claudegoodies
Skill

graphify

From Graphify-Labs

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.

Builds a persistent, queryable knowledge graph from a folder, repo, or URLs with community detection and audit trails.

Use it when

  • Asking questions about a codebase's architecture or file relationships
  • Need cross-repo or cross-document connections surfaced automatically
  • Want exports to Neo4j, FalkorDB, GraphML, SVG, Obsidian, or GraphRAG JSON
  • Tracking incremental changes to a large corpus over time (--update)

Skip it if

  • Requires Python interpreter detection/install (uv, pipx, venv) as first step
  • Video/audio transcription needs a Whisper model, adds heavy dependency
  • Overkill for a small codebase you can just read directly

Facts

Repository
Graphify-Labs/graphify
Status
Actively maintained
Last commit
Source file
graphify/skill.md

Source preview

The instructions Claude Code reads when this skill runs.

# /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 (HTML viz; add --obsidian for a vault)
/graphify <path>                                      # full pipeline on specific path
/graphify https://github.com/<owner>/<repo>           # clone repo then run full pipeline on it
/graphify https://github.com/<owner>/<repo> --branch <branch>  # clone a specific branch
/graphify <url1> <url2> ...                           # clone multiple repos, build each, 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> --whisper-model medium                # use a larger Whisper model for better transcription accuracy
/graphify <path> --cluster-only                       # rerun clustering on existing graph
/graphify <path> --no-viz                             # skip visualization, just report + JSON
/graphify <path> -
View full source on GitHub →

Other skills