graphify

Analyze a directory of files and extract cross-file relationships into a knowledge graph.

3|Updated Nov 15, 2015
One-click install
npx skills add https://github.com/itsdaiego/dotfiles --skill graphify-itsdaiego
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: graphify
Source: https://github.com/itsdaiego/dotfiles/tree/main/.claude/skills/graphify
Command: npx skills add https://github.com/itsdaiego/dotfiles --skill graphify-itsdaiego

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

graphify helps you turn any folder of files into a structured, navigable knowledge graph with clustering, an audit trail, and a multi-output workflow (HTML, JSON, and a readable report).

Core Features & Use Cases

  • Persistent graph: stores relationships across sessions in graphify-out/graph.json.
  • Honest audit trail: edges are tagged EXTRACTED, INFERRED, or AMBIGUOUS for traceability.
  • Cross-document connectivity: discovers connections across code, docs, papers, and images to reveal hidden relationships.
  • Outputs: HTML visualization, GraphRAG-ready JSON, and a plain-language GRAPH_REPORT.md.

Quick Start

Run graphify on a directory to generate a navigable knowledge graph and a comprehensive report.

Frequently Asked Questions about graphify

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

FAQPage Schema
How do I build a knowledge graph from a directory of code and documents?

You can build a knowledge graph by analyzing a directory of code, docs, and media to extract cross-file relationships. The process outputs an HTML visualization, GraphRAG-ready JSON, and a readable report for exploration.

What is the best way to visualize cross-file relationships in a codebase?

Visualizing cross-file relationships involves extracting connections across code, docs, and media into an HTML output. This reveals hidden relationships and provides a navigable format for exploring the corpus.

How does an audit trail work for inferred relationships in a knowledge graph?

An audit trail for inferred relationships works by annotating graph edges as EXTRACTED, INFERRED, or AMBIGUOUS. This preserves provenance and ensures reproducibility by clearly identifying the origin of each connection.

Can I generate GraphRAG-ready JSON from a folder of mixed file types?

Yes, you can generate GraphRAG-ready JSON from a folder of mixed code, docs, and media. The analysis discovers cross-document connectivity and outputs structured JSON alongside an HTML visualization and a markdown report.

Does graphify require any external dependencies to analyze code and documents?

No, graphify does not require any external dependencies to analyze code and documents. It operates independently to extract cross-file relationships and generate its HTML, JSON, and markdown report outputs.

Why are some edges in my generated graph marked as AMBIGUOUS?

Edges in a generated graph are marked as AMBIGUOUS to indicate that the relationship between files could not be definitively extracted or inferred. This tagging preserves provenance and enables reproducibility during cross-reference discovery.