curl -fsSL https://api.cheatcodehq.com/install.sh | sh -s -- graph-engineering --to allCopies 1 skill into each app's skills folder (Claude Code: ~/.claude/skills), after checking every file against codejunkie99/graph-engineering at commit cfacb56. Nothing else on your computer changes. To undo it, run the terminal command with --uninstall at the end; that also removes what the app added.
Then start a new session in your AI app and ask for the work in plain words; it picks the skill from its description. In Claude Code you can also type /graph-engineering:graph-engineering.
See it in use
After installing, start a new session and say: Use the graph-engineering skill to build a small knowledge graph from these notes, with an ontology and a subgraph diagram.
What else it can do, and its limits
- Needs no tools beyond a terminal; it reasons over text and writes markdown or mermaid, no account or install.
- Teaches the 9-stage knowledge graph pipeline (scope, representation, ontology, extraction, fusion, serving) distilled from a university course.
- Also covers task graphs: orchestrating multiple agents as a graph, with fan-out, verifiers and human gates.
- A teaching mode walks through each stage with the user's own project as the running example.
- Rejects edges whose endpoint types don't match the ontology; this removes most hallucinated structure.
Sample input Recorded Oct 27, 2026 in Claude Code 2.1.308 with Sonnet 5.5. The video replays that session; nothing in it was acted or edited.
What's inside 1 skill
graph-engineeringTeaches an agent graph engineering — both halves. Knowledge graphs (ontology design, entity/relation/event extraction, fusion, GraphRAG/memory serving; distilled and translated from Southeast University's graduate Knowledge Graph course, npubird/KnowledgeGraphCourse, 4.4K stars) and task graphs (agent orchestration — parallel fan-out, verifier separation, the stop rule, human gates). Use when asked to build a knowledge graph, extract entities/relations from text, design an ontology, dedupe/merge entities, add graph memory or GraphRAG to an agent, orchestrate multi-agent workflows as a graph, or LEARN graph engineering — in teaching mode the agent explains each stage with worked examples and generates visual diagram artifacts.
Teaches an agent graph engineering — both halves. Knowledge graphs (ontology design, entity/relation/event extraction, fusion, GraphRAG/memory serving; distilled and translated from Southeast University's graduate Knowledge Graph course, npubird/KnowledgeGraphCourse, 4.4K stars) and task graphs (agent orchestration — parallel fan-out, verifier separation, the stop rule, human gates). Use when asked to build a knowledge graph, extract entities/relations from text, design an ontology, dedupe/merge entities, add graph memory or GraphRAG to an agent, orchestrate multi-agent workflows as a graph, or LEARN graph engineering — in teaching mode the agent explains each stage with worked examples and generates visual diagram artifacts.
About
Graph engineering for AI agents: the 9-stage knowledge-graph pipeline (translated from SEU's graduate course) + task-graph orchestration patterns, as a Claude skill with teaching mode and paste-ready workflows
Something wrong with this listing, or it did not install? Tell us