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.
Write a screen-recording walkthrough script for {outcome} in {app or workflow}. The format works when the viewer can follow every click at phone size, so each click gets a zoom and a label and the dead time between clicks is cut. Structure (45 s, 9:16 crop of a screen recording, or 16:9 for YouTube): - 0-3 s OUTCOME: the finished state on screen. Spoken: 'Here is how to get {outcome} in {N} clicks.' On-screen: '{N} clicks'. - 3-6 s START: the starting screen, full. One line on where we are. - 6-38 s CLICKS: {N} clicks (4 to 7). For each: zoom to 200% on the element 0.5 s before the click, hold 1 s after, cut the waiting. Spoken line per click, max 8 words, imperative. On-screen: the click number and the element name as typed in the app ('Export', 'Cut out'). If a value is typed, show it as text on screen. - 38-43 s OUTCOME AGAIN: the result, with one line on what to do with it. - 43-45 s CLOSE: 'Saved? Try it on your next one.' No download ask in a walkthrough; the app is on screen the whole time. Word budget: 75-85 words at 165 wpm; silence between clicks is fine, music under at low level. Return: the click list (element, what happens) so I can rehearse, then a table (time, screen state, zoom target, spoken line, on-screen label), then a one-line title for YouTube under 60 characters. Outcome: {outcome} App or workflow: {app or workflow} Clicks as I do them: {rough list}
In Claude Code, paste the prompt as a message, or run /video-promo which does this end to end.
Example
Outcome: a weekly meal plan exported as a shopping list. App: a recipe notes app.
Clicks: 1 open ‘This week’, 2 tap ‘+’ and pick 5 recipes, 3 tap ‘Shopping list’, 4 tap ‘Merge duplicates’, 5 tap ‘Share’ to the reminders app.
| Time | Screen | Zoom | Spoken line | Label |
|---|---|---|---|---|
| 0-3 s | Shopping list in reminders, 23 items | none | Five recipes to one shopping list in five taps. | 5 TAPS |
| 3-6 s | App home | none | Start on the home screen. | |
| 6-12 s | ‘This week’ tab | the tab | Open This week. | 1 · THIS WEEK |
| 12-20 s | Recipe picker, five selected | the ‘+’ then the picker | Tap plus, pick your five. | 2 · + ADD RECIPES |
| 20-26 s | Shopping list, 31 items | the button | Tap Shopping list. | 3 · SHOPPING LIST |
| 26-32 s | Same list, 23 items | the toggle | Merge duplicates. Three onions become one line. | 4 · MERGE DUPLICATES |
| 32-38 s | Share sheet | the share icon | Share to reminders. | 5 · SHARE |
| 38-43 s | Reminders app, 23 items, checkboxes | none | That’s the shop. Tick them off in the aisle. | |
| 43-45 s | Same | none | Saved? Try it on Sunday. |
YouTube title: 5 recipes to one shopping list in 5 taps
Tips
- Record at the device's native resolution and crop to 9:16 in the edit; a 16:9 recording squeezed into vertical is unreadable on a phone.
- Cut every pause longer than 0.5 s between clicks. Loading spinners are where viewers leave.
- In Claude Code, `/video-promo` assumes screen recording as the primary footage and writes the shot list; use this prompt for the per-click zoom plan it does not produce.
| 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 | screen-recording-walkthrough-format.md |
Related
'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.
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.
Comparison: two ways to do one thing, side by side, same task, same clock
The split-screen comparison that is fair enough to be believed: identical task, identical start, a visible timer, a verdict earned on screen. Prompt returns the script and the fairness checks.
'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.
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.
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.