graphify

Convert code, documents, and media into a navigable knowledge graph.

4|1|Updated Mar 22, 2026
One-click install
npx skills add https://github.com/lgwanai/openforce --skill graphify-lgwanai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: graphify
Source: https://github.com/lgwanai/openforce/tree/main/skills/graphify
Command: npx skills add https://github.com/lgwanai/openforce --skill graphify-lgwanai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Graphify transforms messy, unstructured project folders (code, docs, papers, and media) into a navigable knowledge graph so you can ask questions and trace relationships across a codebase with an honest audit trail.

Core Features & Use Cases

  • Knowledge graph extraction across file types: Builds entities and relationships from code structure (AST) and semantic content from documents and papers.
  • Honest provenance & confidence: Labels edges as EXTRACTED, INFERRED, or AMBIGUOUS to make uncertainty visible instead of hidden.
  • Multiple outputs for different workflows: Produces interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPH_REPORT.md for humans.
  • Scalable graph building for repos and paths: Supports local paths, GitHub URLs (including multi-repo merge), clustering, directed graphs, and incremental updates.

Quick Start

Use the graphify skill to build a knowledge graph from the current directory and enable subsequent graph queries.

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 queryable knowledge graph?

To turn a codebase into a knowledge graph, you can convert folders of code, documents, and media into a navigable graph using fast deterministic AST extraction and semantic extraction. This creates an interactive structure for tracing concept relationships and querying project content.

What is the best way to trace concept relationships across a repository?

Tracing concept relationships across a repository requires building a knowledge graph that labels edges as EXTRACTED, INFERRED, or AMBIGUOUS. This confidence-labeled approach makes uncertainty visible, providing an honest audit trail for navigating complex project dependencies.

Can I generate GraphRAG-ready JSON from local project folders?

Yes, you can generate GraphRAG-ready JSON from local project folders by ingesting the repository and applying semantic extraction. The process exports structured graph artifacts alongside interactive HTML and a plain-language GRAPH_REPORT.md for human review.

Does graph ingestion support multi-repo merging and incremental updates?

Graph ingestion supports multi-repo merging from GitHub URLs alongside local paths, featuring clustering and directed graphs. It handles scalable graph building by reusing cached graph artifacts when available to apply incremental updates efficiently.

How does knowledge graph extraction handle mixed file types like code and papers?

Knowledge graph extraction handles mixed file types by applying fast deterministic AST extraction for code structure and semantic extraction for documents and papers. This unified approach builds entities and relationships from diverse project content into a single navigable graph.