out the waiting silently. - Every spoken line describes an action or a result. Delete any line with 'easy', 'powerful', 'seamless', 'amazing'. Structure (30 s, 9:16, phone or screen recording with hands or a cursor visible): - 0-3 s: the task stated as the viewer would say it ('I need this photo on a white background by tonight'). On-screen: the task in 5 words. - 3-8 s: the starting state, held. What is wrong with it, one line. - 8-24 s: the task done. 3-4 actions, one spoken line each (max 10 words), on-screen label per action with the tap or key named. - 24-28 s: the result, held, full frame. One line on what it is now good for. - 28-30 s: one line. This is the ONE video in the series that carries the download ask, so say the name once and point to the link in bio. In the other videos of the series, leave this line out. Word budget: 60-70 words at 165 wpm. On-screen text: the task, one label per action, the result label. Nothing animated. Return: a table (time, what is on screen, spoken line, on-screen label), a list of the actual taps/clicks in order so I can rehearse it, and the caption (one line, the task, no hashtag spam). Product: {product} Task: {task} Actual steps in the product: {the clicks}
In Claude Code, paste the prompt as a message, or run /video-promo which does this end to end.
Example
Product: a notes app for students. Task: turn a photo of a whiteboard into typed, searchable notes.
| Time | On screen | Spoken line | Label |
|---|---|---|---|
| 0-3 s | Phone pointed at a whiteboard full of equations | Lecture’s over and this is all I’ve got. | WHITEBOARD TO NOTES |
| 3-8 s | The photo in the camera roll, glare across half of it | A photo. Half of it is glare and none of it is searchable. | |
| 8-12 s | Share sheet, tap the app | Share to the app. | TAP: SHARE |
| 12-17 s | Progress, then text appears in a note | It reads the board, glare and all. | 1x, REAL TIME |
| 17-21 s | Tap on an equation, it becomes editable | Tap any line to fix it. | TAP: EDIT |
| 21-24 s | Search bar, type ‘eigen’, the note appears | Searchable from now on. | SEARCH: eigen |
| 24-28 s | The typed note full screen, the photo as a thumbnail at the top | That’s the whole lecture, typed, with the photo kept. | |
| 28-30 s | App icon in the corner | It’s called {product}, link in bio. |
Taps: camera roll, share, app, wait, tap line, edit, back, search ‘eigen’. Caption: whiteboard photo to typed notes, from the share sheet.
Tips
- In Claude Code, `/video-promo` reads the PRD and writes the hook/problem/demo/CTA script; use this prompt when you want a single task instead of a tour.
- Shoot the task three times and use the take where something small went wrong and you fixed it on camera. That is the moment that reads as real.
- The creator-growth rule: the download ask lives in one video in several, not in every one. Pick which one before you shoot the series.
| 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 | watch-me-use-it-product-demo-format.md |
Related
Screen-recording walkthrough: 45 seconds, one outcome, zoom on every click
The faceless screen walkthrough that stays watchable because every click is zoomed and labelled and the outcome is shown first. The prompt returns the click list, the zoom plan and the voice-over.
Before/after: the 20-second reveal with the 'after' shown first
The before/after format with the twist that keeps it from being skipped: open on the finished result, then show how bad it was, then the change. The prompt returns a timed script and text plan.
'3 mistakes' in 40 seconds: the educational format that converts
Three mistakes the viewer is making right now, each with the fix shown in a shot, ranked so the last one is the one they did not know about. Prompt returns the script, text plan and shot list.
Tutorial in 30 seconds: result first, then the steps at reading speed
The compressed how-to that gets saved: the finished thing in frame 1, then 3-5 numbered steps each shown and captioned. The prompt budgets the words so the steps fit at 165 wpm.
Founder explainer: 'I built this because' in 40 seconds, to camera, one problem
The founder-to-camera format that converts because it names the specific moment the problem became unbearable, then shows the product once. The prompt bans origin-story clichés and budgets the words.
Countdown listicle: 5 items in 45 seconds, best one last, numbers on screen
The ranked list format, with the rule that makes it hold: each item gets shorter as the count drops and number one gets the longest shot. The prompt returns script, text plan and the caption list.