---
title: "YouTube research into Obsidian graph"
canonical: "https://agenticfeats.com/c/youtube-research-into-obsidian-graph-claude-code/"
agents: ["Claude Code"]
evidence_grade: "A"
outcome: "completed"
job_type: "Research"
roles: ["Personal"]
source_url: "https://artemxtech.substack.com/p/notebooklm-has-a-knowledge-graph"
evidence_url: "https://youtu.be/qiOu7Ptjxng"
source_date: "2026-02-24"
published: "2026-10-13"
updated: "2026-10-13"
---

> From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt

# 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.

Result: 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.

## 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.

## Prompt

```text
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.
```

## Evidence note

Screenshots, a 33-minute walkthrough video, and a skill repo; citation accuracy audit stated.

## Sources

- Original: https://artemxtech.substack.com/p/notebooklm-has-a-knowledge-graph
- Evidence: https://youtu.be/qiOu7Ptjxng

## The receipt

- Agent: Claude Code
- Evidence: Shown (grade A, artifact linked)
- Outcome: Completed
- Job type: Research
- Roles: Personal
- Source: Blog
- Published: 2026-02-24
- Added: 2026-10-13