What problem does it solve? Understanding a large codebase or document corpus requires reading hundreds of files manually. This Skill turns any folder of code, docs, papers, images, or videos into a navigable knowledge graph with community detection, so you can query concepts, trace relationships, and discover cross-document connections without reading everything. ## Core Features & Use Cases - Multi-format extraction: Combines deterministic AST parsing for code with LLM-based semantic extraction for docs, papers, and images, plus Whisper transcription for video and audio files. - Honest audit trail: Every edge is labeled EXTRACTED, INFERRED, or AMBIGUOUS with a confidence score, so you know what is fact versus inference. - Multiple outputs: Generates an interactive HTML visualization, GraphRAG-ready JSON, a plain-language GRAPH_REPORT.md, plus optional exports to GraphML, SVG, Neo4j, Obsidian vaults, and an agent-crawlable wiki. - Query and analysis: Supports BFS/DFS graph queries, shortest-path lookups between concepts, plain-language node explanations, community detection, and incremental updates on changed files. - Use Case: Point it at a GitHub repository URL to clone it, build a cross-repo knowledge graph, and ask questions like how the authentication module connects to the database layer. ## Quick Start Run /graphify on the current directory to build a knowledge graph and open the generated interactive HTML report.
