Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
Keeps the context that raw transcripts usually lose: creator, source, capture date, chapters, and language. Short-video notes can also include frames to preserve information that appears only on screen.
WHO IT'S FOR
Obsidian users
build a video-based knowledge base
AI agent / automation builders
integrate video transcription into AI workflows
Content researchers
analyze and summarize multi-platform video content
Digital archivists
create local backups of video transcripts and frames
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
In the terminal, change to the installed skill directory before running the runtime setup commands. This procedure requires a writable skill directory.
Run this complete block in the terminal to create an isolated environment, install dependencies, and check them.
Installs: Clone the canonical repository containing youtube-fetcher and set up its caption runtime. No agent-specific registration procedure is supplied.
Before you start
Git must be available.
Python 3.8–3.14 for captions.
Python 3.10 or newer is recommended for current optional yt-dlp releases.
Platform: macOS/Linux
Run this command in a terminal to clone the canonical repository.
Installs: Clone the canonical repository containing youtube-fetcher and set up its caption runtime. No agent-specific registration procedure is supplied.
Before you start
Git must be available.
Python 3.8–3.14 for captions, available through the py command.
Python 3.10 or newer is recommended for current optional yt-dlp releases.
Platform: Windows PowerShell
Run this command in a terminal to clone the canonical repository.
Replace [video URL] with one accessible YouTube video URL that exposes captions.
Replace [destination directory] with your desired writable notes directory.
Set up the caption runtime dependencies and use that environment's Python interpreter.
Use youtube-fetcher to save an archival Markdown note for this YouTube video: [video URL]. Save it in [destination directory] and report the absolute saved path.
Replace [YouTube video URL] with one accessible YouTube video URL that exposes captions.
Set up the caption runtime dependencies and use that environment's Python interpreter.
Use youtube-fetcher to retrieve the captions for [YouTube video URL] and give me a short summary of what was said, with timestamp links for the key points.