Skip to content
Back to search

graph-engineering

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

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/codejunkie99--graph-engineering/badge.svg)](/listings/codejunkie99--graph-engineering)

HTML

<a href="/listings/codejunkie99--graph-engineering"><img src="/api/listings/codejunkie99--graph-engineering/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

git clone https://github.com/codejunkie99/graph-engineering.git
cp -r graph-engineering/graph-engineering ~/.claude/skills/

Then ask your agent to *build* ("build a knowledge graph from my docs") or to *teach* ("teach me graph engineering") — teaching mode walks the pipeline stage by stage with worked examples and generated diagrams, using your own project as the running example.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 72 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Graph Engineering
  2. **The discipline of designing the structures AI agents work through — not the prompts.**
  3. It has two halves:
  4. 1. **Knowledge graphs** — what agents *remember*. Nodes are entities and facts, edges are
  5. relationships with time and provenance. Ontology → extraction → fusion → serving.
  6. 2. **Task graphs** — how agents *work*. Nodes are jobs, edges are execution dependencies.
  7. Parallel fan-out, separate verifiers, the stop rule, the human gate.
  8. Prompt engineers steered the model's words. Loop engineers steered its iterations.
  9. Graph engineers steer its **topology**.
  10. This repo turns Southeast University's graduate Knowledge Graph course
  11. ([npubird/KnowledgeGraphCourse](https://github.com/npubird/KnowledgeGraphCourse), 4.4K★,
  12. taught in Chinese since 2019) — plus the modern agent-orchestration research behind
  13. task graphs — into things you can actually use today.
  14. ## What's inside
  15. | Path | What it is |
  16. |---|---|
  17. | [`graph-engineering/`](graph-engineering/) | **The skill.** Hand it to your agent (Claude Code / any skill-compatible harness) — it learns the full 9-stage knowledge-graph pipeline, the task-graph patterns, and a teaching mode that explains every stage with diagrams drawn from *your* domain. |
  18. | [`graph-engineering/references/`](graph-engineering/references/) | The distilled course: [curriculum map](graph-engineering/references/curriculum.md) (translated, with links to the original Chinese decks), [modeling](graph-engineering/references/modeling.md), [extraction](graph-engineering/references/extraction.md), [fusion + GraphRAG](graph-engineering/references/fusion-and-llm.md), [task graphs](graph-engineering/references/task-graphs.md). |
  19. | [`WORKFLOWS.md`](WORKFLOWS.md) | Nine paste-ready prompt blocks — a `/kg-tutor` that teaches you the whole course interactively, plus eight single-purpose tools (`/kg-scope` → `/kg-rag`) that chain into a full build. |
  20. | [`dist/graph-engineering.skill`](dist/) | The packaged skill file. |
  21. ## Install (two commands)
  22. ```bash
  23. git clone https://github.com/codejunkie99/graph-engineering.git
  24. cp -r graph-engineering/graph-engineering ~/.claude/skills/
  25. ```
  26. Then ask your agent to *build* ("build a knowledge graph from my docs") or to *teach*
  27. ("teach me graph engineering") — teaching mode walks the pipeline stage by stage with
  28. worked examples and generated diagrams, using your own project as the running example.
  29. ## The 9-stage pipeline
  30. ```mermaid
  31. flowchart LR
  32. A[1 scope] --> B[2 representation] --> C[3 ontology] --> D[4 entities]
  33. D --> E[5 relations] --> F[6 events] --> G[7 quality gate]
  34. G --> H[8 fusion] --> I[9 serve to LLMs]
  35. ```
  36. Model the domain **before** extracting. Fuse **before** storing. Verify at every stage.
  37. A knowledge graph is a product with a schema, not a pile of triples.
  38. ## The task-graph rules (the other half)
  39. - Delete **fake edges**: an arrow is real only when work flows through it.
  40. - The **diamond**: split → parallel workers → *separate* verifier contexts → one owned merge.
  41. - The **stop rule** (Google DeepMind × MIT, 180 configurations): teams win ~80% on work that
  42. splits; every team configuration loses on sequential work. The shape of the work decides.
  43. - The **human gate**: your approval sits exactly where a mistake is expensive to undo.
  44. Details: [references/task-graphs.md](graph-engineering/references/task-graphs.md)
  45. ## Credits
  46. The knowledge-graph half is an independent English distillation of 东南大学《知识图谱》研究生课程
  47. (Southeast University's graduate Knowledge Graph course), Prof. Peng Wang —
  48. [npubird/KnowledgeGraphCourse](https://github.com/npubird/KnowledgeGraphCourse). All original
  49. lecture PDFs are in Chinese and remain in the original repo; none are redistributed here.
  50. Task-graph material draws on Google DeepMind × MIT's
  51. ["Towards a Science of Scaling Agent Systems"](https://research.google/blog/towards-a-science-of-scaling-agent-systems-when-and-why-agent-systems-work/)
  52. and Anthropic's published multi-agent engineering work.
  53. MIT licensed. Built by [@Av1dlive](https://x.com/Av1dlive).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.