graphify

Generate knowledge graphs from code, docs, papers, and images with auditable edges.

58|17|Updated Apr 10, 2026
One-click install
npx skills add https://github.com/TtTRz/graphify-rs --skill graphify
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: graphify
Source: https://github.com/TtTRz/graphify-rs/tree/main
Command: npx skills add https://github.com/TtTRz/graphify-rs --skill graphify

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

graphify-rs transforms diverse inputs (code, docs, papers, and images) into a structured, queryable knowledge graph with an auditable edge trail and multi-format exports.

Core Features & Use Cases

  • Create a unified graph from mixed sources, revealing cross-document connections and community structure.
  • Export interactive HTML visuals, a graph-data JSON, and a plain-language GRAPH_REPORT.md for auditing and insights.
  • Use case: understand a large codebase alongside referenced docs and papers to surface hidden dependencies and design rationales.

Quick Start

Run graphify-rs build on a folder to generate the graph outputs.

Frequently Asked Questions about graphify

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

FAQPage Schema
How do I generate a knowledge graph from code and documents?

Generate a knowledge graph from mixed sources by running an end-to-end pipeline that extracts AST data, applies optional semantic extraction, and builds graph clusters. This reveals cross-document connections and outputs interactive HTML visuals alongside a graph-data JSON.

What is the best way to visualize cross-document connections in a large codebase?

The best way to visualize cross-document connections is to build a unified knowledge graph that clusters related files and exports interactive HTML visuals. This approach surfaces hidden dependencies between code, referenced docs, and design papers.

Can I create a navigable graph from mixed datasets containing images and papers?

Yes, you can create a navigable graph from mixed datasets containing images and papers. The pipeline detects diverse inputs, applies deterministic extraction, and builds an auditable graph with multi-format exports including a plain-language audit report.

How does community detection work for software project analysis?

Community detection for software project analysis works by clustering nodes within the generated knowledge graph to reveal structural communities. This uncovers hidden dependencies and design rationales across code and referenced documentation.

Does the knowledge graph export include an auditable edge trail?

Yes, the knowledge graph export includes an auditable edge trail. It generates a plain-language GRAPH_REPORT.md for auditing insights and a graph-data JSON that maps the deterministic connections extracted from your source inputs.