397fa2aa5d
* Fix SEO skill 34 bugs, Korean labels, and transition Ahrefs refs to our-seo-agent P0: Fix report_aggregator.py — wrong SKILL_REGISTRY[33] mapping, missing CATEGORY_WEIGHTS for 7 categories, and break bug in health score parsing that exited loop even on parse failure. P1: Remove VIEW tab references from skill 20, expand skill 32 docs, replace Ahrefs MCP references across all 16 skills (19-28, 31-34) with our-seo-agent CLI data source references. P2: Fix Korean labels in executive_report.py and dashboard_generator.py, add tenacity to base requirements, sync skill 34 base_client.py with canonical version from skill 12. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Add Claude Code slash commands for SEO skills 19-34 and fix stale paths Create 14 new slash command files for skills 19-28, 31-34 so they appear as /seo-* commands in Claude Code. Also fix stale directory paths in 8 existing commands (skills 12-18, 29-30) that referenced pre-renumbering skill directories. Update .gitignore to track .claude/commands/ while keeping other .claude/ files ignored. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Add 8 slash commands, enhance reference-curator with depth/output options - Add slash commands: ourdigital-brand-guide, notion-writer, notebooklm-agent, notebooklm-automation, notebooklm-studio, notebooklm-research, reference-curator, multi-agent-guide - Add --depth (light/standard/deep/full) with Firecrawl parameter mapping - Add --output with ~/Documents/reference-library/ default and user confirmation - Increase --max-sources default from 10 to 100 - Rename /reference-curator-pipeline to /reference-curator - Simplify web-crawler-orchestrator label to web-crawler in docs Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
63 lines
1.2 KiB
Markdown
63 lines
1.2 KiB
Markdown
---
|
|
description: Q&A agent using NotebookLM's Gemini-powered analysis with source citations
|
|
---
|
|
|
|
# NotebookLM Agent
|
|
|
|
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` |
|
|
|
|
## Source
|
|
Full details: `custom-skills/50-notebooklm-agent/code/CLAUDE.md`
|