What problem does it solve? When producing Xiaohongshu (RED) videos from Markdown articles, users face multiple pipeline choices involving different TTS engines, aspect ratios, and rendering approaches. This Skill acts as a unified entry point that collects user preferences first, then routes to the correct video production pipeline, eliminating confusion about which workflow to use. ## Core Features & Use Cases - Preference Collection: Asks five structured questions covering translation needs, TTS requirements, TTS engine selection (ChatTTS vs edge-tts), and BGM style before any production begins. - Pipeline Routing: Routes to Pipeline A (xhs-video-pipeline, GSAP screenshots + BGM, 1080×1440) or Pipeline B (xhs-video-workflow, HyperFrames + TTS, 1080×1920) based on answers. - Environment Check: Verifies ffmpeg availability before starting production. - Use Case: A content creator has a Markdown article and wants a narrated vertical video for Xiaohongshu. The orchestrator asks whether they need ChatTTS voiceover, then hands off to the matching pipeline skill to execute the full rendering workflow. ## Quick Start Ask the assistant to make a Xiaohongshu video from your Markdown article and answer the preference questions about translation, TTS, and BGM style.
