GitHub radar
Explainer Video From Any Topic: Claude Code and Codex Skill
A skill for Claude Code and Codex that turns any topic into a narrated motion-graphics MP4 with voiceover, subtitles, and chapter markers — agents build every frame in code, no video editor required.
anything2explainer is a skill for Claude Code and Codex that generates complete narrated explainer videos from any topic. You install it once by linking the repository into your skills folder, state your topic, and the agent pipeline takes over: it researches the topic with sources, writes the narration, generates word-boundary-aligned TTS voiceover, creates a shot-by-shot storyboard, and dispatches parallel build agents that write each frame as a Remotion (React) component. The output is a 1280×720 H.264 MP4 with synchronized voiceover, subtitles, chapter cards, and a progress bar. A 2–3 minute video runs in approximately 1 hour of wall clock time; a 3–5 minute reference-tier video takes approximately 2 hours. English and Chinese are both supported natively. You are consulted at exactly four checkpoints.
Why a vibe-coder should care
Lets you produce polished explainer videos on any topic without hiring a motion graphics designer or paying for a generative video service. Everything runs locally — no cloud rendering, no subscription — just Claude Code or Codex and standard open-source tools.
How to install
Copy this and send it to your agent — Claude Code, Codex, any of them:
Install the skill from https://github.com/Vincentwei1021/anything2explainer: clone the repo into ~/.claude/skills/anything2explainer, install dependencies per the README (Node 18+, ffmpeg, Python packages), then make a demo explainer video on 'What are AI agents' and show me the output MP4. Ask me if you need any TTS API keys.
Разработан и проверен на macOS; Linux должен работать, Windows не тестировался. Нужен Node 18+, ffmpeg и Python — обычный MacBook справится. Рендеринг видео займёт 1–3 часа в фоне.
Open on GitHub▌ More finds