# Graphify

> any input (code, docs, papers, images) → knowledge graph → clustered communities → HTML + JSON + audit report. Use when user asks any question about a codebase, project content, architecture, or file relationships — especially if graphify-out/ exists. Provides persistent graph with god nodes, community detection, and BFS/DFS query tools.

- Skill: `presidenteog/graphify` (Agent Skill, multi-file: 6 files)
- Install (CLI): `npx skillmds@latest add presidenteog/graphify`
- Raw SKILL.md: https://api.skillmd.com/api/skills/presidenteog/graphify/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Web & Frontend
- Author: PresidenteOG (https://skillmd.com/u/presidenteog)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/presidenteog/graphify

---


# /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 → Obsidian vault
/graphify <path>                                      # full pipeline on specific path
/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> --html                               # (HTML is generated by default - this flag is a no-op)
/graphify <path> --svg                                # also export graph.svg (embeds in Notion, GitHub)
/graphify <path> --graphml                            # export graph.graphml (Gephi, yEd)
/graphify <path> --neo4j                              # generate graphify-out/cypher.txt for Neo4j
/graphify <path> --neo4j-push bolt://localhost:7687   # push directly to Neo4j
/graphify <path> --wiki                               # build agent-crawlable wiki (index.md + one article per community)
/graphify <path> --obsidian --obsidian-dir ~/vaults/my-project  # write vault to custom path (e.g. existing vault)
/graphify <path> --mcp                                # start MCP stdio server for agent access
/graphify <path> --watch                              # watch folder, auto-rebuild on code changes (no LLM needed)
/graphify add <url>                                   # fetch URL, save to ./raw, update graph
/graphify add <url> --author "Name"                   # tag who wrote it
/graphify add <url> --contributor "Name"              # tag who added it to the corpus
/graphify query "<question>"                          # BFS traversal - broad context
/graphify query "<question>" --dfs                    # DFS - trace a specific path
/graphify query "<question>" --budget 1500            # cap answer at N tokens
/graphify path "AuthModule" "Database"                # shortest path between two concepts
/graphify explain "SwinTransformer"                   # plain-language explanation of a node
```

## What graphify is for

graphify is built around Andrej Karpathy's /raw folder workflow: drop anything into a folder - papers, tweets, screenshots, code, notes - and get a structured knowledge graph that shows you what you didn't know was connected.

Three things it does that your AI assistant alone cannot:
1. **Persistent graph** - relationships are stored in `graphify-out/graph.json` and survive across sessions. Ask questions weeks later without re-reading everything.
2. **Honest audit trail** - every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS. You know what was found vs invented.
3. **Cross-document surprise** - community detection finds connections between concepts in different files that you would never think to ask about directly.

Use it for: a codebase you're new to, a reading list, a research corpus, or a personal /raw folder.

## What You Must Do When Invoked

If the user invoked `/graphify --help` or `/graphify -h` (with no other arguments), print the contents of the `## Usage` section above verbatim and stop. Do not run any commands, do not detect files, do not default the path to `.`. Just print the Usage block and return.

If no path was given, use `.` (current directory). Do not ask the user for a path.

**Read ONLY the reference file for the invoked subcommand** (progressive disclosure — do not read the others):

| Invocation | Read | Contents |
|---|---|---|
| `/graphify [<path>]` + build flags (`--mode`, `--directed`, `--no-viz`, `--svg`, `--graphml`, `--neo4j*`, `--wiki`, `--obsidian*`, `--mcp`) | `references/build.md` | Full pipeline Steps 1-9: install check, file detection, video transcription, extraction, cluster/analyze, community labels, vault + HTML, exports, benchmark, manifest/report |
| `/graphify <path> --update` or `--cluster-only` | `references/incremental.md` | Incremental re-extraction (manifest diff, ghost pruning) and clustering re-runs |
| `/graphify query` / `path` / `explain` | `references/query.md` | BFS/DFS traversal, token-budget output, shortest path, node explanation |
| `/graphify add <url>`, `--watch`, git hook, native CLAUDE.md integration | `references/integrations.md` | URL ingestion, watch mode, commit hooks, CLAUDE.md wiring |

Follow the steps in the reference file in order. Do not skip steps.

## Troubleshooting

PowerShell 5.1 vertical scrolling breaks after a run → ANSI escape output from `graspologic` (suppressed in graphify v0.3.10+). Fixes: upgrade (`pip install --upgrade graphifyy`), use Windows Terminal, reopen the console, or `pip uninstall graspologic` (falls back to NetworkX Louvain, no ANSI).

## Honesty Rules

- Never invent an edge. If unsure, use AMBIGUOUS.
- Never skip the corpus check warning.
- Always show token cost in the report.
- Never hide cohesion scores behind symbols - show the raw number.
- Never run HTML viz on a graph with more than 5,000 nodes without warning the user.