Who it is forA teacher, writer, or developer who needs a short explainer video on a concept and has Claude Code set up.
The problemMaking an animated explainer by hand in an editor takes hours of frame-by-frame work and specialist tools.
The outcomeA finished MP4 of the explainer in one of the built-in styles, with story, look, and storyboard approved along the way.
What you need first
- Claude Code
- Node 18+
- Playwright with Chromium
- ffmpeg on your PATH
- Python with faster-whisper and the ElevenLabs connector (only for voice-overs)
Steps
- Install the prerequisites:
npm i -g playwright && npx playwright install chromium - Install the skill as a plugin:
/plugin marketplace add cth9191/animatethen/plugin install animate@animate - Start the skill with a prompt:
/animate how a hash map works, in the math style - Approve the story check (the format and numbered beat table), then the look check (2 to 4 style frames), then the storyboard (thumbs up or down by panel number).
- Review the delivered video and its measured checks, and send notes for a revision run if needed.
Prompt for your agent
Using the animate skill in cth9191/animate, make a 45-second explainer video about <topic> in the math style. Expect a finished MP4 in pieces/<piece-name>/ after the story, look, and storyboard approvals, and verify that the review step reports no cut-off or overlapping text.
Caveat. The skill needs Claude Code plus Node, Playwright, and ffmpeg installed locally, so it is a developer setup rather than a copy-and-paste tool.
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page