Auto Pop-Sci is an Agent Skill for Cursor, Claude Code, Codex and other agents that makes 3Blue1Brown-style math and science videos. It works through a hook-build-deepen-conclude outline, a full narration script, Manim scenes and Edge TTS voice, then a timestamp-based ffmpeg pipeline keeps audio, animation and subtitles aligned. Narration defaults to Chinese but other languages are supported. Install with npx skills add; needs Python 3.11+, uv, LaTeX and ffmpeg.
INSTALL AUTO-POPSCI
npx skills add TrapedCircuit/Auto-PopSci
Copied as written in the repo's README. Check the README for options and requirements.
STACK
ManimPythonEdge TTSFFmpeguv
“Agent Skill for generating math/science popularization videos with Manim + AI narration”
About Explainers
Narrated lessons and knowledge videos: script, voiceover, diagrams and captions assembled into a teaching video.