AI video skill for Claude Code & Codex — cinematic, editable product promos with Remotion: 124 shot recipe cards, 150 motion previews, beat sync, sound design, Motion Workbench & JianYing (CapCut CN) export.
About this project
video-shotcraft is an open-source video generation project on GitHub: AI video skill for Claude Code & Codex — cinematic, editable product promos with Remotion: 124 shot recipe cards, 150 motion previews, beat sync, sound design, Motion Workbench & JianYing (CapCut CN) export. It sits in the video generation space, where the pipeline has to keep frames, motion and often audio consistent over time rather than produce a single still. It is maintained by Vincentwei1021 and published as a public repository you can read, fork and run yourself.
On GitHub the repository is tagged agent-skills, ai-agents, ai-video, claude-code, claude-code-skills, claude-skills, codex, motion-design, motion-graphics and product-video, which is a fair summary of what it covers. Workflows are heavier than image generation: long render times, significant VRAM and a queue-based setup if you plan to produce more than a handful of clips.
It is written mainly in TypeScript and released under APACHE-2.0, a permissive license — commercial use is fine as long as copyright notices are kept. It is actively maintained: the most recent commit landed on November 18, 2026.
To try it, clone the repository and follow its README; that file is the canonical install guide. There is also a project page at https://vincentwei1021.github.io/video-shotcraft/ for documentation or a hosted demo. Because it runs on your own infrastructure, budget time for environment setup: dependencies, model weights and configuration usually take longer than the first successful run.
Key facts as recorded on GitHub: 21,084 stars; 1,941 forks; primary language TypeScript; license APACHE-2.0; last commit on November 18, 2026; topics agent-skills, ai-agents, ai-video, claude-code, claude-code-skills, claude-skills.