What problem does it solve? Creating precise mathematical or scientific animation videos by hand is slow and error-prone. This Skill turns a plain-language idea into a finished MP4 by writing, rendering, reviewing, and finalizing Manim scene code through a structured seven-stage workflow. ## Core Features & Use Cases - Seven-stage pipeline: framework selection (ManimCE vs ManimGL), sandbox setup, scene planning, code generation, low-quality rendering, self-review with frame extraction, and 1080p60 finalization with ffmpeg concatenation. - Narration and subtitle support: per-scene audio clips generated with text-to-speech, duration-matched animation timing, and word-level Whisper transcription producing SRT subtitles muxed into the final video. - Curated rule packs and plugins: topic-specific ManimCE/ManimGL rule files, runnable examples, scene templates, and a trigger table for on-demand plugins like manim-dsa, manim-ml, and manim-voiceover. - Use Case: Ask for a step-by-step animation explaining gradient descent with LaTeX equations and narration; the Skill plans the scenes, writes the code, renders and reviews each scene, then delivers a subtitled final MP4. ## Quick Start Create a narrated Manim animation video that explains how a binary search algorithm works, with LaTeX formulas and English subtitles.
