'I tried it for 7 days': a diary cut with one metric logged every day
The experiment-diary format that stays honest because one number is measured daily and shown on screen; the prompt plans the daily clip, the tally and a verdict that includes what did not work.
Write a '{N} days of {habit or tool}' diary script. The format works because the viewer is promised a verdict and gets a daily number along the way; a diary with no number is a vlog. Before writing, choose ONE metric I can measure every day in under a minute (minutes, count, grams, a score out of 10). Every daily clip shows the metric on screen. Structure (60 s, 9:16, cut from clips I film each day): - 0-4 s HOOK: 'I did {habit} every day for {N} days. Day {N} surprised me.' On-screen: 'DAY 1 of {N}' and the metric at zero or baseline. - 4-10 s WHY: the reason in two lines, present tense, and the rule I set myself. - 10-48 s DAYS: one clip per day, 5-6 s each, shot in a different place or light where possible. Each has: a day stamp top-left, the metric for that day under it, and one spoken line (max 12 words) that says one thing that happened, not how I feel. Days 3 and 5 should contain a dip or a problem; a straight line is not believed. - 48-56 s VERDICT: the metric on day 1 next to day {N}, on screen. Spoken: what changed, what did not, in two sentences. - 56-60 s CLOSE: 'Would you try it for a week?' If a product was the tool, it was in every clip; no download ask, the comments will ask. Word budget: 140-150 words at 165 wpm. On-screen: day stamp and metric on every clip, the two-number comparison at the verdict, nothing else. Return: the metric and how it is measured (one line), then a table (day, time range, where I film, spoken line, on-screen), then the verdict lines. Habit or tool: {habit or tool} N: {7} What I expect: {honest guess}
In Claude Code, paste the prompt as a message.
Example
Habit: 10 minutes of a language app every morning before the phone opens anything else. N: 7. Metric: words I can recall on a 20-word evening test.
Metric: a 20-word self-test each evening, score out of 20, written on a sticky note held to camera.
| Day | Time | Where | Spoken line | On-screen |
|---|---|---|---|---|
| 1 | 10-16 s | Kitchen, 7 a.m. | Day one. Ten minutes, then coffee. Evening test: six. | DAY 1 · 6/20 |
| 2 | 16-22 s | Bus | Day two, on the bus. Eight. | DAY 2 · 8/20 |
| 3 | 22-27 s | Bed, lights off | Day three, I skipped the morning and did it at midnight. Five. | DAY 3 · 5/20 |
| 4 | 27-33 s | Park bench | Back to mornings. Nine. | DAY 4 · 9/20 |
| 5 | 33-38 s | Office desk | Day five, I’m bored of the same unit. Nine again. | DAY 5 · 9/20 |
| 6 | 38-43 s | Kitchen | Switched to a new unit, it hurt. Eleven. | DAY 6 · 11/20 |
| 7 | 43-48 s | Café | Day seven. Thirteen out of twenty. | DAY 7 · 13/20 |
Verdict: ‘Six to thirteen in a week. The day I did it at midnight was the worst day, and the day I changed units was the best, so the time of day mattered more than the app did. Would you try it for a week?’ On-screen: 6/20 → 13/20.
Tips
- Film every day even on the day you fail. The failed day is the one that makes the verdict believable.
- Life2Film can pull the best 5 seconds from each day's clip by frame score, which is the whole edit for this format; you only write the lines.
- Keep N at 7. A 30-day version is a series of four 7-day videos, each with its own verdict.
| 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. · Life2Film: The montage app: analysis, segment scoring and cuts on your device. |
| 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 | i-tried-it-for-seven-days-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.
Build in public: a 45-second behind-the-scenes cut around one decision
The founder diary format that earns trust because it shows the decision, not the launch: the prompt structures a week of real screen and desk footage around one choice and one measured result.
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.
Storytime with a twist: a 60-second told story with the turn at 40 seconds
The talking-to-camera story that holds because the opener promises a turn and the turn arrives late. The prompt plans the beats, the b-roll inserts and the one line of text per beat.
Myth vs fact: three beliefs checked in 35 seconds, each with a demonstration
The format where a common belief is stated, then tested on camera, then labelled. Works because the viewer picks a side in the first second; the prompt insists on a visible test per myth.
'Things I wish I knew': 5 lessons in 50 seconds, each with what it cost me
The advice format that gets saved because every lesson is attached to the mistake that taught it. The prompt orders the lessons by cost and plans one number on screen per lesson.