Menu
any input (code, docs, papers, images) - knowledge graph - clustered communities - HTML + JSON + audit report
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, managing credentials, auditing instance security, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns. IMPORTANT — Always consult this skill before calling any n8n-mcp tool — it prevents common mistakes like wrong nodeType formats, incorrect parameter structures, and inefficient tool usage. If the user mentions n8n, workflows, nodes, or automation and you have n8n MCP tools available, use this skill first.
Expert n8n workflow development — expression syntax, MCP tools, workflow patterns, node configuration, validation, Code node JS/Python, n8nac code-first development, and code-mode runtime optimization. USE WHEN n8n, n8n workflow, build workflow, n8n node, n8n expression, n8n validation, n8n code node, n8n pattern, n8n MCP, automation workflow, n8n template, webhook workflow, batch processing, n8n agent, n8n javascript, n8n python, workflow architecture, n8nac, n8n-as-code, code-first, workflow.ts, n8nac push, n8nac pull, n8nac init, code-mode, sandbox, token savings, tool consolidation, sibling tools, lazy import.
Developer utilities — CLI generation, skill scaffolding, agent delegation, system upgrades, evals, documents, parsing, audio editing, Codex, Cloudflare, browser automation, prompting, aphorisms, n8n workflows, beads management, full output enforcement, knowledge base, compound engineering. USE WHEN create CLI, scaffold skill, delegate, upgrade system, eval, document, parse, cloudflare, browser, n8n, beads, full output, knowledge, compound engineering.
Compose CUSTOM agents from Base Traits + Voice + Specialization for specialized perspectives. USE WHEN create custom agents, spin up agents, specialized agents, agent personalities, available traits, list traits, agent voices, compose agent, load agent context, agent profile, spawn parallel agents, launch agents. NOT for agent teams/swarms (use Delegation skill → TeamCreate) or Codex delegation (use Delegation skill → CodexBridge).
Audit or initialize repo Beads workflow and files. USE WHEN bootstrap Beads, adopt Beads, standardize Beads workflow, initialize a new repo onto Beads, or verify whether a repo already has mature Beads doctrine.
Turn raw failures into high-signal beads. USE WHEN logs, repro commands, or observed behavior need to become self-contained evidence-first tasks instead of vague TODOs.
| name | graphify |
| description | any input (code, docs, papers, images) - knowledge graph - clustered communities - HTML + JSON + audit report |
| trigger | /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.
Use this skill when the user asks to turn code, docs, papers, images, videos, notes, or a mixed corpus into a persistent knowledge graph; query an existing graph; find paths between concepts; add a URL to a graph corpus; export graph artifacts; or run graphify watch/hooks/Claude integration.
/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 # preserve edge direction: source -> target
/graphify <path> --cluster-only # rerun clustering on existing graph
/graphify <path> --no-viz # skip visualization, just report + JSON
/graphify <path> --svg # also export graph.svg
/graphify <path> --graphml # export graph.graphml
/graphify <path> --neo4j # generate graphify-out/cypher.txt
/graphify <path> --mcp # start MCP stdio server for agent access
/graphify <path> --watch # watch folder, auto-rebuild on code changes
/graphify <path> --wiki # build agent-crawlable wiki
/graphify add <url> # fetch URL, save to ./raw, update graph
/graphify query "<question>" # BFS traversal - broad context
/graphify path "AuthModule" "Database" # shortest path between concepts
/graphify explain "SwinTransformer" # plain-language node explanation
graphify follows the /raw folder workflow: drop anything into a folder — papers, tweets, screenshots, code, notes — and get a structured graph that shows what is connected.
Three things it does that a model alone cannot reliably provide:
graphify-out/graph.json and survive across sessions.EXTRACTED, INFERRED, or AMBIGUOUS.Use it for new codebases, reading lists, research corpora, and personal raw folders.
Read only the file needed for the requested path:
| Request shape | Read next |
|---|---|
Full /graphify pipeline, including install, file detection, and transcription | SetupAndDetection.md, then Extraction.md, then GraphOutputs.md |
| Entity/relationship extraction details, AST extraction, semantic subagents, caching, or merge logic | Extraction.md |
| Clustering, community labels, HTML, Obsidian, wiki, Neo4j, SVG, GraphML, MCP, benchmark, manifest, and final report | GraphOutputs.md |
--update or --cluster-only | IncrementalOps.md |
query, path, or explain | QueryOps.md |
add, --watch, commit hook, or Claude integration | AutomationOps.md |
| Edge provenance, cost visibility, warning, and reporting constraints | HonestyRules.md |
For normal full-pipeline invocation, follow the referenced files in order and do not skip steps.
. and do not ask for a path.AMBIGUOUS.$(cat graphify-out/.graphify_python) after setup.Extraction.md; do not read all files manually one by one.