Vibetube — Development skill for Claude Code

VibeTube

Desktop **multicam recorder** (macOS / Electron). It captures your **screen** and your **webcam + microphone** in sync, organises them into **projects made of several clips**, and hands the folder to an AI coding agent — **Claude Code or Codex** — which edits the final video for you: automatic shot selection (full-cam / screen / PiP), subtitles, [**HyperFrames**](https://github.com/heygen-com/hyperframes) graphics and sound effects.

Then it **publishes it**. The same agent reads the subtitles of the finished cut and writes five title options and a description with real chapters, and [**Upload-Post**](https://upload-post.com) pushes the video straight to YouTube, TikTok, Reels and the rest — you never open a browser. See [Publishing to YouTube & co.](#publishing-to-youtube--co) below.

You record. The agent edits and publishes.


How it works

flowchart LR
    S["🖥️ Screen
(no audio)"] --> R
    W["🎥 Webcam + 🎙️ mic
(the only audio)"] --> R
    R["VibeTube
N synced clips"] --> P[("Project folder
clips/ + sync.json")]
    P --> A{"Agent
Claude Code
or Codex"}
    A --> V["video-use skill
transcribe → pick shots → cut"]
    V --> G["HyperFrames graphics
+ HeyGen SFX + subtitles"]
    G --> H["edit/final.mp4
1920×1080"]
    G --> N["edit/final_9x16.mp4
1080×1920"]
    H --> U["Upload-Post
YouTube, TikTok, Reels…"]
    N --> U

Every clip keeps two tracks on one timeline: `screen.webm` carries the picture only, and `webcam.webm` carries your camera **and the microphone** — it is the single source of audio for the whole project. `sync.json` stores the offset between them, so the editor can cut between shots without ever breaking the voice.

What happens to each clip before the agent sees it:

flowchart LR
    C["Raw take"] --> B["Bac