跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
搜索与研究

graphify

Knowledge graph tool: '/graphify <path>' builds a graph, '/graphify query' searches existing graph, '/graphify path/explain' traces or explains nodes. Check the subcommand FIRST before responding.

kyopark2014 · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add kyopark2014/agent-wiki --skill graphify

技能说明


name: graphify description: "Knowledge graph tool: '/graphify ' builds a graph, '/graphify query' searches existing graph, '/graphify path/explain' traces or explains nodes. Check the subcommand FIRST before responding." trigger: /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> --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> --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> --mcp                                # start MCP stdio server for agent access
/graphify <path> --watch                              # watch folder, auto-rebuild on code changes (no LLM needed)
/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 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 Claude 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 (understand architecture before touching anything)
  • A reading list (papers + tweets + notes → one navigable graph)
  • A research corpus (citation graph + concept graph in one)
  • Your personal /raw folder (drop everything in, let it grow, query it)

What You Must Do When Invoked

CRITICAL - SUBCOMMAND DISPATCH: Before doing anything else, parse the user's command to identify the subcommand. Follow this table:

User's commandAction
/graphify query "..."Jump to "For /graphify query" section below. Do NOT run the full pipeline.
/graphify path "A" "B"Jump to "For /graphify path" section below. Do NOT run the full pipeline.
/graphify explain "..."Jump to "For /graphify explain" section below. Do NOT run the full pipeline.
/graphify add <url>Jump to "For /graphify add" section below. Do NOT run the full pipeline.
/graphify <path> --updateJump to "For --update" section below.
/graphify <path> --cluster-onlyJump to "For --cluster-only" section below.
/graphify <path> --watchJump to "For --watch" section below.
/graphify or /graphify <path> (with optional flags)Run the full pipeline (Steps 0–9) below.

If the subcommand is query, path, explain, or add, you MUST skip the full pipeline entirely and go directly to the corresponding section. These subcommands operate on an EXISTING graph — they do NOT build a new one.

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

IMPORTANT: Always start by setting the working directory to ~/Documents/wiki to ensure graphify-out is created in the correct location.

Follow these steps in order. Do not skip steps.

Step 0 - Set Working Directory

cd ~/Documents/wiki || { echo "Error: ~/Documents/wiki directory not found. Creating it..."; mkdir -p ~/Documents/wiki; cd ~/Documents/wiki; }

Step 1 - Ensure graphify is installed

cd ~/Documents/wiki
# Detect the correct Python interpreter (handles pipx, venv, system installs)
GRAPHIFY_BIN=$(which graphify 2>/dev/null)
if [ -n "$GRAPHIFY_BIN" ]; then
    PYTHON=$(head -1 "$GRAPHIFY_BIN" | tr -d '#!')
    case "$PYTHON" in
        *[!a-zA-Z0-9/_.-]*) PYTHON="python3" ;;
    e
阅读完整来源 ↗