graphify

Converts code, docs, papers, and media into a persistent knowledge graph with community detection.

Updated Aug 22, 2026
One-click install
npx skills add https://github.com/MSC72m/DevForge --skill graphify-msc72m
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: graphify
Source: https://github.com/MSC72m/DevForge/tree/main/skills/graphify
Command: npx skills add https://github.com/MSC72m/DevForge --skill graphify-msc72m

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires graphifyy.

What problem does it solve? Understanding a new codebase, research corpus, or mixed folder of notes requires re-reading everything each session, and hidden cross-document connections stay invisible. graphify builds a persistent, queryable knowledge graph from any folder so relationships survive across sessions and every edge carries an honest EXTRACTED, INFERRED, or AMBIGUOUS audit tag. ## Core Features & Use Cases - Multi-format extraction: Combines deterministic AST parsing for code with LLM-based semantic extraction for docs, papers, images, and Whisper-transcribed video/audio. - Community detection and analysis: Clusters the graph, identifies god nodes and surprising cross-document connections, and generates a plain-language GRAPH_REPORT.md. - Multiple outputs and query modes: Produces interactive HTML, GraphRAG-ready JSON, Obsidian vaults, SVG/GraphML exports, Neo4j push, an MCP server, and BFS/DFS natural-language queries with token budgets. - Use Case: Point it at an unfamiliar repository to get an architecture graph, labeled communities, and suggested questions before touching any code, then run incremental --update runs as the code changes. ## Quick Start Ask the agent to run /graphify on the current project directory to generate an interactive HTML knowledge graph and audit report in graphify-out/.

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 a codebase?▼

Run /graphify on the target directory. It detects files, runs AST extraction on code and semantic extraction on docs, then clusters the graph and writes graph.html, graph.json, and GRAPH_REPORT.md into graphify-out/.

What file types does graphify support for graph extraction?▼

It supports code files via AST parsing, docs and papers such as Markdown, text, and PDF, images via vision, and video or audio files which are first transcribed with Whisper and treated as documents.

Can I update the graph incrementally when files change?▼

Yes. The --update flag re-extracts only new or changed files using a saved manifest, and a semantic cache avoids reprocessing unchanged files. A --watch mode auto-rebuilds on code changes without LLM calls.

Does graphify work with Neo4j or Obsidian?▼

Yes. The --neo4j flag generates a Cypher import file and --neo4j-push writes directly to a running Neo4j instance using MERGE. The --obsidian flag generates an Obsidian vault with a canvas file and community overview notes.

Why did graphify report an empty graph error?▼

An empty graph means extraction produced no nodes, typically because all files were skipped, the corpus contains only unsupported binaries, or extraction failed. Check that the path contains supported file types and rerun.

What are the limitations of graphify HTML visualization?▼

Graphs with more than 5,000 nodes are too large for the HTML visualizer, so the skill directs you to the Obsidian vault output instead. Very large corpora over 200 files or 2 million words require selecting a subfolder first.