video-talkcraft skill
A skill that turns a coding agent into a studio for voiceover explainer videos: word-level sync, a motion library and Remotion assembly
- 2,292 ★ on the repository
- Last commit
Extended access
Why this level
- The skill runs video rendering and installs dependencies
- It may call a third-party voice synthesis service
Install
- Works in
Manual install
npx skills add Vincentwei1021/video-talkcraftYou will need Node.js 18+, ffmpeg and Python dependencies for rendering.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The skill runs video rendering and installs dependencies
- It may call a third-party voice synthesis service
This is third-party code. Review the repository files before installing.
What it does
video-talkcraft gives an agent a pipeline for voiceover explainer videos. The skill takes a script and a finished voiceover, builds word-level timestamps on the CPU, arranges frames in layers and assembles a cinematic video through Remotion in landscape or portrait format. Inside are a unified visual language, a set of motion cards and a shot-building system that moves away from a static slideshow look. It includes an automatic static-frame check and a separate review loop through a subagent.
Who it is for. For content teams, marketers and authors who need voiceover explainer videos.
Good fit when
- You need an explainer or overview video from a script and voiceover
- You need picture synced to voice at the word level
- You need moving shots instead of static slides
Not a fit when
- You need a digital presenter generated: that is out of scope, the character is an input
- You cannot install Remotion, ffmpeg and Python dependencies
Example request
Make an explainer video from this script and voiceover, sync the picture at the word levelLimitations
The skill assembles video but does not generate a digital presenter: character assets are provided as input. It needs Node.js 18 or later, ffmpeg and a set of Python dependencies, and voiceover synthesis from text optionally uses a third-party service. By default it uses a finished voiceover.
How to disable. Remove the symlink or skill folder from ~/.claude/skills and delete the cloned repository.
FAQ
Does the skill create a talking character?
No, digital presenter generation is out of scope. Character assets are an input; the skill handles video assembly.
Do I need my own voiceover?
By default it uses a finished voiceover; optionally you can synthesize voice and timestamps from a script via a third-party service.
Discussion
No questions or reviews yet.
Related
SkillsA Claude Code and Codex skill that turns a topic into a narrated motion-graphics explainer video on Remotion with subtitles and chapters
A skill that turns a topic into a narrated 4K video: research, script, local TTS, Remotion composition and an FFmpeg mix
A skill for Claude Code and Codex that builds cinematic product videos with Remotion from shot recipe cards, a ready template and audio assets
A Codex skill that turns a script or a voice recording into video with motion graphics, captions and an editable Remotion project.
The video-explainer skill turns a script into a vertical 9:16 explainer: narration, captions, Remotion and a pre-render review
motion-video-production: a skill for motion videos
motion-video-production
A skill that takes an agent through seven stages for a 15 to 90 second video, a script checking each stage before the next
README in short
The README describes video-talkcraft as a skill that turns Claude Code or Codex into a studio for voiceover explainer videos. The pipeline goes from script and voiceover to word-level timestamps, layered shots and Remotion assembly. It has a unified visual language, a motion card library, a shot system against a slideshow look and an automatic check with a review loop. By default it uses a finished voiceover, and presenter generation is out of scope. It needs Node.js, ffmpeg and Python dependencies.