graphify

Converts a folder of files into a knowledge graph with HTML, JSON, and report outputs.

Updated Nov 16, 2022
One-click install
npx skills add https://github.com/kos3nz/dotfiles --skill graphify-kos3nz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: graphify
Source: https://github.com/kos3nz/dotfiles/tree/main/.config/agents/skills/graphify
Command: npx skills add https://github.com/kos3nz/dotfiles --skill graphify-kos3nz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Turn any folder of files (code, docs, papers, images) into a navigable knowledge graph with an honest audit trail and ready-made outputs (interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPH_REPORT.md).

Core Features & Use Cases

  • Persistent graph: relationships survive across sessions via graphify-out/graph.json.
  • Honest audit trail: every edge is labeled EXTRACTED, INFERRED, or AMBIGUOUS to show evidence.
  • Cross-document connections: community detection reveals connections across files in different formats.
  • Use cases: understand unfamiliar codebases, organize reading lists, or structure a personal raw-folder corpus.

Quick Start

Drop any folder into graphify and run the CLI on that path to generate a graph, an HTML/JSON output, and an audit report.

Frequently Asked Questions about graphify

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

FAQPage Schema
How do I turn a folder of code and documents into a knowledge graph?

To turn a folder into a knowledge graph, run the CLI on your target path to detect files, extract cross-document relationships, and generate interactive HTML, GraphRAG-ready JSON, and a plain-language report.

What is an audit trail in a knowledge graph and why does it matter?

An audit trail in a knowledge graph labels every edge as EXTRACTED, INFERRED, or AMBIGUOUS to show evidence. This transparency matters because it reveals the confidence level behind cross-document connections and inferred concepts.

Can I generate a knowledge graph from mixed file formats like code, papers, and images?

Yes, you can generate a knowledge graph from mixed file formats. The tool detects files across code, docs, papers, and images, running deterministic and semantic extraction to reveal cross-format community connections.

How do I keep knowledge graph relationships persistent across different sessions?

To keep knowledge graph relationships persistent across sessions, the tool saves discovered connections to a graph.json file in the output directory, ensuring your extracted and inferred data survives for later exploration.

What is the best way to understand an unfamiliar codebase using a knowledge graph?

The best way to understand an unfamiliar codebase using a knowledge graph is to run extraction on the folder to discover cross-document relationships, cluster concepts, and review the generated plain-language report for navigable insights.

Does graphify require external dependencies to process files for data discovery?

No, graphify does not require external dependencies to process files for data discovery. It operates independently to load paths, detect files, and run deterministic and semantic extraction for your folder corpus.