Skip to content

Step 2: Run the Learning Graph Generator Skill

Prompt

Run the learning-graph-generator skill

The "learning-graph-generator" skill is running

⏺ I'll generate a comprehensive learning graph for your healthcare data modeling course. Let me track this multi-step process with a todo list.

⏺ Bash(mkdir -p docs/learning-graph && ls -la docs/learning-graph) ⎿  total 0
drwxr-xr-x 2 dan staff 64 Nov 6 12:53 . drwxr-xr-x 18 dan staff 576 Nov 6 12:53 ..

⏺ Write(docs/learning-graph/course-description-assessment.md) ⎿  Wrote 171 lines to docs/learning-graph/course-description-assessment.md # Course Description Quality Assessment ## Course Title Modeling Healthcare Data with Graphs ## Overall Score: 100/100 ## Quality Rating: Excellent - Ready for Learning Graph Generation --- … +161 lines (ctrl+o to expand)

⏺ Write(docs/learning-graph/concept-list.md) ⎿  Wrote 243 lines to docs/learning-graph/concept-list.md
# Concept List for Modeling Healthcare Data with Graphs This document contains 200 concepts for the course "Modeling Healthcare Data with Graphs". Each concept is numbered and formatted in Title Case with a maximum of 32 characters. ## Foundation Concepts (1-15) 1. Graph Theory Basics 2. Node 3. Edge 4. Graph Database … +233 lines (ctrl+o to expand)

⏺ Write(docs/learning-graph/learning-graph.csv) ⎿  Wrote 202 lines to docs/learning-graph/learning-graph.csv ConceptID,ConceptLabel,Dependencies 1,Graph Theory Basics, 2,Node,1 3,Edge,1|2 4,Graph Database,1|2|3 5,Labeled Property Graph,4 6,Node Property,2|5 7,Edge Property,3|5 8,Directed Graph,1|2|3 9,Directed Acyclic Graph,8 … +192 lines (ctrl+o to expand)

⏺ Search(pattern: "**/.claude/skills/learning-graph-generator/analyze-graph.py") ⎿  Found 0 files

⏺ Write(docs/learning-graph/analyze-graph.py) ⎿  Wrote 299 lines to docs/learning-graph/analyze-graph.py
#!/usr/bin/env python3 """ Learning Graph Quality Analysis This script analyzes a learning graph CSV file and generates a quality report. It checks for: - DAG structure (no cycles) - Self-dependencies - Foundational concepts (zero dependencies) - Orphaned nodes … +289 lines (ctrl+o to expand)

⏺ Bash(cd docs/learning-graph && chmod +x analyze-graph.py && python analyze-graph.py learning-graph.csv quality-metrics.md) ⎿  Quality report written to quality-metrics.md Quality Score: 90/100 (Excellent)

⏺ Read(quality-metrics.md) ⎿  Read 99 lines

⏺ Write(concept-taxonomy.md) ⎿  Wrote 111 lines to concept-taxonomy.md
# Concept Taxonomy for Modeling Healthcare Data with Graphs This document defines the categorical taxonomy for organizing the 200 concepts in the learning graph. Each category has a TaxonomyID (3-5 letter abbreviation) and a description of the concepts it contains. ## Taxonomy Categories ### 1. Foundation Concepts TaxonomyID: FOUND Description: Fundamental concepts in graph theory and database systems that serve as prerequisites for understanding healthcare graph modeling. Includes basic graph structures, database concepts, and data modeling principles. … +101 lines (ctrl+o to expand)

⏺ Write(add-taxonomy.py) ⎿  Wrote 72 lines to add-taxonomy.py
#!/usr/bin/env python3 """ Add Taxonomy IDs to Learning Graph CSV This script reads the learning-graph.csv file and adds a TaxonomyID column based on concept ranges. """ import csv … +62 lines (ctrl+o to expand)

⏺ Bash(cd docs/learning-graph && python add-taxonomy.py) ⎿  Error: Exit code 1 (eval):cd:1: no such file or directory: docs/learning-graph

⏺ Bash(python docs/learning-graph/add-taxonomy.py) ⎿  Error: Exit code 2 python: can't open file '/Users/dan/Documents/ws/modeling-healthcare-data/docs/learning-graph/docs/learning-graph/add-taxonomy.py': [Errno 2] No such file or directory

⏺ Bash(pwd && ls -la docs/learning-graph/.py) ⎿  Error: Exit code 1 (eval):1: no matches found: docs/learning-graph/.py

1
 /Users/dan/Documents/ws/modeling-healthcare-data/docs/learning-graph

⏺ Bash(ls -la) ⎿  total 96
drwxr-xr-x 9 dan staff 288 Nov 6 12:59 . drwxr-xr-x 18 dan staff 576 Nov 6 12:53 .. … +7 lines (ctrl+o to expand)

⏺ Bash(python add-taxonomy.py) ⎿  Updated CSV written to learning-graph.csv Added TaxonomyID to 200 concepts

⏺ Write(metadata.json) ⎿  Wrote 11 lines to metadata.json
{ "title": "Modeling Healthcare Data with Graphs", "description": "This course teaches students to model complex healthcare data from multiple perspectives including the patient, provider and payer. Students learn how graph databases excel at modeling interconnected clinical data, and explore graph algorithms, graph data science, embeddings and graph neural networks to enable value-based care systems and reduce healthcare costs.", "creator": "Dan McCreary", "date": "2025-11-06", "version": "1.0", "format": "Learning Graph JSON v1.0", "schema": "https://raw.githubusercontent.com/dmccreary/learning-graphs/refs/heads/main/src/schema/learning-graph-schema.json", "license": "CC BY-NC-SA 4.0 DEED" } … +1 line (ctrl+o to expand)

