Hey everyone, I've been working on this for a while and finally shipped it. The problem was simple: I kept saving huge YouTube playlists ("learn React", "best productivity tips", etc.) and then never finishing them because half the videos were clickbait, outdated, or just not relevant to me. So I built **SiftWatch** — you paste a YouTube playlist URL, and AI analyzes every video and classifies them into three categories: - **WATCH** — worth your full attention - **LISTEN** — good content but you don't need to watch the screen (perfect for commuting) - **SKIP** — not worth your time **What makes it different from just reading comments:** The AI doesn't just give you a thumbs up/down. For each video, you get: - A relevance score (1-10) - A summary of what the video actually covers - Key takeaways (bullet points) - Timestamps for the important moments - Skip segments (sponsors, long intros, padding) - An "effective duration" — how long the video is if you skip the filler

My YouTube playlists are embarrassing. 200+ videos I saved and never went back to. I don't even remember why half of them are there. I got tired of opening a playlist and just... staring at it. So I built SiftWatch. Paste a playlist link, it tells you what's worth watching, what works as background audio, and what you should've never saved in the first place. The skip list is brutal. I love it.