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 presenter in one continuous shot on top, a hand-drawn whiteboard below that fills in stroke by stroke as the words are said, one numbered section at a time, two-word captions on the seam.

Presets

Presenter over a drawn board

Every point is drawn at the moment it is said, so the board stays readable as notes.

Use when
Explainers, frameworks, numbered ways or steps, course teasers.

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: Presenter over a drawn board. Every point is drawn at the moment it is said, so the board stays readable as notes. How it works: A presenter in one continuous shot on top, a hand-drawn whiteboard below that fills in stroke by stroke as the words are said, one numbered section at a time, two-word captions on the seam. Right for: Explainers, frameworks, numbered ways or steps, course teasers. What we learned from tested runs: - Never show a board section finished before its point is spoken. - Measured: 1.03 big changes per 10 seconds with a median of 9.22 seconds between them, because a section is drawn up gradually and only clears on the next number. - Under 45 seconds the drawing has no time to happen. 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
Length223.1 s
Aspect9:16
Visual changes per 10 s1.03
Median segment9.22 s
First visual change9.17 s
First spoken word0.0 s
Spoken words per second3.26
Loudness, integrated-14.2 LUFS
True peak-1.4 dBTP
Sound floor-79.8 dBFS (clean silences, no music)
Face in sampled framesthe presenter is a cartoon in every frame; the face detector counts 14 percent
Plays, saves40,900 plays, 6.5 percent saved (read 23 Oct 2026)
Against the account's median6.9 times

The recipe

  1. Stack the frame: the presenter on top at about 39 percent of the height, one continuous locked shot; a whiteboard canvas below at about 61 percent, hand-drawn style on white.
  2. Frame 0: the first board already drawn with the promise of the video in two or three shapes. The first word is on frame 0.
  3. For each numbered point: clear to a fresh area, write the number in a coloured circle and the heading, then draw each shape and word at the moment it is said, led by a labelled cursor. Type text letter by letter.
  4. A cleared section lands about once every 8 to 12 seconds, with small strokes all the time in between.
  5. End on a row of all the numbered circles as a recap, then the call to action.
  6. Captions of two words (one to three), white bold sans on a dark rounded box at the foot of the presenter zone, the spoken word in the accent colour.
  7. No music, no sound effects. Voice at -14 LUFS, true peak at or under -1.5 dBTP.

Not for

Emotional stories, testimonials, product beauty, luxury brands, anything under 45 seconds.

Related

Each shape and word on the whiteboard appears stroke by stroke at the moment it is spoken, led by a cursor that carries the presenter's name.

Drawn as it is saidPrompt

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

Captions of about three words in white, the term being defined in the brand accent colour at the moment it is said.

Coloured keyword in the captionPrompt

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

Sources

Our own reading and measurement of a TikTok by @pro.glitch, posted 18 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.