feat: Add NotebookLM skills (50-53) for Claude Code and Desktop
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>
This commit is contained in:
45
custom-skills/50-notebooklm-agent/README.md
Normal file
45
custom-skills/50-notebooklm-agent/README.md
Normal file
@@ -0,0 +1,45 @@
|
||||
# NotebookLM Agent
|
||||
|
||||
Q&A agent that answers user questions based on NotebookLM notebooks. Leverages NotebookLM's Gemini-powered analysis to provide grounded, citation-backed responses from uploaded sources.
|
||||
|
||||
## Use Cases
|
||||
|
||||
- Ask questions about documents in a specific notebook
|
||||
- Get summaries with source citations
|
||||
- Compare information across multiple sources
|
||||
- Research assistant workflows
|
||||
|
||||
## Prerequisites
|
||||
|
||||
```bash
|
||||
pip install notebooklm-py
|
||||
playwright install chromium
|
||||
notebooklm login # One-time browser auth
|
||||
```
|
||||
|
||||
## Quick Start
|
||||
|
||||
```bash
|
||||
# Set active notebook
|
||||
notebooklm use <notebook_id>
|
||||
|
||||
# Ask questions
|
||||
notebooklm ask "What are the key findings?"
|
||||
notebooklm ask "Compare approaches from different sources"
|
||||
|
||||
# Get citations with JSON output
|
||||
notebooklm ask "Summarize the methodology" --json
|
||||
```
|
||||
|
||||
## Versions
|
||||
|
||||
| Version | Path | Purpose |
|
||||
|---------|------|---------|
|
||||
| Claude Code | `code/` | CLAUDE.md for Claude Code integration |
|
||||
| Claude Desktop | `desktop/` | SKILL.md for Claude Desktop skills |
|
||||
|
||||
## Related Skills
|
||||
|
||||
- [51-notebooklm-automation](../51-notebooklm-automation/) - Full automation workflows
|
||||
- [52-notebooklm-studio](../52-notebooklm-studio/) - Content generation (podcasts, videos)
|
||||
- [53-notebooklm-research](../53-notebooklm-research/) - Research and source discovery
|
||||
55
custom-skills/50-notebooklm-agent/code/CLAUDE.md
Normal file
55
custom-skills/50-notebooklm-agent/code/CLAUDE.md
Normal file
@@ -0,0 +1,55 @@
|
||||
# NotebookLM Agent - Claude Code
|
||||
|
||||
Q&A agent that answers questions using NotebookLM's Gemini-powered analysis with source citations.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
```bash
|
||||
pip install notebooklm-py
|
||||
playwright install chromium
|
||||
notebooklm login # One-time auth
|
||||
```
|
||||
|
||||
## Commands
|
||||
|
||||
```bash
|
||||
# List notebooks
|
||||
notebooklm list
|
||||
|
||||
# Set context
|
||||
notebooklm use <notebook_id>
|
||||
|
||||
# Ask questions
|
||||
notebooklm ask "What are the key findings?"
|
||||
notebooklm ask "Elaborate on point 2" # continues conversation
|
||||
notebooklm ask "New topic" --new # new conversation
|
||||
|
||||
# With citations (JSON output)
|
||||
notebooklm ask "Summarize" --json
|
||||
|
||||
# Query specific sources
|
||||
notebooklm ask "Compare" -s source1 -s source2
|
||||
```
|
||||
|
||||
## Autonomy
|
||||
|
||||
**Auto-run:** `list`, `status`, `source list`, `ask`
|
||||
**Ask first:** `delete`, `source add`
|
||||
|
||||
## JSON Output Format
|
||||
|
||||
```json
|
||||
{
|
||||
"answer": "Response with [1] [2] citations",
|
||||
"references": [
|
||||
{"source_id": "...", "citation_number": 1, "cited_text": "..."}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
## Error Recovery
|
||||
|
||||
| Error | Fix |
|
||||
|-------|-----|
|
||||
| No context | `notebooklm use <id>` |
|
||||
| Auth error | `notebooklm login` |
|
||||
118
custom-skills/50-notebooklm-agent/desktop/SKILL.md
Normal file
118
custom-skills/50-notebooklm-agent/desktop/SKILL.md
Normal file
@@ -0,0 +1,118 @@
|
||||
---
|
||||
name: notebooklm-agent
|
||||
description: |
|
||||
Q&A agent for NotebookLM notebooks. Ask questions and get grounded, citation-backed answers from your sources.
