AI Video Effect · Long form
Split-Screen Lesson
A lesson recording with the notes beside the speaker. The notes document on the left scrolls in sync with the speech: headings, bullets, checkboxes, callouts and tables highlight as they are spoken. The speaker sits on the right. You give Claude Code your video; it plans the edit, renders it on your computer and exports a finished 1920×1080 MP4.
# Split-Screen Lesson — video style
A lesson recording with the notes beside the speaker. The notes document on the left scrolls in sync with the speech: headings, bullets, checkboxes, callouts and tables highlight as they are spoken. The speaker sits on the right.Every paid plan opens all 18 styles.
How it works.
- 01
Add your video
Put
lesson.mp4in a folder, with the extras next to it, and open that folder in Claude Code. - 02
Make a Split-Screen Lesson from lesson.mp4. My notes are in notes.md.Type the prompt
Paste it into Claude Code and press Enter. Claude writes a short plan first.
- 03
Get your edit
Claude edits it, checks it frame by frame and saves the finished MP4 in the Export folder.
First time? Unzip the skill into .claude/skills/ and type “Set up the Split-Screen Lesson skill.” once.
Questions
What do I need to use Split-Screen Lesson?
Claude Code (the desktop app's Code tab or the terminal), a Mac or Linux computer with Python 3.9+ and ffmpeg, and about 3 GB of free disk space for the speech and vision models, which download once. Then: your talking-head video. Horizontal 16:9 is ideal; a vertical recording also works.
What does Split-Screen Lesson export?
1920×1080 (16:9), source frame rate (24, 25 or 30 fps), H.264 + AAC, ready for YouTube.
Can I change the colours and fonts?
Yes. They live in the skill's brand settings. Tell Claude your colours and font, for example "Use my brand: #0E1A2B background, #F4EFE6 text, Gilroy font", and it updates them. The default fonts are free (SIL Open Font License).
Is my video uploaded anywhere?
No. Everything runs on your computer, and your video and voice are never uploaded. The only downloads happen during setup: Python packages, two MediaPipe models from Google, the Whisper speech model and the free fonts.
Can I use a vertical recording?
Yes. Horizontal 16:9 is ideal, but a vertical recording also works: the skill has a fallback layout for it.
What happens when I correct something?
Claude adds your correction to the skill as a rule, so the same thing does not happen in your next edit.
What should I prepare?
Your talking-head video. Horizontal 16:9 is ideal; a vertical recording also works. Optional: screenshots, photos, logos and B-roll that support what you say. Optional: your notes as a Markdown or text file. Without them, Claude drafts the document from the transcript and shows it to you first.
What does Split-Screen Lesson not do?
Without your notes, Claude drafts the document from the transcript; read it before the render. It runs on macOS or Linux with Python 3.9+ and ffmpeg, not on Windows. Sound effects are not included. Add your own licensed samples, or it uses clean built-in sounds.