Director Chair
All groups

Camera

Shot sizes 13Angles 13Camera moves 42Rigs 6Lenses 9Focus and depth 4

Frame

Composition 13Aspect ratios 6

Light and look

Light 11Time of day 4Colour looks 13Film stock and texture 9Art styles 6

People and places

Characters 5Expressions 31Settings 3

Motion

Subject motion and speed 8

Edit

Transitions 21Edit effects 41Sound 14

Story

Hooks 46Script arcs 10Video formats 11Calls to action 5Test and publish 16

Recipes

Presets 28Prompt guides 11

Tools

BoardModelsGuidesAboutAgent skill

A handheld selfie at arm's length in the room as it is, a POV title on top, one-to-three-word captions on the chest, and every claim arriving with a receipt in the platform's own interface.

Presets

Selfie with receipts

Nothing looks produced, so the proof on screen is believed.

Use when
Build-in-public updates, proof of a result, a comment-keyword call to action.

Prompt instructions

You are my video producer. Give me a production plan: the shots or scenes in order, what each one needs, and the edit settings, for a short video about [your product], aimed at [your audience]. Technique: Selfie with receipts. Nothing looks produced, so the proof on screen is believed. How it works: A handheld selfie at arm's length in the room as it is, a POV title on top, one-to-three-word captions on the chest, and every claim arriving with a receipt in the platform's own interface. Right for: Build-in-public updates, proof of a result, a comment-keyword call to action. What we learned from tested runs: - Every number on a receipt is real and readable at phone size, and lands on the word that claims it. - Measured: 2.57 visual changes per 10 seconds, median segment 2.93 seconds. - The reference runs hot at -10.3 LUFS; export at -14 with the true peak at or under -1 dBTP. Be concrete: numbers, seconds and settings, no theory. Ask me one question first if something you need is missing.

Paste it into Claude, ChatGPT or Gemini.

Watch out

Notes

Measured on the reference

WhatValue
Length31.2 s
Aspect9:16
Visual changes per 10 s2.57
Median segment2.93 s
First visual change2.93 s
First spoken word0.0 s
Spoken words per second3.0
Loudness, integrated-10.3 LUFS (hot)
True peak-1.0 dBTP
Sound floor-32.8 dBFS (room noise or a quiet bed)
Face in sampled frames69 percent, middle third
Plays, saves, comments173,000 plays, 2.6 percent saved, 1.4 percent commented (read 22 Oct 2026)
Against the account's median10.3 times

The recipe

  1. A full-frame handheld selfie at arm's length, the face at about half the height, the room as it is with its own light. The first word is on frame 0.
  2. A POV title in the platform's own text style in the top fifth for the first half.
  3. Captions of one to three words, white medium sans, sentence case, no box, centred on the chest.
  4. Two or three handheld cutaways of 2 to 7 seconds to the screen where the work happens.
  5. Receipts float in the top fifth, each on the word that claims it: a card of a real post with its counter climbing, a comment box typing the keyword, the message the keyword triggers.
  6. Close on a time-stamp card and the next step of the diary.

Not for

Corporate B2B, regulated sectors, a client's brand voice, any claim without real numbers.

Related

A card of the earlier post floats in the top fifth of the frame, its comment counter climbing as he says the number.

Receipts in the platform's own interfacePrompt

A two-line title that starts with POV in the platform's own text style, white with a black stroke, in the top fifth for the first half of the video.

POV title in the platform's stylePrompt Whip between two subjectsPrompt Phone selfiePrompt

Comment the word EDIT and I will send you the link, while a comment box on screen types the word.

Comment keywordPrompt

A phone at arm's length, the room as it is, text in the platform's own styles, and recreated platform interface as inserts: a comment, a message, a notification.

Handheld selfie in platform dressPrompt

A little more midtone contrast than for a big screen, colours natural not boosted, shadows with detail, whites not clipped.

Social contentPrompt

Sources

Our own reading and measurement of a TikTok by @mino.mp4, posted 15 Oct 2026. The clip is a third-party reference and is not shown; the words here are ours Source Checked 2026-11-13.

For agents: this card as markdown, as JSON.