survey

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

63|2|Updated Mar 27, 2026
One-click install
npx skills add https://github.com/SNL-UCSB/literature-survey-skill --skill survey-snl-ucsb
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: survey
Source: https://github.com/SNL-UCSB/literature-survey-skill/tree/main
Command: npx skills add https://github.com/SNL-UCSB/literature-survey-skill --skill survey-snl-ucsb

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and scripts (resource) components.

What problem does it solve?

This Skill solves the operational exhaustion of academic literature surveys by automating paper ingestion, claim extraction, and cross-referencing, allowing researchers to focus on hypothesis formation and narrative construction.

Core Features & Use Cases

  • Structured Workflow: Guides users through Intent, Triage, Deepen, and Synthesize modes to prevent common cognitive biases like anchoring and WYSIATI.
  • Grounded Analysis: Uses NotebookLM as a query backend to ensure all extractions are backed by exact quotes and citations.
  • Use Case: A PhD student preparing for an area exam can use this to map a 100-paper corpus, identify fundamental design invariants, and generate a structured gap analysis in a fraction of the usual time.

Quick Start

Run the survey intent command to begin capturing your research goals and survey archetype.

Frequently Asked Questions about survey

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

FAQPage Schema
How do I automate literature survey analysis for a large research paper corpus?

Automated literature survey analysis uses a structured workflow to ingest papers, extract claims, and cross-reference dependencies. This Skill maps a large corpus by guiding you through Intent, Triage, Deepen, and Synthesize modes to prevent cognitive biases.

Does this literature survey workflow require NotebookLM to extract grounded citations?

Yes, grounded citation extraction requires the NotebookLM MCP CLI configured as an MCP server within your Claude Code environment. It acts as a query backend to ensure all extracted claims are backed by exact quotes and citations from the source papers.

What is the best way to map cross-paper dependencies and identify research gaps?

Mapping cross-paper dependencies and research gaps is achieved through first-principles decomposition and structured synthesis modes. The Skill tracks dependencies across papers and generates a structured gap analysis, allowing you to focus on hypothesis formation and narrative construction.

Can I use this academic synthesis workflow for a 100-paper PhD area exam preparation?

Yes, this academic synthesis workflow is designed for PhD area exam preparation and similar scale demands. It handles a 100-paper corpus by mapping the landscape, identifying fundamental design invariants, and generating gap analysis in a fraction of the usual time.

How do I start a structured literature review using AI-driven rigor?

Start a structured literature review by running the survey intent command to capture your research goals and survey archetype. This initiates the structured analysis workflow, automating paper ingestion and claim extraction to eliminate operational exhaustion.

What are the limitations of using AI for academic literature reviews?

AI-driven literature reviews rely entirely on the NotebookLM backend and the ingested corpus for grounded analysis. The approach prevents anchoring biases during synthesis but requires proper MCP server configuration and cannot generate hypotheses beyond the provided papers.