mcpbeat

Ontology School Path Generator

microsoft/ontology-school-path-generator

Generate Ontology School course paths/labs with progressive step ontologies from source ontology material. Use when user asks to tutorialize an ontology into school lessons and per-step builds.

621 tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
2320
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/microsoft/Ontology-Playground --skill ontology-school-path-generator

What comes with it

479 bytes besides the instruction
README.md

The instruction itself

8 sections, as written by the author

Ontology School Path Generator Skill

Goal

Generate a complete Ontology School course with progressive ontology steps.

Read First

  • docs/authoring-guide.md
  • docs/learn-content-guide.md
  • docs/embed-guide.md
  • Example lab:
  • content/learn/iq-lab-retail-supply-chain/
  • catalogue/official/iq-lab-retail-step-1/

Workflow

  • Extract a teachable subset from source ontology.
  • Define step progression (4-7 steps).
  • Create step ontologies under catalogue/official/<slug>-step-N/.
  • Mark step ontologies with "category": "school".
  • Create course under content/learn/<course-slug>/.
  • Add <ontology-embed> + diff for progressive steps.
  • Include at least one quiz per article.

Person Names

If the course, step ontologies, examples, sample data, quests, quiz text, or docs

need any person names, first use the name-generator skill. Do not invent

customer, employee, patient, student, instructor, reviewer, or other human names.

All generated person names must come from:

data/reference/FNF-2026-06-01-01002-0268.csv

Use the CSV FullName column by default, and keep selected names consistent

across source markdown, RDF/OWL examples, generated catalogue data, and tests.

Validate

  • npm run qa:tutorial-content
  • npm run build

Human Review Flow

If lesson content is not yet approved:

  • Add reviewStatus: under-human-review to article frontmatter
  • Open review issue via .github/ISSUE_TEMPLATE/ontology-school-review.yml

Done Criteria

  • Course renders in /#/learn
  • Step ontologies are isolated in School category
  • Any person names introduced by the lesson or sample data came from the

name-generator skill / approved CSV fixture

  • Builds and validators pass

How to use it

Copy the folder

Take microsoft/ontology-school-path-generator from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.