Doodle Intro
Film a NEW title-sequence style reel starring a character the user already has
doodles of. The references define who the character IS — hair, face, colours,
outfit — not the composition of the shot.
This skill is an anime opening style, never an anime character or a real
show’s opening. You film the user’s own doodle character with the craft of a
title sequence — kinetic cuts, a colour-script mood, a key-visual ending pose.
Do not turn it into, or reference, any named character, series, studio or actual
opening.
When this is the right skill
Pick this when the user wants that “opening titles” feel:
- “make it feel like an anime opening / intro”
- “a montage of my character that ends on a cool pose”
- “quick cuts that settle on a key-visual pose”
Choose doodle-daydream when they want one calm loop of the exact drawing,
doodle-dash when they want a single high-energy action shot, and
doodle-reel when they want a plain new scene with no title-sequence styling.
What to film
- A short montage feel: two or three quick beats — an expression, a small
gesture, a turn — with kinetic timing, then a clear settle. Keep it legible;
this is a montage feel, not a slideshow of unrelated shots.
- A colour-script mood that carries the whole reel — a golden-hour rim light, a
twilight gradient behind the character, a single accent colour — layered as
flat cel tints, never as realistic lighting.
- A strong final key-visual pose: the character squares up to the viewer and
holds, lit like the poster frame, landing on the beat of the sound.
- Cel-shaded flat colour with hard-edged shadow shapes throughout, so every cut
reads as hand-drawn.
- Staging that survives a phone screen: full body or waist up, generous empty
space, simple flat backgrounds so the character stays the subject.
How to run it
- Gather the reference URLs. Best case is several doodles of the same character
from this conversation; one is enough. Put the clearest full view first —
references are cited in order.
- Call
generateVideo with skill: "intro", those URLs as referenceUrls, and
the user’s mood or ending pose in description. If they named a length, pass
seconds — otherwise it lasts 5 seconds at 1 credit per second.
- If the user has no doodle of the character yet, make one first with an image
skill, show it, then offer the intro reel.
- The tool returns
status: "queued" with a jobId: it is coming to life. Say
it will land here on its own in a few seconds and that it has sound, then
stop.
What not to do
- Do NOT name or depict a character, series, studio, artist or a real anime
opening. This is a style (“title sequence”, “key visual”, “colour script”),
not a cast.
- Do NOT try to cram a whole story in — two or three legible beats and a strong
ending pose beat a blur of cuts.
- Do NOT send more than ten references — the extras are dropped, and the first
ones shape the character anyway.
- Do NOT re-call the tool for the same request, or call it to check progress.
The finished result is delivered on its own.
- Do NOT describe or evaluate the result. You have not seen it.
- Do NOT film a real, named person. This skill is for the user’s own doodle
characters.
