graphifylisted

Use for any question about a codebase, its architecture, file relationships, or project content - especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.
vanducng/skills · ★ 7 · AI & Automation · score 81

Install: claude install-skill vanducng/skills

# /graphify Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPH_REPORT.md. ## Usage ``` /graphify # full pipeline on current directory /graphify <path> # full pipeline on specific path /graphify https://github.com/<owner>/<repo> [--branch <branch>] # clone repo, then build (multiple URLs merge into one cross-repo graph) /graphify <path> --mode deep # thorough extraction, richer INFERRED edges /graphify <path> --update # incremental - re-extract only new/changed files /graphify <path> --directed # build directed graph (preserves edge direction: source→target) /graphify <path> --cluster-only # rerun clustering on existing graph /graphify <path> --no-viz # skip visualization, just report + JSON /graphify <path> --obsidian [--obsidian-dir <vault>] # also write an Obsidian vault /graphify <path> --wiki | --svg | --graphml | --neo4j | --falkordb | --mcp # extra exports - see references/exports.md /graphify add <url> [--author "Name" | --contributor "Name"] # fetch URL into ./raw, update graph /graphify query "<question>" [--dfs | --budget N] # BFS/DFS traversal over the built graph /graphify path "A" "B"