skills.rest
prabaljainn
prabaljainnCOMMUNITY
Explore all skills by this author →
𝕏@prabaljainnGitHub

graphify

Convert code, documents, papers, images, and videos into a persistent knowledge graph with community detection.

Updated Aug 17, 2026
Search Tags:#knowledge graph#obsidian#codebase analysis#neo4j#entity extraction#graphrag#community detection
One-click install
npx skills add https://github.com/prabaljainn/my-claude-code-setup --skill graphify-prabaljainn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: graphify
Source: https://github.com/prabaljainn/my-claude-code-setup/tree/main/claude/skills/graphify
Command: npx skills add https://github.com/prabaljainn/my-claude-code-setup --skill graphify-prabaljainn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires graphifyy.

What problem does it solve? Understanding a new codebase, research corpus, or mixed folder of notes requires reading everything manually, and insights disappear between sessions. graphify turns any folder into a persistent, queryable knowledge graph with an honest audit trail showing which relationships were extracted versus inferred. ## Core Features & Use Cases - Multi-format extraction: Parses code via AST, documents, papers, images (via vision), and transcribes video/audio with Whisper into a unified graph of nodes, edges, and hyperedges. - Persistent graph with audit trail: Stores results in graphify-out/graph.json with every edge tagged EXTRACTED, INFERRED, or AMBIGUOUS plus confidence scores, so queries work across sessions without re-reading files. - Community detection and outputs: Clusters the graph, labels communities, and generates an interactive HTML visualization, GraphRAG-ready JSON, GRAPH_REPORT.md, and optional Obsidian vault, Neo4j, GraphML, or SVG exports. - Use Case: Point it at an unfamiliar GitHub repository to get a navigable architecture graph with god nodes, surprising cross-file connections, and suggested questions before touching any code. ## Quick Start Run /graphify on the current directory to build a knowledge graph and open the generated report.

Frequently Asked Questions about graphify

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

FAQPage Schema
How do I build a knowledge graph from a codebase?▼

Run /graphify on the project directory or pass a GitHub URL to clone and process it. The pipeline runs AST extraction on code, dispatches parallel subagents for semantic extraction on docs, then clusters the merged graph and generates a report and interactive HTML.

What file types can be turned into a knowledge graph?▼

Code files, Markdown and text documents, PDF papers, images, and video or audio files are supported. Video and audio are first transcribed with Whisper, then treated as documents during extraction.

Can I query the knowledge graph after it is built?▼

Yes, the graph persists in graphify-out/graph.json across sessions. Use /graphify query for BFS or DFS traversal, /graphify path to find shortest paths between concepts, and /graphify explain for plain-language node explanations.

Does graphify support exporting to Neo4j or Obsidian?▼

Yes, it can generate a Cypher file or push directly to Neo4j via bolt, write an Obsidian vault with one note per community, and export GraphML for Gephi or SVG for embedding in Notion and GitHub.

Why did graphify produce an empty graph?▼

An empty graph means extraction produced no nodes, usually because all files were skipped, the corpus contains only unsupported binaries, or extraction subagents failed. Check that subagents run as general-purpose type so they can write chunk files to disk.

How do I update the graph when files change?▼

Run /graphify with the --update flag for incremental extraction of only new or changed files, using the semantic cache to skip unchanged content. The --watch flag monitors the folder and rebuilds automatically on code changes without an LLM.

Related Skills

Explore More Software Engineering Skills→
sxgsxg
1

context-ingestion

Validate project folders, clone GitHub repositories, and generate inventory.md.

Community
Intermediate
Abulfadl-AhmadiAbulfadl-Ahmadi

wiki-import

Imports knowledge graphs into an Obsidian vault from graph.json or OKF markdown.

Community
Advanced
AGM1968AGM1968

plan-agent

Audit Git commits to generate PLAN.md and enrich Weave graph nodes.

Community
Advanced
p-o-ke-naep-o-ke-nae

scripting-guide

Run C# file-based data processing scripts via dotnet run in PowerShell or Bash.

Community
Intermediate