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.
Write a before/after script for {topic}. The format works because the gap between two states is the whole message; narration only labels what the eye already sees. Structure (20 s, 9:16): - 0-2 s AFTER FIRST: the finished result, full screen, no narration. On-screen text: the one number or word that describes the gap ('2 taps', '40 min to 4'). - 2-6 s BEFORE: the starting state, held for 4 s. One spoken line that names what was wrong, max 12 words. - 6-14 s THE CHANGE: 2-3 shots of the thing being done, 3 s each. One short line each, present tense. - 14-18 s AFTER AGAIN: the same framing as shot 1, held. Spoken line: what changed, with the number. - 18-20 s CLOSE: a question for the comments or nothing. No download ask; this format sells by the reveal, and the viewer who wants the thing will ask 'what app' in the comments. Answer there. Word budget: 40-50 words at 165 wpm. Match the before and after framing exactly: same angle, same distance, same light. Say so in the shot notes. Return: a table (time, shot, spoken line, on-screen text), then a 3-line shooting note on how to match the two framings. Topic details: {what the before state is, what the after state is, the number that describes the gap}
In Claude Code, paste the prompt as a message.
Example
Topic: a photo app that removes the background from a product photo.
| Time | Shot | Spoken line | On-screen text |
|---|---|---|---|
| 0-2 s | Finished listing photo of a ceramic mug on white, phone held in hand | (silence) | 2 TAPS |
| 2-6 s | Same mug on a cluttered kitchen counter, cables, a sponge | This is what my product photos looked like. | BEFORE |
| 6-9 s | Thumb opens the app, picks the photo | Open the photo. | |
| 9-12 s | Tap on ‘cut out’, background drops away | One tap. Background is gone. | |
| 12-14 s | Tap on ‘white’, export | White, export. | |
| 14-18 s | The clean listing photo again, same hand, same angle | From this to this in two taps, on the phone, before the coffee got cold. | AFTER |
| 18-20 s | Hold on the result | What would you shoot first? |
Shooting note: shoot the ‘after’ shot at 0-2 s and the one at 14-18 s as one take, held in the same hand against the same wall. Shoot ‘before’ in the same spot with the clutter put back. Window light both times, no lamp.
Tips
- Hold the before shot longer than feels comfortable. Four seconds of the bad state is what makes the after land.
- If the number in the first frame is not real and measurable (taps, minutes, dollars), cut it and use a word instead.
| 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. |
| 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 | before-after-reveal-format.md |
Related
Day in the life: a 45-second cut from real footage with one through-line
A recipe for the vlog-style day that keeps working because the viewer waits for one promised payoff; the prompt turns your clip list into a timed script with text overlays.
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.
POV: a 15-second first-person scene with the text doing the storytelling
The POV format in which the camera is the viewer's eyes and one line of on-screen text sets the situation; the prompt writes the text, the single action and the beat where it turns.
Reaction / duet style: respond to a clip in 30 seconds without stealing it
The split-screen or picture-in-picture response format, written so the reaction adds a fact or a demonstration instead of a face. The prompt plans the pause points and what you say at each.
'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.