A Codex/WorkBuddy skill producing a five-layer breakdown of a video, link, or transcript: positioning, viral structure, content, audiovisual language, and reusable strategy. It transcribes locally with a hardware-adaptive Whisper backend, using yt-dlp and FFmpeg for media handling. Installed by copying the folder into the agent's skills directory.
STACK
WhisperFFmpegyt-dlp
“专业的五层视频拆解 Codex Skill：支持视频链接、本地媒体和逐字稿。”
About Scripts & learning
Scripts, prompts and learning material about making video with agents rather than rendering tools themselves.