Not in the top 1,000 by GitHub stars
codejunkie99/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
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
graph-engineering/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
cfacb56a05a3 → cfacb56a05a3
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → cfacb56a05a3
No earlier version was observed for comparison.
567GitHub stars
10stars in 7 days
1skill in this repository
0commits in 30 days
Heat
5.9- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- graph-engineering
graph-engineering
How it works
graph-engineering
When your agent uses it
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.
What it loads into context
Frontmatter
156 tokensAlways available to the agent
SKILL.md
1,790 tokensWhen the skill is activated
Reference documents
5,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Teaching Mode
- The 9-Stage Pipeline
- Working Rules
- Reference Files
- Credits
Files
SKILL.mdcore7,934 bytesSKILL.mdcore7,934 bytesSKILL.mdcore7,934 bytesSKILL.mdcore7,934 bytesreferences/curriculum.mddoc4,402 bytesreferences/extraction.mddoc5,507 bytesreferences/fusion-and-llm.mddoc4,801 bytesreferences/modeling.mddoc4,669 bytesreferences/task-graphs.mddoc3,519 bytes
Read SKILL.md
# Graph Engineering
Graph engineering is the discipline of designing the structures agents work through — not the
prompts. It has two halves:
1. **Knowledge graphs** — what agents remember. Nodes are entities and facts, edges are
relationships with time and provenance. This file's 9-stage pipeline covers it, distilled
from Southeast University's graduate KG course
(https://github.com/npubird/KnowledgeGraphCourse, Prof. Peng Wang), translated to English
and adapted for LLM-era agents.
2. **Task graphs** — how agents work. Nodes are jobs, edges are execution dependencies:
parallel fan-out, separate verifier contexts, the stop rule, the human gate.
Read [references/task-graphs.md](references/task-graphs.md) when the request is about
orchestrating agents rather than building memory.Skills included
- graph-engineering
Repository facts
- License
- MIT
- Created
- Jul 23, 2026
- Last pushed
- Jul 23, 2026
- Forks
- 68
- Open issues
- 0
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 3 notes
graph-engineering/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedgraph-engineering/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedgraph-engineering/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 7 network referencesin 2 files: graph-engineering/SKILL.md:12 graph-engineering/references/curriculum.md:3
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 7 signals by file
graph-engineering/SKILL.md
- Network accessline 12
relationships with time and provenance. This file's 9-stage pipeline covers it, distilled from Southeast University's graduate KG course (https://github.com/npubird/KnowledgeGraphCourse, Prof. Peng Wang), translated to English - Network accessline 13
from Southeast University's graduate KG course (https://github.com/npubird/KnowledgeGraphCourse, Prof. Peng Wang), translated to English and adapted for LLM-era agents. - Network accessline 14
(https://github.com/npubird/KnowledgeGraphCourse, Prof. Peng Wang), translated to English - Network accessline 118
Distilled and translated from 东南大学《知识图谱》研究生课程 (Southeast University graduate course on Knowledge Graphs), Prof. Peng Wang — https://github.com/npubird/KnowledgeGraphCourse. - Network accessline 119
course on Knowledge Graphs), Prof. Peng Wang — https://github.com/npubird/KnowledgeGraphCourse.
graph-engineering/references/curriculum.md
- Network accessline 3
Southeast University graduate course《知识图谱》(Knowledge Graphs), Prof. Peng Wang. Repo: https://github.com/npubird/KnowledgeGraphCourse (4.4K★, running since 2019, updated yearly). - Network accessline 4
Repo: https://github.com/npubird/KnowledgeGraphCourse (4.4K★, running since 2019, updated yearly).
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Signal confidence: 7 facts
- Network access in prose of the SKILL.mdgraph-engineering/SKILL.md:12Low confidence
- Network access in prose of the SKILL.mdgraph-engineering/SKILL.md:13Low confidence
- Network access in prose of the SKILL.mdgraph-engineering/SKILL.md:14Low confidence
- Network access in prose of the SKILL.mdgraph-engineering/SKILL.md:118Low confidence
- Network access in prose of the SKILL.mdgraph-engineering/SKILL.md:119Low confidence
- Network access in prose of documentationgraph-engineering/references/curriculum.md:3Low confidence
- Network access in prose of documentationgraph-engineering/references/curriculum.md:4Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md graph-engineering/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md graph-engineering/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md graph-engineering/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md graph-engineering/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md graph-engineering/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md graph-engineering/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
