Communitygithub.com

presenter-led-explainer

Plan and produce a presenter-led explainer video where a human talks to a Reveal.js deck while the browser records their face, voice and the slides. Use when the user wants to turn a topic or idea into an explainer video, write the script and slides for one, start a recording, or edit a recorded take.

What is presenter-led-explainer?

presenter-led-explainer is a Claude Code agent skill that plan and produce a presenter-led explainer video where a human talks to a Reveal.js deck while the browser records their face, voice and the slides. Use when the user wants to turn a topic or idea into an explainer video, write the script and slides for one, start a recording, or edit a recorded take.

Works with~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/CeezR/lagom-ai-presenter-led-explainer/tree/HEAD/skills/presenter-led-explainer

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Presenter-led explainer

The human is the presenter. Your job is everything around them: shape the idea, write a script they can read or listen to, build a deck they can talk to, get the recording running in the browser, and edit the take afterwards. You never synthesize their voice.

Workflow

  1. Discuss the idea. Settle three things with the user before writing anything: the question the video answers, the one core idea, and the audience. Keep the video to one idea. Ask only what you cannot decide yourself.
  2. Scaffold. From the user's project root run node <skill>/scripts/new.mjs <slug> [--title "..."] [--lang sv]. This creates videos/NNN-slug/ with script.md, deck.json, scenes/, runtime/ and takes/.
  3. Write script.md. One section per slide, in the language the user will speak. It is a listening script: the user reads or hears it to prepare, then talks freely on camera. They do not read it aloud. Short sentences, concrete examples.
  4. Build the deck. One slide = one entry in deck.json (id, title, 2-4 points) + one file scenes/<id>.html. Read reference/deck-format.md for the page contract and style/STYLE.md for the look. The points are the presenter's reminders: each arrow-key press reveals the next point, and the scene shows one handwritten caption per point. Run node <skill>/scripts/build.mjs after changing deck.json.
  5. Review with the user. Run node <skill>/scripts/open.mjs. The user steps through the deck (arrow keys, T = talking points). Iterate until they approve the script and the slides. Do not record before they approve.
  6. Record. node <skill>/scripts/record.mjs serves the deck on localhost and opens it in Chrome or Edge. In the page: F11 for full screen, R starts (3-2-1) and R stops, arrow keys step through the points, N opens the talking points in a separate window that is not recorded. The webcam appears as a bubble in the corner. Takes land in videos/NNN-slug/takes/. The user presents a few takes. Details: reference/recording.md.
  7. Edit. node <skill>/scripts/transcribe.mjs takes/<file> gives a transcript. Then follow reference/editing.md: pick the best take, cut mistakes and dead air, add chapters, write the title and description. Keep the original takes.

Rules

  • Recordings (*.mkv, *.mp4, audio) stay local and gitignored. Never commit them or upload them anywhere without asking.
  • Never ask for, print or store API keys. Nothing in this skill needs one.
  • Follow style/STYLE.md unless the user gives another direction. Hand-authored SVG only, no raster images in decks.
  • Keep each slide simple. If a scene needs more than a few objects and one motion, split the slide.
  • Do not commit or publish unless the user asks.

Related Skills