skills.rest
TarunTeja44
TarunTeja44COMMUNITY
Explore all skills by this author →
GitHub

graphify

Builds a queryable knowledge graph from code, docs, papers, images, and video.

1|Updated Feb 22, 2026
Search Tags:#knowledge graph#codebase analysis#neo4j#graphrag#code visualization#community detection#ast extraction
One-click install
npx skills add https://github.com/TarunTeja44/portfolio --skill graphify-tarunteja44
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: graphify
Source: https://github.com/TarunTeja44/portfolio/tree/main/.agents/skills/graphify
Command: npx skills add https://github.com/TarunTeja44/portfolio --skill graphify-tarunteja44

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires graphifyy, networkx, and includes references (resource) components.

What problem does it solve? Understanding a large codebase or mixed document corpus requires reading hundreds of files manually. This Skill turns any folder into a persistent knowledge graph with community detection and an honest audit trail, so questions about architecture, file relationships, and cross-document connections can be answered by graph traversal instead of re-reading source files. ## Core Features & Use Cases - Knowledge graph construction: Extracts entities and relationships from code (AST-based, no LLM needed), docs, papers, images, and transcribed video, then clusters them into labeled communities with god-node and surprising-connection analysis. - Query, path, and explain tools: Answers natural-language questions via BFS/DFS traversal, finds shortest paths between concepts, and explains individual nodes with source citations. - Multiple outputs and integrations: Generates interactive HTML visualization, GraphRAG-ready JSON, GRAPH_REPORT.md, Obsidian vaults, wikis, and exports to Neo4j, FalkorDB, SVG, GraphML, or an MCP server. - Use Case: Point it at a repository (local path or GitHub URL) to produce a cross-repo graph, then ask "How does authentication reach the database?" and get a cited traversal answer without re-extracting anything. ## Quick Start Run /graphify on the current directory to build the knowledge graph, then ask any codebase question to query it.

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 a local path or GitHub URL. It detects files, extracts code structure via AST and semantics from docs via subagents, then clusters the graph and writes graph.json, an HTML visualization, and GRAPH_REPORT.md to graphify-out/.

How do I query a codebase knowledge graph with natural language?▼

Once graphify-out/graph.json exists, run graphify query "your question" for BFS traversal, graphify path "A" "B" for shortest paths, or graphify explain "Node" for a plain-language summary. Answers cite source files and are saved back into the graph.

Does graphify require an API key?▼

No. Code extraction is AST-based and needs no key. Semantic extraction for docs, papers, and images uses Gemini only if GEMINI_API_KEY or GOOGLE_API_KEY is set; otherwise the host agent itself performs extraction.

Can graphify export to Neo4j or other graph databases?▼

Yes. Use --neo4j to generate a Cypher file or --neo4j-push to load a running Neo4j instance. FalkorDB, GraphML, SVG, Obsidian vaults, and an MCP stdio server are also supported via export flags.

How does incremental update work when files change?▼

Run /graphify --update to re-extract only new or changed files and prune deleted ones, merging into the existing graph. A post-commit hook or --watch mode can automate rebuilds for code-only changes without an LLM.

What are the limitations of graphify on very large corpora?▼

Corpora over 2 million words or 500 files trigger a warning and prompt narrowing to a subfolder. Semantic extraction cost scales with document count, though caching and code-only fast paths reduce repeat work.

Related Skills

Explore More Software Engineering Skills→
TairitsuaTairitsua
13

third-party-source-catalog

Catalog and fetch third-party library source trees from GitHub repositories and local folders.

Community
Advanced
CoderCoco-StudiosCoderCoco-Studios
1

graphify

Builds a queryable knowledge graph from code, docs, papers, images, and video with community detection.

Official
Advanced
phraphra

code-review

Review modified code files and auto-fix mechanical issues.

Community
Advanced
jhl-labsjhl-labs
50

RAG & Vector Search

Retrieve relevant documents and augment LLM prompts with vector search.

Official
Advanced