October 4, 2026
html-explainer
A skill that has your AI coding agent turn a topic into a narrated explainer video with subtitles and covers, on your own computer.
- Ecosystem
- Agent Skills
- Skill category
- Education
- Creator / organization
- OneMoh
What it is
html-explainer is an open-source agent skill by GitHub user OneMoh. Give it a topic, such as "why is the sky blue," and your AI coding agent researches it, writes a narration script, generates the voiceover, builds the visuals as web-page animations timed to the speech, renders them frame by frame, and assembles an MP4. The finished video has word-aligned burned-in subtitles and a progress bar, plus landscape, portrait, and 3:4 covers and a quality-check report. The documentation mentions 23 built-in visual style templates, and the README lists Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, and other tools that follow the Agent Skills convention.
Who it's for:creators who make explainer or science videos. It produces animated explanations; the documentation says it is not meant for live-action editing or real-person narration.
Before you start: you need to know how to install a skill in your AI coding agent, and your computer needs Python 3.9 or later, Node.js 18 or later, Chrome or Edge, and ffmpeg. A setup script installs missing dependencies. Each video takes about 2 GB of disk space while rendering. The default voice engine is edge-tts, which the documentation describes as free with no API key, offering built-in Chinese and English voices. Volcano Engine TTS 2.0 is an option that needs your own API key and charges per character. The documentation is mainly in Simplified Chinese, with an English version. MIT license.
Based on the project's public documentation. Not tested by AI Inspiration World.