video1.0<iframe src="https://www.loom.com/embed/2efdc288e8ad4c6084fd0187d42bfd95" frameborder="0" width="1280" height="960" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>9601280Loomhttps://www.loom.com9601280https://cdn.loom.com/sessions/thumbnails/2efdc288e8ad4c6084fd0187d42bfd95-a5efbc7e67400ae4.gif173.719Hi, this is the Thief, and I’m documenting my project knowledge. I built an autonomous YouTube agent that takes a YouTube URL and a target folder, then extracts the content and saves raw and processed data into a predefined 6 to 7 folder structure. After that it updates the index, rebuilds a local semantic vector database, and pushes everything to GitHub for backup. If you want another folder or skill, you can use add content, folder scale, and it will ask for the folder name and skill type.