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 into a persistent knowledge graph with community detection, so questions about architecture, file relationships, and cross-document connections can be answered by querying the graph instead of re-reading everything. ## Core Features & Use Cases - Knowledge graph extraction: Combines deterministic AST parsing for code with LLM-based semantic extraction for docs, papers, and images, producing nodes and edges tagged EXTRACTED, INFERRED, or AMBIGUOUS for an honest audit trail. - Query, path, and explain tools: Ask natural-language questions with BFS/DFS traversal, find shortest paths between two concepts, or get plain-language explanations of any node. - Multiple outputs and integrations: Generates interactive HTML visualization, GraphRAG-ready JSON, GRAPH_REPORT.md, plus exports to Neo4j, FalkorDB, GraphML, SVG, Obsidian vaults, and an MCP server. - Incremental updates and automation: Supports --update for changed files only, --watch for auto-rebuilds, a git post-commit hook, and video/audio transcription via Whisper. - Use Case: Point it at a monorepo or several GitHub URLs, then ask "How does the auth flow reach the database?" and get an answer traced through the merged cross-repo graph with source citations. ## Quick Start Run /graphify on the current directory to build the knowledge graph, then ask any question about the codebase to query it.
