skills.rest
roycolumbia-code
roycolumbia-codeCOMMUNITY
Explore all skills by this author →
GitHub

nlm-vault

Query NotebookLM corpora with long-context memory and parse JSON responses.

Updated Mar 23, 2026
Search Tags:#notebooklm#data insights#corpus analysis#semantic query#long-context memory
One-click install
npx skills add https://github.com/roycolumbia-code/claude-global-config --skill nlm-vault
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nlm-vault
Source: https://github.com/roycolumbia-code/claude-global-config/tree/main/skills/nlm-vault
Command: npx skills add https://github.com/roycolumbia-code/claude-global-config --skill nlm-vault

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mcp__notebooklm, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill enables users to access a "long-context memory" for in-depth corpus analysis, using NotebookLM. It's ideal for large corpora that exceed the context window and requires semantic analysis.

Core Features & Use Cases

  • Long-Context Memory: Utilizes NotebookLM for in-depth analysis of large corpora.
  • Semantic Queries: Allows users to ask complex, semantic questions about the data.
  • Use Case: When Roy needs to analyze large corpora like vault Obsidian, email batches, or historical quotes, this Skill can index the data and provide meaningful insights.

Quick Start

Use the command /nlm-vault ask <notebook_name> <question> to query the NotebookLM with a specific question.

Frequently Asked Questions about nlm-vault

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I analyze large corpora that exceed the standard context window limits?▼

You can analyze large corpora exceeding context window limits by integrating NotebookLM for long-context memory, which indexes multifaceted data sets to provide meaningful semantic insights.

Can I ask complex semantic queries about my Obsidian vault using NotebookLM?▼

Yes, you can ask complex semantic queries about an Obsidian vault using NotebookLM, as this Skill indexes large corpora and parses JSON responses to extract meaningful answers.

What is the best way to index email batches for semantic data insights?▼

The best way to index email batches for semantic data insights is using NotebookLM integration to handle long-context memory and process complex queries across multifaceted data sets.

Do I need an MCP connection to perform corpus analysis with NotebookLM?▼

Yes, you need the MCP NotebookLM connection enabled to perform corpus analysis, as the Skill depends on it to access long-context memory and parse JSON responses for your queries.

How does long-context memory handle complex queries for historical quote analysis?▼

Long-context memory handles complex queries for historical quote analysis by integrating NotebookLM to index the large corpus and parse semantic queries to extract targeted insights.

What are the limitations of using NotebookLM for large corpus analysis?▼

A limitation of using NotebookLM for large corpus analysis is that it requires the MCP NotebookLM dependency to be configured, and it specifically outputs JSON responses that must be parsed to retrieve user query answers.

Related Skills

Explore More Data & Analytics Skills→
SNL-UCSBSNL-UCSB
63

survey

Automate structured analysis and synthesis of research paper corpora using NotebookLM.

Official
Advanced
alibabaalibaba
10.5k

pdf-extractor

Extract text, tables, and metadata from PDF documents into JSON.

Official
Intermediate
lucifertrjlucifertrj
17

nltk-nlp-text-cleaning

Clean, tokenize, and normalize English text with NLTK for NLP pipelines.

Community
Advanced
dglijin-ossdglijin-oss
10

elite-longterm-memory-local

Store and search memories locally using LanceDB and Ollama embeddings.

Community
Advanced