skills.rest
JongDeug
JongDeugCOMMUNITY
Explore all skills by this author →
GitHub

graphify

Converts code, docs, papers, images, and videos into a queryable knowledge graph with community detection.

Updated Mar 19, 2026
Search Tags:#knowledge graph#mcp#codebase analysis#code extraction#neo4j#community detection#graph rag
One-click install
npx skills add https://github.com/JongDeug/dotfiles --skill graphify-jongdeug
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: graphify
Source: https://github.com/JongDeug/dotfiles/tree/main/ai/claude/skills/graphify
Command: npx skills add https://github.com/JongDeug/dotfiles --skill graphify-jongdeug

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Understanding a large codebase or mixed corpus of documents requires reading hundreds of files manually. This Skill turns any folder of code, docs, papers, images, or videos into a persistent knowledge graph with community detection, so you can ask natural-language questions, trace dependency paths, and get plain-language explanations instead of reading everything yourself. ## Core Features & Use Cases - Knowledge Graph Construction: Extracts entities and relationships from code (AST-based, no LLM needed) and from docs/papers/images (semantic extraction), producing graph.json, an interactive HTML visualization, and a plain-language GRAPH_REPORT.md. - Graph Querying: Answers questions about the codebase via BFS/DFS traversal, finds shortest paths between two concepts, and explains individual nodes with source citations. - Incremental Updates & Exports: Supports --update for re-extracting only changed files, --watch for auto-rebuilds, and exports to Neo4j, FalkorDB, GraphML, SVG, Obsidian vaults, wikis, and an MCP server. - Use Case: Point it at a unfamiliar repository (or a GitHub URL) and ask "How does authentication flow through this system?" — it builds the graph once, then answers from the graph without re-reading the code. ## Quick Start Ask the assistant to run /graphify on the current directory to build a knowledge graph, then ask any question about how the codebase works.

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 parsing and document concepts via semantic extraction, then clusters the graph and outputs graph.json, an HTML visualization, and a GRAPH_REPORT.md summary.

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

Once graphify-out/graph.json exists, run graphify query with your question. It expands the query against the graph's vocabulary, runs BFS traversal by default (or DFS with --dfs to trace a path), and answers using only what the graph contains.

Does graphify require an API key to run?▼

No API key is required. Code is extracted structurally via AST with no LLM. Semantic extraction for docs, papers, and images uses Gemini only if GEMINI_API_KEY or GOOGLE_API_KEY is already set; otherwise the host agent itself performs the extraction.

Can graphify export to Neo4j or other graph databases?▼

Yes. Use --neo4j to generate a Cypher file or --neo4j-push to push directly to a running Neo4j instance. FalkorDB, GraphML, SVG, Obsidian vault, wiki, and MCP server exports are also supported via corresponding flags.

How do I update the graph after changing only a few files?▼

Run /graphify <path> --update. It detects new, changed, and deleted files, re-extracts only what changed (skipping the LLM entirely for code-only changes), merges into the existing graph, and prunes nodes from deleted files.

Why does graphify query return no matching nodes?▼

The query matcher uses case-folded substring matching with no stemming or synonyms. If your wording differs from the graph's labels, the constrained query expansion step maps your question to tokens that actually exist in the graph vocabulary before traversing.

Related Skills

Explore More Software Engineering Skills→
usadamasausadamasa

ghq-lookup

Prioritize local ghq clones for repository URLs before remote fetching.

Community
Intermediate
Michael1PengMichael1Peng

wiki-export

Export Obsidian wiki wikilink graphs to JSON, GraphML, Cypher, and HTML.

Community
Intermediate
ceratops-codeceratops-code

ceratops-gh-codex-skill-ship

Ship staged Ceratops skill batches from runtime checkout to GitHub and restore main.

Official
Intermediate
mgreenlymgreenly

ctags

Generate a ctags tags file for symbol lookup across multi-language codebases.

Community
Basic