graphify

Build a knowledge graph from codebases and documents with AST and semantic extraction.

1|1|Updated May 3, 2026
One-click install
npx skills add https://github.com/matt-riley/agent-skills --skill graphify-matt-riley
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: graphify
Source: https://github.com/matt-riley/agent-skills/tree/main/skills/graphify
Command: npx skills add https://github.com/matt-riley/agent-skills --skill graphify-matt-riley

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill automates turning a folder of code and related documents into a persistent knowledge graph, enabling quick exploration of code structure, architecture, and cross-file relationships with an auditable trail.

Core Features & Use Cases

  • Deterministic AST extraction for code files and semantic extraction for documents to build a connected graph of nodes and edges.
  • Outputs include an interactive HTML visualization, GraphRAG-ready JSON, and a readable GRAPH_REPORT.md for audits.
  • Use cases include codebase exploration, architecture analysis, and dependency tracing across repositories.

Quick Start

Invoke the graphify workflow from the repository root to build a graph for a local folder or GitHub URL.

Frequently Asked Questions about graphify

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

FAQPage Schema
How do I turn a codebase into a navigable knowledge graph?

To turn a codebase into a navigable knowledge graph, you can automate codebase exploration by extracting AST code structures and document semantics to generate interactive HTML visualizations and JSON graph data.

What is the best way to analyze codebase architecture and cross-file dependencies?

Analyzing codebase architecture and cross-file dependencies is best handled by building a persistent knowledge graph that maps code structure and relationships, producing a readable audit report for architecture analysis.

Can I generate GraphRAG-ready JSON data from my source code and documents?

You can generate GraphRAG-ready JSON data from source code and documents by performing deterministic AST extraction and LLM-based semantic extraction to build connected graph nodes and edges.

Does building a codebase knowledge graph work with local folders and GitHub repositories?

Building a codebase knowledge graph works with both local folders and GitHub repositories, allowing you to invoke the workflow from the repository root to extract code and document relationships.

What outputs can I expect from automated codebase architecture analysis?

Outputs from automated codebase architecture analysis include an interactive HTML visualization for exploration, GraphRAG-ready JSON for downstream processing, and a GRAPH_REPORT.md for auditing code structure.