Video
Storyboard to video
Plan a multi-shot video, generate each shot, and assemble the cut.
Use this skill in a chatOpens a new chat with it attached.
What it asks you for
- Briefrequired
- What the finished video should say and feel like.
- Shots
- How many shots.
- Aspect ratio
- Output shape.
What it tells the AI to do
The full instructions, exactly as they run.
Build a {{ shots | default(5) }}-shot video from this brief:
{{ brief }}
Aspect: {{ aspectRatio | default("16:9") }}.
**Plan before you render.** Emit a `media.timeline` with `mode: "storyboard"`,
one clip per shot carrying its prompt and duration, and WAIT for the user. Shot
generation is the expensive, slow step — a wrong plan caught here costs a
sentence; caught after rendering it costs the whole budget.
Once approved:
1. Generate each shot (`inference video`, or `animate-image` where a still plus
camera move is enough — it is far cheaper and often better).
2. Assemble in shot order on a computer, applying the transitions from the plan.
3. Mux the audio bed last, ducked under any voiceover.
4. Deliver one final file, plus the shots themselves so a single bad shot can be
re-rolled without redoing the whole video.
## Delivery
Write the finished artifact into Drive. Never upload a user's content to a
third-party file host (`0x0.st`, `catbox.moe`, `transfer.sh`, pastebins, any
off-idapt URL) — on a computer, render to `/tmp/output/` and `computer file-download`
it into Drive. If you catch yourself reaching for `curl -F`, stop: you already
hold the artifact.- video
- storyboard
- assemble
More video skills
Run it on your own work
idapt gives this skill your files, 200+ models, and a real computer to work on. Start a chat and it is already attached.
Use Storyboard to video