agentsclimarketplace

Ontology ontology architect

Skill Mokee04/ontology_research/ontology-ontology-architect

Hierarchical agent skills for domain ontology planning, research, construction, and validation with saved research artifacts and eval-ready workflows.

Install
npx -y skills add Mokee04/ontology_research --skill ontology-ontology-architect

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Design a domain ontology from evidence using layered modeling, stable concept definitions, explicit relations, SKOS-first structure, and selective OWL formalization with recorded modeling decisions.

SKILL.md

1.8 KB, 358 tokens by cl100k_base, as published. Nobody here has run it

Ontology Ontology Architect

Read:

  • ../refs/Total Guide.md
  • ../shared/references/skill-family-architecture.md
  • ../shared/references/templates.md
  • ../shared/references/ontology-codegen-spec.md when code generation is needed
  • ../shared/references/ontology-spec.template.json when initializing a new machine-readable ontology spec

Use this worker skill to turn research outputs into a coherent ontology design.

Tasks

  1. Identify the conceptual backbone of the domain.
  2. Separate core concepts, domain concepts, and application-specific extensions.
  3. Start with a glossary or SKOS concept scheme.
  4. Add relations and formal constraints only where justified by CQ and evidence.
  5. Record modeling decisions, alternatives, and unresolved ambiguity.
  6. When requested, turn the stable ontology outline into a JSON spec that can be rendered into RDF/OWL Turtle with ../shared/scripts/generate_ontology_ttl.py.
  7. Start from ../shared/references/ontology-spec.template.json unless a run-specific spec already exists.

Outputs

Write or refine:

  • ../exe/<run-id>/build/glossary.md
  • ../exe/<run-id>/build/modeling-decisions.md
  • ../exe/<run-id>/build/ontology-outline.md
  • ../exe/<run-id>/build/mapping-notes.md
  • ../exe/<run-id>/build/ontology-spec.json when machine-generated Turtle is requested

Guardrails

  • do not confuse taxonomy with every kind of relation
  • do not add OWL complexity without a concrete payoff
  • do not finalize equivalence or inheritance decisions without evidence
  • do not generate RDF/OWL code from unstable modeling decisions

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.