whiteboard-teacher-video skill
A skill that turns a script into an explainer video: drawings are sketched by hand, text types out, no image generators needed.
- 546 ★ on the repository
- Last commit
Minimal access
Why this level
- The skill runs local scripts, downloads an engine and opens your browser for rendering.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/whiteboard-teacher-videoDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill runs local scripts, downloads an engine and opens your browser for rendering.
This is third-party code. Review the repository files before installing.
What it does
The `whiteboard-teacher-video` skill makes a whiteboard-style explainer video: drawings are traced in code stroke by stroke, text writes out letter by letter, all synced with a narrator voice. It offers five styles and renders in local Chrome or Edge without any image-generation API. The video is a pure function of time, `renderAt(t)`, so frames are reproducible, changing a line re-renders only affected segments in seconds, and scenes can embed numbers, charts, code and page screenshots. The engine is fetched by `scripts/setup.py` via sparse checkout, and voice-over uses `edge-tts`.
Who it is for. Teachers, channel authors and analysts who need to explain a topic with a short animation without costly AI video services.
Good fit when
- A two-minute clip explaining a theorem or financial statement is wanted.
- One line in a finished video must be fixed without a full re-render.
- The scene must show exact numbers or real charts.
- Money goes only to voice-over, not image generation.
Not a fit when
- A photorealistic clip is needed: images are drawn in code.
- There is no Chrome or Edge: rendering runs through them.
- The video would be uploaded to a platform without checking voice and asset licenses.
Example request
Make a two-minute whiteboard video: how GPS works, with a step-by-step satellite drawing and narration.Limitations
Resources are fetched during setup: the roughly sixteen megabyte engine downloads from GitHub, and `playwright-core` drives your browser without installing Chromium. Git is required for setup. Voice-over uses `edge-tts` by default, and the fallback `apiz-cli` may require payment. The repository metadata defines no license. Documentation is in Chinese and samples are posted on Bilibili. Voice quality and vocabulary depend on the chosen voice, so listen to technical terms before publishing.
How to disable. Delete the skill folder from the agent's skills directory and the downloaded engine that the setup script clones into the project directory.
FAQ
Is an image generation API needed?
No, drawings are produced in code; you pay only for voice-over if a paid voice is chosen.
Which styles are available?
Five styles to choose from.
Why are edits fast?
The video is a function of time, so only the affected segments re-render.
What is downloaded during setup?
The roughly sixteen megabyte engine via sparse checkout and `playwright-core` without Chromium.
Which browser is needed?
An installed Chrome or Edge; the skill does not download its own.
Discussion
No questions or reviews yet.
Related
SkillsA skill makes a video from a script where diagrams and captions are drawn stroke by stroke as the narrator speaks.
A Codex skill that renders images, SVGs and scripts as hand-drawn whiteboard videos, with 30 styles and narration
A skill that makes video in pure code: narrated explainers and website promos in 35 visual styles, in 16:9 and 9:16.
A skill for Khan Academy style explainer videos: a pen draws on a board while a voice speaks, one scene file renders to MP4
A skill that turns your narration and real assets into a 20–60 second video in the style you pick, rendered locally as MP4.
A skill that turns a script into a finished video with voice-over, subtitles, a cover and a publish text, frames drawn by code.
README in short
The README is in Chinese: the render-as-function-of-time principle, comparison with AI video tools, dependencies and installation.