explaingit

oguzcankaraman/watch_youtube_skill

Analysis updated 2026-05-18

44PythonAudience · vibe coderComplexity · 3/5Setup · moderate

TLDR

A Python pipeline that lets Claude watch YouTube videos by combining transcripts and key screenshots into searchable Obsidian notes.

Mindmap

mindmap
  root((Watch Youtube Skill))
    What it does
      Downloads video transcript
      Extracts key screenshots
      Sends both to Claude
    Tech stack
      Python
      ffmpeg
      spaCy and scikit-learn
    Use cases
      Turn tutorials into notes
      Search video content as text
      Build a personal video wiki
    Audience
      Tutorial watchers
      Claude Code users
    Output
      Obsidian Markdown notes
      Storyboard grid images

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Turn a long tutorial video into structured, searchable notes automatically.

USE CASE 2

Combine video transcripts with key screenshots so on screen content is not lost.

USE CASE 3

Build a personal Obsidian knowledge base from videos you watch regularly.

USE CASE 4

Let Claude Code automatically summarize any YouTube link you share with it.

What is it built with?

PythonffmpegspaCyscikit-learnyt-dlpPillow

How does it compare?

oguzcankaraman/watch_youtube_skilllorenliu13/claude-code-for-hydrologyalibaba/omnidoc-tokenbench
Stars444443
LanguagePythonPythonPython
Setup difficultymoderateeasymoderate
Complexity3/52/53/5
Audiencevibe coderresearcherresearcher

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Requires Python 3.11+, ffmpeg, and the spaCy language model downloaded before first use.

No license information was provided in the README, so usage rights are unclear.

In plain English

Watch Youtube Skill is a Python tool that turns a YouTube video into a set of notes by having Claude, Anthropic's AI, effectively watch the video and write up what it sees and hears. It builds a grid of screenshots taken from the video's most informative moments, hands that grid along with the transcript to Claude for analysis, and saves the results as structured notes in a personal knowledge base built on Obsidian, a note taking app. The problem it solves is that a transcript alone misses everything that only appears on screen, such as code, diagrams, terminal output, or slides. The tool bridges that gap by combining transcript text with carefully chosen screenshots rather than grabbing frames at fixed time intervals. It works as a pipeline. First it downloads the video's transcript, or if none exists, transcribes the audio using a fallback service. Then it uses a natural language processing library to find moments where the speaker points at something on screen, using phrases like "look at this" or "here we have", and also detects long stretches of silence, which often mean a demo or visual is being shown without narration. It pulls video frames from just those moments using ffmpeg, arranges them into a grid image called a storyboard, and sends the transcript and storyboard together to Claude, which can read both text and images, for a written analysis. The resulting notes are saved as Markdown files formatted for Obsidian, organized under a docs folder with an index page and per-video records. The system also learns over time. After each video it compares the words near chosen screenshot moments against the rest of the transcript to find terms that matter most, and stores those in a small local file so future videos benefit from what it has learned. This is best suited for people who watch a lot of tutorial or educational videos and want searchable, structured notes without rewatching the whole thing. It requires Python 3.11 or newer and ffmpeg installed locally, and works either as a standalone command line tool or automatically inside Claude Code.

Copy-paste prompts

Prompt 1
Explain how Watch Youtube Skill decides which video frames to turn into screenshots.
Prompt 2
Walk me through installing Python 3.11, ffmpeg, and this tool's dependencies.
Prompt 3
Show me how to run watch-youtube from the command line on a specific video URL.
Prompt 4
Help me set up the optional Groq API key for videos without captions.
Prompt 5
Explain how the self-learning keyword system improves screenshot selection over time.

Frequently asked questions

What is watch_youtube_skill?

A Python pipeline that lets Claude watch YouTube videos by combining transcripts and key screenshots into searchable Obsidian notes.

What language is watch_youtube_skill written in?

Mainly Python. The stack also includes Python, ffmpeg, spaCy.

What license does watch_youtube_skill use?

No license information was provided in the README, so usage rights are unclear.

How hard is watch_youtube_skill to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is watch_youtube_skill for?

Mainly vibe coder.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.