Video
Cut into shorts
Turn a long video into several vertical short clips with captions.
Use this skill in a chatOpens a new chat with it attached.
What it asks you for
- Videorequired
- The long video.
- How many clips
- Number of shorts to cut.
- Length
- Target seconds per clip.
What it tells the AI to do
The full instructions, exactly as they run.
Cut {{ count | default(3) }} vertical shorts of ~{{ seconds | default(45) }}s from {{ video }}.
Pick the moments from the TRANSCRIPT, not by slicing at fixed intervals. A short
works when it contains a complete thought with a hook in the first two seconds;
an arbitrary 45-second window almost never does.
1. `inference transcribe` the source.
2. Choose {{ count | default(3) }} self-contained moments. Show them as a
`media.timeline` (`mode: "edl"`) BEFORE rendering, so bad picks cost nothing.
3. For each: trim, reframe to 9:16 (keep the speaker in frame — centre-crop
decapitates people), burn captions, and export.
Deliver all clips into one Drive folder, named by their hook.
## 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
- shorts
- social
- vertical
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 Cut into shorts