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

One continuous take of the speaker on top, a single brand-colour board below with every numbered step, a virtual camera walking the board to the step being named, three-word captions on the seam.

Presets

Red board list

The viewer always sees the whole list and where they are in it.

Use when
Tool tutorials, step lists, how-tos with a screenshot per step.

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: Red board list. The viewer always sees the whole list and where they are in it. How it works: One continuous take of the speaker on top, a single brand-colour board below with every numbered step, a virtual camera walking the board to the step being named, three-word captions on the seam. Right for: Tool tutorials, step lists, how-tos with a screenshot per step. What we learned from tested runs: - The speaker zone must stay one continuous take; a cut or reframe there is the listed failure. - Measured: the board changes 4.7 times per 10 seconds with a median hold of 1.44 seconds, the voice starts on frame 0 at 4.21 words per second, and there is no music. - Under 20 seconds there is no time to walk a board. 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
Length85.1 s
Aspect9:16
Visual changes per 10 s4.7
Median segment1.44 s
First visual change9.39 s
First spoken word0.0 s
Spoken words per second4.21
Loudness, integrated-14.7 LUFS
True peak-1.5 dBTP
Sound floor-52.6 dBFS (clean silences, no music)
Face in sampled frames100 percent, top third
Plays, saves148,200 plays, 11 percent saved (read 22 Oct 2026)
Against the account's median71.9 times

The recipe

  1. Stack the frame: the speaker on top at 29 percent of the height, a locked camera, one take; one board canvas below at 71 percent in a saturated brand colour.
  2. Build the board first as one large canvas: a title, a row of examples, every numbered step with its number in a hand-drawn circle, its title in marker lettering and its screenshot beside it.
  3. Frame 0 shows the whole board zoomed out with the title readable. The first word is on frame 0.
  4. Move the virtual camera to each step as it is named and hold until the next: 4 to 5.5 moves per 10 seconds, each hold 1.2 to 1.8 seconds.
  5. Draw a circle by hand around any button or field the speaker describes.
  6. Captions of three words (two to four), white heavy capitals on a tight black box, centred on the seam.
  7. No music and no sound effects. Voice at -14 LUFS, true peak at or under -1.5 dBTP.
  8. End by zooming back out to the full board on the closing line.

Not for

Emotional stories, testimonials, product beauty, anything under 20 seconds, a topic with no visual steps.

Related

Split the vertical frame: the speaker in the top 29 percent as one continuous take, a board in a saturated brand colour in the lower 71 percent, captions on the seam.

Speaker over a boardPrompt

One large board holds every step; a virtual camera pans and zooms to the step being named and holds there until the next one.

Camera move on one canvasPrompt

The first frame shows the entire board zoomed out, the title and all ten numbered steps, before the camera goes to step one.

The whole list as a map in frame 0Prompt

Captions of two or three words, white bold sans on a dark box, timed to the words.

Phrase captions on a chipPrompt

A red hand-drawn circle is drawn around the button as she names it, stroke by stroke.

Live markupPrompt

The frame split horizontally: the speaker in the top third as one continuous take, a board or screen recording below that changes on every point, captions on the seam.

Speaker over a boardPrompt

No message needed, the full list is in the caption, said while pointing down.

Everything is in the captionPrompt

Sources

Our own reading and measurement of a TikTok by @paytonkaleiwahea, posted 14 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.