What problem does it solve? Turning an article, notes, or a topic brief into a narrated explainer video normally requires scripting, voiceover recording, motion design, and video assembly. This Skill automates that entire pipeline: it converts arbitrary text into a narrator script, synthesizes voiceover and background music, designs typography/abstract/diagram/data-viz scenes, and renders a finished video up to about 3 minutes long. ## Core Features & Use Cases - Text-to-video orchestration: A binding multi-phase runbook (init, scaffold, scriptwriting, design system, audio, visual design, captions, parallel scene workers, finalize) that produces narrator_scripts.json, audio_meta.json, section_plan.md, group_spec.json, and a rendered video.mp4. - Generated narration and music: TTS via HeyGen, ElevenLabs, or local Kokoro, plus BGM via Lyria or local MusicGen, with word-level timestamps driving deterministic captions. - Auto-selected visual style: The scriptwriting agent picks one of five shipped style presets (block-frame, capsule, claude, pin-and-paper, scatterbrain) and landscape/portrait/square orientation per input. - Use Case: Paste a blog post about a technical concept and receive a 60-90 second captioned explainer video with synthesized narration, background music, and animated typography scenes, with no website capture or product screenshots involved. ## Quick Start Ask the agent to turn your article or notes into a faceless explainer video, then confirm the topic, length, aspect ratio, and language when prompted.
