graph-navigator

Build and traverse SDLC knowledge graphs from decisions, learnings, and patterns.

3|Updated Jan 12, 2026
One-click install
npx skills add https://github.com/arbgjr/sdlc_agentico --skill graph-navigator
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: graph-navigator
Source: https://github.com/arbgjr/sdlc_agentico/tree/main/.claude/skills/graph-navigator
Command: npx skills add https://github.com/arbgjr/sdlc_agentico --skill graph-navigator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) components.

What problem does it solve?

Graph Navigator provides a centralized way to model and explore the SDLC knowledge graph built from decisions, learnings, patterns, and concepts across the corpus, enabling clear understanding and governance of software lifecycle knowledge.

Core Features & Use Cases

  • Build and maintain the semantic graph from corpus documents (decisions, learnings, patterns)
  • Navigate relationships, discover related concepts, and perform path and transitive-closure analyses
  • Generate visualizations in Mermaid and DOT formats for knowledge maps and impact analysis
  • Support incremental updates and comprehensive graph exploration with a script suite (graph_builder.py, concept_extractor.py, graph_visualizer.py)

Quick Start

Rebuild the graph with the provided scripts and generate a Mermaid diagram to visualize the current graph.

Frequently Asked Questions about graph-navigator

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

FAQPage Schema
How do I visualize an SDLC knowledge graph from decisions and learnings?

Visualizing an SDLC knowledge graph from decisions and learnings involves building a semantic graph from corpus documents and generating Mermaid or DOT diagrams for clear knowledge maps.

What is a transitive closure analysis for software lifecycle artifacts?

Transitive closure analysis for software lifecycle artifacts is a graph traversal technique that discovers all reachable concepts and relationships across decisions, learnings, and patterns to perform comprehensive impact analysis.

How do I generate Mermaid or DOT diagrams for impact analysis?

You generate Mermaid or DOT diagrams for impact analysis by traversing the knowledge graph and performing path searches across SDLC artifacts, which produces visual relationship maps for understanding dependencies.

Does this graph visualization approach require external graph database dependencies?

No, this graph visualization approach does not require external graph database dependencies, as the script suite coordinates graph construction, concept extraction, and visualization while requiring only the PyYAML library.

Can I perform incremental updates to a knowledge graph built from corpus documents?

Yes, you can perform incremental updates to a knowledge graph built from corpus documents, as the graph builder supports comprehensive exploration and maintenance of decisions, learnings, and patterns over time.

What's the best way to extract concepts from software engineering decisions and patterns?

The best way to extract concepts from software engineering decisions and patterns is to use an automated concept extraction script that models relationships and builds a semantic graph for governance of lifecycle knowledge.