anything2explainer Skill Turns Topics into Narrated Explainer Videos with Remotion

anything2explainer is a Claude Code and Codex skill that converts a given topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar in Chinese or English. The workflow researches sources, writes narration, generates voiceover, storyboards shots and assigns multiple agents to draw each frame in code with Remotion, followed by per-chapter review agents. A Chinese example on RAG and knowledge bases runs nearly five minutes across 44 shots, with production taking about one to three hours depending on length.
Event version 1.
Key insights
Topic-to-video pipeline
The skill accepts a topic and outputs a narrated explainer video with voiceover, subtitles and a chapter progress bar. It supports both Chinese and English.
Research-backed narration
The workflow first researches material and attaches sources to every number and analogy. It then writes narration and generates the voiceover before storyboarding shots against the audio.
Parallel Remotion rendering
Multiple agents draw each shot in parallel using Remotion, with every frame drawn in code rather than stock footage or generative video models. Dedicated agents then review and fix issues chapter by chapter.
Limited human checkpoints
The process pauses to ask the user only at four checkpoints and runs autonomously otherwise. A Chinese example on RAG and knowledge bases spans nearly five minutes and 44 shots.
Production time
Producing one video takes roughly one to three hours depending on its length.