Who it is forA product manager, support lead or founder who must show a new user how to complete a task in the app.
The problemScreen recordings are slow to re-make after each UI change, and static screenshots do not explain the order of steps.
The outcomeA tutorial MP4 where arrows, circles and numbered steps are drawn over your screenshots while the voice explains each one.
What you need first
- macOS
- Node 20 or newer
- ffmpeg (install with brew install ffmpeg)
- Claude Code, since the repo installs as a Claude Code skill
Steps
- Complete the install steps:
brew install ffmpeg, thengit clone https://github.com/haiderfarooq3/khan-explainer ~/.claude/skills/khan-explainer, thencd ~/.claude/skills/khan-explainer/scripts && npm install && npx playwright install chromium. - Run the example to see the draw-over-UI mode:
cd ~/.claude/skills/khan-explainerandnode scripts/render.js examples/ui-tutorial.js tutorial.mp4. - Ask Claude Code: Draw over these screenshots and show a new user how to send their first invoice, and give it the screenshot files.
- Review the contact sheet path printed by the render to check that each arrow lands on the right element before you share the MP4.
Prompt for your agent
Using the khan-explainer skill, build a draw-over-UI tutorial from the screenshots in <screenshot folder> that shows a new user how to <task>. Expected output is a tutorial MP4 with arrows and numbered steps drawn over the screenshots. Verify with the contact sheet that every step points at the correct part of the screen.
Caveat. The README points to SKILL.md for the capture recipe for tutorials, so read that file before you prepare screenshots for a real product.
Get 5 new use cases every morning. Free, one short email, 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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