A Codex skill for Vox-style paper-collage explainers with no video-generation model: an image model produces approved hero-frame stills, only key layers are cut out and animated, and HyperFrames handles camera moves, text, and narration deterministically, gated by three user approvals before rendering.
INSTALL PAPER-CUT
git clone https://github.com/aijiduonadegou/paper-cut.git "$env:USERPROFILE\.codex\skills\paper-cut"
Copied as written in the repo's README. Check the README for options and requirements.
STACK
HyperFramesFFmpegPython
“无需视频模型，即可制作拼贴动画的skill。用图像模型定稿、原图拆层与 HyperFrames 代码动画制作可编辑 Paper Cut / Vox 风格纸拼贴科普视频；支持三阶段审批、旁白、音效、文字动效与确定性 QA。”
About Explainers
Narrated lessons and knowledge videos: script, voiceover, diagrams and captions assembled into a teaching video.