|
||||
Triggers: ask NotebookLM, query notebook, research question, 노트북 질문, NotebookLM 에이전트.
|
||||
---
|
||||
|
||||
# NotebookLM Agent
|
||||
|
||||
Q&A agent that answers questions using NotebookLM's Gemini-powered analysis. Returns grounded responses with source citations.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
NotebookLM CLI must be installed and authenticated:
|
||||
|
||||
```bash
|
||||
pip install notebooklm-py
|
||||
playwright install chromium
|
||||
notebooklm login
|
||||
```
|
||||
|
||||
## When This Skill Activates
|
||||
|
||||
- User asks "ask NotebookLM about X"
|
||||
- User wants to "query my notebook"
|
||||
- User needs "research answers from sources"
|
||||
- Korean: "노트북LM에서 찾아줘", "노트북 질문"
|
||||
|
||||
## Quick Reference
|
||||
|
||||
| Task | Command |
|
||||
|------|---------|
|
||||
| List notebooks | `notebooklm list` |
|
||||
| Set active notebook | `notebooklm use <id>` |
|
||||
| Ask question | `notebooklm ask "question"` |
|
||||
| New conversation | `notebooklm ask "question" --new` |
|
||||
| With citations | `notebooklm ask "question" --json` |
|
||||
| Specific sources | `notebooklm ask "q" -s src1 -s src2` |
|
||||
|
||||
## Workflow
|
||||
|
||||
### 1. Select Notebook
|
||||
|
||||
```bash
|
||||
# List available notebooks
|
||||
notebooklm list
|
||||
|
||||
# Set context (use partial ID)
|
||||
notebooklm use abc123
|
||||
```
|
||||
|
||||
### 2. Ask Questions
|
||||
|
||||
```bash
|
||||
# Simple question
|
||||
notebooklm ask "What are the main findings?"
|
||||
|
||||
# Follow-up (continues conversation)
|
||||
notebooklm ask "Can you elaborate on point 2?"
|
||||
|
||||
# New conversation
|
||||
notebooklm ask "Different topic" --new
|
||||
|
||||
# Query specific sources only
|
||||
notebooklm ask "Compare these two" -s source1_id -s source2_id
|
||||
```
|
||||
|
||||
### 3. Get Structured Output
|
||||
|
||||
For citations and references, use `--json`:
|
||||
|
||||
```bash
|
||||
notebooklm ask "Summarize the methodology" --json
|
||||
```
|
||||
|
||||
Returns:
|
||||
```json
|
||||
{
|
||||
"answer": "The methodology involves... [1] [2]",
|
||||
"references": [
|
||||
{"source_id": "abc...", "citation_number": 1, "cited_text": "..."},
|
||||
{"source_id": "def...", "citation_number": 2, "cited_text": "..."}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
## Autonomy Rules
|
||||
|
||||
**Run automatically:**
|
||||
- `notebooklm list` - view notebooks
|
||||
- `notebooklm status` - check context
|
||||
- `notebooklm source list` - view sources
|
||||
- `notebooklm ask "..."` - answer questions
|
||||
|
||||
**Ask before running:**
|
||||
- `notebooklm delete` - destructive operations
|
||||
- `notebooklm source add` - modifies notebook
|
||||
|
||||
## Tips
|
||||
|
||||
1. **Set context first**: Always `use` a notebook before asking
|
||||
2. **Use --json for citations**: Get structured references for research
|
||||
3. **Continue conversations**: Omit `--new` for follow-up questions
|
||||
4. **Filter sources**: Use `-s` to query specific documents only
|
||||
|
||||
## Error Handling
|
||||
|
||||
| Error | Solution |
|
||||
|-------|----------|
|
||||
| "No notebook context" | Run `notebooklm use <id>` |
|
||||
| Auth error | Run `notebooklm login` |
|
||||
| Source not found | Check `notebooklm source list` |
|
||||
|
||||
## Related Skills
|
||||
|
||||
- **notebooklm-automation**: Full notebook management
|
||||
- **notebooklm-studio**: Generate podcasts, videos, quizzes
|
||||
- **notebooklm-research**: Add sources and research workflows
|
||||
Reference in New Issue
Block a user