kg-enrich-auto

Automate scholarly paper discovery and ingestion into a Neo4j knowledge graph.

1|Updated Jan 11, 2026
One-click install
npx skills add https://github.com/YH-05/quants --skill kg-enrich-auto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kg-enrich-auto
Source: https://github.com/YH-05/quants/tree/main/.claude/skills/kg-enrich-auto
Command: npx skills add https://github.com/YH-05/quants --skill kg-enrich-auto

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automatically searches for academic papers using alphaxiv MCP and continuously ingests results into a Neo4j knowledge graph, enabling ongoing knowledge accumulation until a specified END_TIME.

Core Features & Use Cases

  • Autonomous loop of gap-analysis, search, ingestion, connectivity, and optimization that runs until END_TIME.
  • Ingests paper metadata into Neo4j as Source nodes, Authors, Topics, and Claims; creates relationships such as AUTHORED_BY, TAGGED, MAKES_CLAIM, USES_METHOD.
  • Ideal for building a living scholarly KG for literature reviews, meta-analyses, and research trend exploration in academic or research engineering settings.

Quick Start

Run kg-enrich-auto with END_TIME set to a future ISO 8601 timestamp to start the continuous enrichment cycle.

Frequently Asked Questions about kg-enrich-auto

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

FAQPage Schema
How do I automatically ingest academic papers into a Neo4j knowledge graph?

Automatically ingest academic papers into a Neo4j knowledge graph by running an autonomous loop that uses alphaxiv MCP for discovery, creating Source, Author, Topic, and Claim nodes with deterministic MERGE-based Cypher patterns for idempotent writes.

Can I run continuous knowledge graph enrichment until a specific time limit?

Continuous knowledge graph enrichment runs until a specified time limit by setting the END_TIME parameter to a future ISO 8601 timestamp, driving a cyclic process of gap analysis, search, ingestion, connectivity, and optimization.

What is the best way to structure scholarly literature review data in Neo4j?

Structure scholarly literature review data by ingesting paper metadata into Neo4j as Source nodes and creating relationships like AUTHORED_BY, TAGGED, MAKES_CLAIM, and USES_METHOD to map complex academic connections for meta-analyses.

Does this knowledge graph enrichment workflow require manual gap analysis between searches?

Gap analysis is fully automated within the cyclic process, requiring no manual intervention between searches. The workflow autonomously identifies missing knowledge, searches via alphaxiv MCP, ingests results, and optimizes graph connectivity continuously.

How do Neo4j MERGE-based Cypher patterns ensure deterministic graph writes?

Neo4j MERGE-based Cypher patterns ensure deterministic, idempotent writes by generating specific IDs and using MERGE clauses to prevent duplicate nodes or relationships during the autonomous academic paper ingestion process.

What scholarly paper metadata gets extracted when building a knowledge graph?

Scholarly paper metadata extracted includes Source nodes representing papers, Authors, Topics, and Claims, connected through structured relationships to enable comprehensive research trend exploration and living knowledge accumulation.