Add notebooklm skill#73
Closed
apcg2001 wants to merge 1 commit into
Closed
Conversation
Integrates Google NotebookLM into the Claude Code skills system.
## What this does
Turns any expert content corpus (YouTube channels, PDFs, web pages) into
a cited knowledge base queryable from Claude Code, with answers linked back
to exact source passages as clickable Obsidian wikilinks.
## Workflow
1. **Load sources** — bulk-import YouTube channels or other content into a
NotebookLM notebook via the `notebooklm` CLI (async, 200 videos in ~75s)
2. **Query with citations** — ask questions via `nlm notebook query`, get
answers with `[N]` citation markers traced to exact transcript passages
3. **Resolve to wikilinks** — `resolve_citations.py` converts `[N]` to
`[[Source#^anchor|[N]]]` clickable links that jump to cited passages
4. **Import to vault** — source files with transcripts, cited passages, and
AI-generated guides land in `Notes/NotebookLM/{slug}/`
## Files
- `SKILL.md` — skill definition and routing table
- `scripts/load_channel.py` — YouTube channel scraper + async NotebookLM loader
- `scripts/import_sources.py` — imports NotebookLM sources as vault notes
- `scripts/resolve_citations.py` — resolves `[N]` to Obsidian block anchors (~96% accuracy)
- `scripts/extract_passages.py` — extracts cited passages into source files
- `scripts/backfill_fulltext.py` — backfills transcripts into existing source files
- `workflows/ask.md` — Q&A with citation resolution workflow
- `workflows/import.md` — import notebook sources to vault
- `workflows/youtube-channel.md` — bulk YouTube channel loader workflow
- `workflows/auth.md` — Google authentication via browser
## Prerequisites
```bash
uv tool install notebooklm-py --python 3.11
uv tool install notebooklm-mcp-cli
playwright install chromium
notebooklm login # browser auth
nlm login # browser auth
```
## Credits
Original skill by ArtemXTech (https://github.com/ArtemXTech/personal-os-skills)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
notebooklmskill that connects Claude Code to Google NotebookLM for cited Q&A against large source corpora[N]citation markers in NotebookLM answers to clickable[[Source#^anchor|[N]]]Obsidian wikilinks pointing to exact transcript passages (~96% resolution accuracy)What changed
New skill:
skills/notebooklm/SKILL.mdscripts/load_channel.pyscripts/import_sources.pyscripts/resolve_citations.py[N]citations to[[Source#^anchor]]wikilinksscripts/extract_passages.pyscripts/backfill_fulltext.pyworkflows/ask.mdworkflows/import.mdworkflows/youtube-channel.mdworkflows/auth.mdPrerequisites
Obsidian Dataview plugin required for notebook dashboards.
Test plan
notebooklm listreturns notebooks without errors after authnlm notebook listreturns notebooks without errors after authload_channel.py scrapefetches video list from a YouTube channel URLimport_sources.pycreates source.mdfiles with correct frontmatterresolve_citations.pyconverts[N]to wikilinks in Q&A outputCredits
Original skill concept and implementation by @ArtemXTech. This PR ports it to the obsidian-skills format.
🤖 Generated with Claude Code