Create voiceover-synced explainer videos with video-talkcraft
Use video-talkcraft when a coding agent needs to turn a script and finished voiceover into a Remotion-rendered explainer video with timed motion, subtitles, QA, and reviewable shot structure.
npx skills add agentskillexchange/skills --skill create-voiceover-synced-explainer-videos-with-video-talkcraft
video-talkcraft is an agent skill for producing voiceover-driven explainer videos through Claude Code, Codex, or compatible local coding agents. Use it when the operator has a narration script and finished audio, or wants the agent to generate narration assets, then create a shotbook, align word-level timing, implement Remotion scenes, render the video, and run visual/audio checks. The scope boundary is end-to-end local video-production workflow from script and voiceover to rendered explainer; it is not a generic Remotion framework listing, generic video editor, or stock media tool.
What this skill actually does
Inputs and prerequisites: Claude Code, Codex, or compatible coding agent; Node.js 18+; Python 3.10+; ffmpeg; Remotion dependencies installed by the skill workflow.
Setup notes: Install with npx skills add Vincentwei1021/video-talkcraft, or clone https://github.com/Vincentwei1021/video-talkcraft and link it into the target agent skills directory. Provide a script and voiceover file, then invoke the skill to generate the shotbook, timing, Remotion implementation, render, and QA outputs.
Source and verification boundary: use https://vincentwei1021.github.io/video-talkcraft/ as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.