⏺ Write(csv-to-json.py) ⎿  Wrote 153 lines to csv-to-json.py
#!/usr/bin/env python3 """ Convert Learning Graph CSV to JSON This script converts a learning graph CSV file (with taxonomy) to the complete JSON format required by vis-network.js visualizations. """ import csv import json … +143 lines (ctrl+o to expand)

⏺ Bash(python csv-to-json.py learning-graph.csv learning-graph.json metadata.json) ⎿  Learning graph JSON created successfully! Output file: learning-graph.json Total concepts: 200 … +2 lines (ctrl+o to expand)

⏺ Write(taxonomy-distribution.py) ⎿  Wrote 124 lines to taxonomy-distribution.py
#!/usr/bin/env python3 """ Generate Taxonomy Distribution Report This script analyzes the distribution of concepts across taxonomy categories and generates a markdown report. """ import csv import sys … +114 lines (ctrl+o to expand)

⏺ Bash(python taxonomy-distribution.py learning-graph.csv taxonomy-distribution.md) ⎿  Taxonomy distribution report written to taxonomy-distribution.md

⏺ Read(taxonomy-distribution.md) ⎿  Read 44 lines

⏺ Write(index.md) ⎿  Wrote 176 lines to index.md
# Learning Graph ## Introduction Welcome to the learning graph for Modeling Healthcare Data with Graphs. This section contains comprehensive documentation of the learning graph that underpins this intelligent textbook. A learning graph is a directed acyclic graph (DAG) that maps out the conceptual dependencies and relationships between topics in a course. It serves as the foundation for personalized learning pathways and adaptive content delivery. ## What is a Learning Graph? … +166 lines (ctrl+o to expand)

⏺ Read(~/Documents/ws/modeling-healthcare-data/mkdocs.yml) ⎿  Read 69 lines

⏺ Update(~/Documents/ws/modeling-healthcare-data/mkdocs.yml) ⎿  Updated ../../mkdocs.yml with 8 additions
11 - About: about.md 12 - Course Description: course-description.md 13
14 + - Learning Graph: 15 + - Introduction: learning-graph/index.md 16 + - Course Description Assessment: learning-graph/course-description-assessment.md 17 + - Concept List: learning-graph/concept-list.md 18 + - Quality Metrics: learning-graph/quality-metrics.md 19 + - Concept Taxonomy: learning-graph/concept-taxonomy.md 20 + - Taxonomy Distribution: learning-graph/taxonomy-distribution.md 21 +
22 - MicroSims: 23 - Introduction: sims/index.md 24 - Codes: sims/codes/index.md

⏺ Learning Graph Generation Complete!

Congratulations! I've successfully generated a comprehensive learning graph for your course "Modeling Healthcare Data with Graphs". Here's what was accomplished:

Files Created

All files are located in docs/learning-graph/:

  1. course-description-assessment.md - Quality assessment (100/100 score)
  2. concept-list.md - 200 concepts organized by category
  3. learning-graph.csv - Core dependency graph with taxonomy
  4. learning-graph.json - Complete JSON for visualization (vis-network.js format)
  5. metadata.json - Course metadata
  6. concept-taxonomy.md - 13 taxonomy category definitions
  7. quality-metrics.md - Quality validation report (90/100 - Excellent)
  8. taxonomy-distribution.md - Category distribution analysis
  9. index.md - Introduction and documentation page

Python Tools Created

  1. analyze-graph.py - Quality validation tool
  2. add-taxonomy.py - Taxonomy assignment tool
  3. csv-to-json.py - CSV to JSON converter
  4. taxonomy-distribution.py - Distribution analysis tool

Key Statistics

  • Total Concepts: 200
  • Dependencies: 299 prerequisite relationships
  • Taxonomy Categories: 13 well-balanced categories
  • Foundational Concepts: 4 (Graph Theory Basics, Relational Database, Healthcare System, Artificial Intelligence)
  • Quality Score: 90/100 (Excellent)
  • Max Dependency Chain: 11 levels
  • Average Dependencies: 1.50 per concept

Quality Highlights

✓ Valid DAG structure (no circular dependencies) ✓ No self-dependencies ✓ Well-balanced taxonomy distribution ✓ Comprehensive coverage of all course topics ✓ Multiple learning pathways supported

Taxonomy Categories

  1. Foundation Concepts (FOUND) - 15 concepts
  2. Graph Technologies (GTECH) - 10 concepts
  3. Healthcare Domain (HCARE) - 20 concepts
  4. Patient Data (PAT) - 25 concepts
  5. Provider Operations (PROV) - 25 concepts
  6. Payer & Insurance (PAYER) - 20 concepts
  7. Financial & Business (FIN) - 15 concepts
  8. Fraud & Compliance (FRAUD) - 15 concepts
  9. Graph Analytics (ANAL) - 15 concepts
  10. AI & Machine Learning (AI) - 15 concepts
  11. Security & Privacy (SEC) - 10 concepts
  12. Data Governance (GOV) - 10 concepts
  13. Capstone & Career (CAP) - 5 concepts

Next Steps

You can now:

  1. View the learning graph in your MkDocs site (navigation updated)
  2. Install the Learning Graph Viewer skill for interactive visualization
  3. Generate chapter structure using the book-chapter-generator skill
  4. Create a glossary using the glossary-generator skill
  5. Build quizzes using the quiz-generator skill

The learning graph is production-ready and provides an excellent foundation for building intelligent, adaptive educational content!