YouTube research into Obsidian graph
Claude Code searched YouTube, loaded 20 videos into NotebookLM, asked cited questions, and saved everything to Obsidian as linked notes.
The author turned 20 videos into a browsable knowledge graph of sources and topics in their vault. A citation audit found about 60% strong matches.
Overview
How it was set up
Claude Code skill driving a NotebookLM CLI, ytcli for YouTube search, and Obsidian for the vault. The skill repo is on GitHub.
Worth knowing
Citation audit found 31% partial matches and 10-15% weak ones. Good as a research starting point, not for citing without checking.
A prompt to start from
Search YouTube for [topic], show me the results so I can pick videos, add the chosen ones to a new NotebookLM notebook, ask [question], and save the cited answer into my Obsidian vault with a file per source and per topic, linked by wikilinks.
Written by Agentic Feats from the source. Not the author's exact prompt.
Sources 1
History
- Source published
- 2026-02-24
- Added to Agentic Feats
- 2026-10-13
- Pick
- No
- Markdown copy
- /c/youtube-research-into-obsidian-graph-claude-code.md
More in research
36 featsResultIt created the text file as asked, but after clicking a result it took a screenshot too early and hallucinated the answer.
ResultOperator handled tour search and lesson plan but was slow; adding three grocery items took 15 minutes and an Uber price check took five.
ResultThe draft was usable but weaker than accepted NSF summaries; thinking mode helped, though it began hallucinating and misreading the sources.