skills.rest
u9401066
u9401066COMMUNITY
Explore all skills by this author →
GitHub

knowledge-extractor

Extract concepts, entities, and relationships from educational materials into structured JSON knowledge graphs.

1|Updated Feb 3, 2026
Search Tags:#knowledge-graph#multi-hop#concept-extraction#ner#ai-augmentation#relation-detection#educational-materials
One-click install
npx skills add https://github.com/u9401066/anesthesia-exam --skill knowledge-extractor-u9401066
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: knowledge-extractor
Source: https://github.com/u9401066/anesthesia-exam/tree/main/.claude/skills/knowledge-extractor
Command: npx skills add https://github.com/u9401066/anesthesia-exam --skill knowledge-extractor-u9401066

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extract concepts, entities, and relationships from educational materials to build structured knowledge graphs that support advanced question generation and reasoning.

Core Features & Use Cases

  • NER and entity extraction: identify drugs, diseases, procedures, anatomy, and other domain concepts.
  • Relationship discovery: infer relations between entities to form graph edges.
  • Knowledge graph output: produces a structured JSON graph suitable for downstream tasks like multi-hop questions.

Quick Start

Process a textbook corpus to output a knowledge graph with entities, relationships, and provenance data.

Frequently Asked Questions about knowledge-extractor

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

FAQPage Schema
How do I extract concepts and relationships from educational materials to build a knowledge graph?▼

To build a knowledge graph from educational materials, apply named entity recognition and relation detection to textbooks or lecture notes to output a structured JSON graph of concepts and relationships.

What is multi-hop question generation and how does a knowledge graph support it?▼

Multi-hop question generation relies on structured knowledge graphs to chain multiple concepts. By extracting entities and relationships from educational texts, the graph provides the provenance data needed for downstream AI reasoning tasks.

Can I use this to extract medical concepts like drugs and diseases from clinical references?▼

Yes, you can extract clinical concepts like drugs, diseases, procedures, and anatomy from clinical references. The named entity recognition identifies domain concepts to form graph nodes for your structured output.

How do I perform relation detection between entities in textbook corpora?▼

Relation detection infers connections between extracted entities to form graph edges. Processing textbook corpora with this method yields a structured JSON graph suitable for downstream tasks like concept analysis.

Does this knowledge graph extraction process output structured data for downstream AI tasks?▼

Yes, the extraction process outputs a structured JSON graph containing entities, relationships, and provenance data. This format directly supports downstream AI augmentation tasks like multi-hop question generation.

Related Skills

Explore More Education & Research Skills→
aeonbridgeaeonbridge

graphrag

Build and query knowledge graphs from unstructured text with entity-relationship extraction.

Official
Advanced
zilliztechzilliztech
3

multi-hop-rag

Decompose questions, retrieve across documents, and synthesize cited answers.

Official
Advanced
SaschaBrunnerCHSaschaBrunnerCH
19

arcgis-knowledge-graphs

Query and visualize ArcGIS Knowledge graphs using openCypher.

Community
Advanced
vignesh2027vignesh2027
6

knowledge-graph-builder

Turn unstructured documents into queryable knowledge graphs with entity extraction and relationship mapping.

Community
Advanced