Add 4 specialized NotebookLM skills based on notebooklm-py library: - 50-notebooklm-agent: Q&A agent for notebook queries with citations - 51-notebooklm-automation: Full notebook/source/artifact management - 52-notebooklm-studio: Content generation (podcasts, videos, quizzes) - 53-notebooklm-research: Web/Drive research and source discovery Each skill includes: - README.md: Overview and quick start - code/CLAUDE.md: Claude Code version (concise) - desktop/SKILL.md: Claude Desktop version (with YAML frontmatter) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
1.2 KiB
1.2 KiB
NotebookLM Research - Claude Code
Research workflows: web research, Drive search, auto-import, source extraction.
Prerequisites
pip install notebooklm-py
playwright install chromium
notebooklm login
Research Commands
# Web research
notebooklm source add-research "topic"
notebooklm source add-research "topic" --mode deep --import-all
notebooklm source add-research "topic" --mode deep --no-wait
# Drive research
notebooklm source add-research "topic" --from drive
# Status and wait
notebooklm research status
notebooklm research wait --import-all
Source Extraction
notebooklm source fulltext <id>
notebooklm source guide <id>
Research Modes
| Mode | Sources | Time |
|---|---|---|
fast |
5-10 | seconds |
deep |
20+ | 2-5 min |
Subagent Pattern
# Non-blocking deep research
notebooklm source add-research "topic" --mode deep --no-wait
# Spawn subagent to wait
Task(
prompt="Wait for research and import: notebooklm research wait -n {id} --import-all",
subagent_type="general-purpose"
)
Autonomy
Auto-run: research status, source fulltext, source guide
Ask first: source add-research, research wait --import-all