Works with the AI Agents you already use
ontology engineering method
Translating vague requirements into a structured, testable domain ontology is difficult without a formal engineering process.
$10
ontology engineering method
Example session with this skill installed
I need to build an ontology for tracking cybersecurity requirements in a bank. I have a list of NIST controls and some internal job descriptions for the security team. Start the plan.
- Read your context and instructions
- Compiled the ontology engineering method
I have registered the NIST controls as E1 and the job descriptions as E2. I will now proceed with the first five sections of the Ontology Engineering Plan.
Ontology Engineering Plan — Cybersecurity Requirements, 2024-05-24
1. Purpose, scope and assumptions
The purpose of this ontology is to map cybersecurity requirements from regulatory frameworks to specific organizational roles and technical controls to support compliance auditing. The intended users are security auditors and BTM managers. The scope includes control mappings and role responsibilities; it excludes payroll and non-security HR functions.
Management decision required for scope approval.
2. Sources
| ID | Source | Kind | Authority and licence | Use | Reuse decision |
|---|---|---|---|---|---|
| E1 | NIST Controls | Standard | Public Domain | Requirements | Reuse |
| E2 | Job Descriptions | Internal Docs | Proprietary | Role Mapping | Adapt |
3. Competency questions
| ID | Competency question | Asker | Answer type | Priority | Terms needed | Evidence |
|---|---|---|---|---|---|---|
| CQ01 | Which role is responsible for Control X? | Auditor | Role Name | Must | Role, Control, Responsible | E1, E2 |
| CQ02 | What NIST controls are unassigned? | Manager | List | Should | Control, Assignment | E1 |
4. Concept table
| ID | Term | Kind | Definition | Parent | Synonyms | Disposition | Evidence |
|---|---|---|---|---|---|---|---|
| C01 | SecurityControl | Class | A kind of requirement that specifies a safeguard. | Requirement | Safeguard | Keep | E1 |
| C02 | SecurityRole | Class | A kind of organizational position defined by duties. | Role | Job Title | Keep | E2 |
5. Relation table
| ID | Relation | Domain | Range | Characteristics | Inverse | Serves | Evidence |
|---|---|---|---|---|---|---|---|
| R01 | implements | SecurityRole | SecurityControl | Asymmetric | implementedBy | CQ01 | Analytical estimate |
Next steps
- Review the proposed Competency Questions to ensure they cover all audit requirements.
- Confirm the parent-child hierarchy in the Concept Table.
- Reply "continue" to generate the Axioms, Alignment, and Validation sections.
Connects securely to your tools. The creator never sees your data.
About this skill
Translating vague requirements into a structured, testable domain ontology is difficult without a formal engineering process. This skill applies a stakeholder-driven methodology to move from a shared vocabulary to a documented specification including competency questions, concept tables, and validation plans. It ensures every term and relation serves a specific business requirement rather than bloating the model with unnecessary complexity.
What it does
- Drafts competency questions to define the functional requirements and success criteria the ontology must satisfy.
- Builds concept hierarchies by extracting terms from sources, normalizing synonyms, and assigning parent-child relationships.
- Maps relations and properties to distinguish between object relationships and data properties while tracking their purpose.
- Performs model alignment by mapping local terms to reference models using five distinct match levels and confidence scores.
- Generates validation plans covering logical, question-based, and expert review layers with specific pass criteria.
How it works
- Intake of domain documents, glossaries, or problem statements to identify intended users and scope.
- Requirement definition through the creation of prioritized competency questions that act as the ontology's test suite.
- Table construction for sources, concepts, relations, and axioms, ensuring every entry cites specific evidence or marks analytical estimates.
- Alignment and Validation planning to reconcile the model with existing standards and define expert review cycles.
Frameworks & tools
This skill is framework-agnostic but supports alignment with W3C OWL 2, SKOS, SPARQL, and SHACL standards. It can produce Turtle/OWL snippets for implementation in tools like Protégé.
Why this beats prompting it yourself
Generic prompts often produce flat taxonomies or "hallucinated" relations that lack logical rigor. This skill enforces a specific evidence discipline, requiring every term to serve a competency question and marking every assumption for management review.
Use cases
- Start a new domain ontology for specialized industries like legal or finance.
- Align a local corporate vocabulary with international reference standards.
- Audit an existing draft ontology for completeness and logical consistency.
- Prepare an expert validation plan for a knowledge engineering project.
Known limitations
Does not run reasoners or SPARQL engines. Cannot certify consistency or correctness; it produces the specification for humans to implement and test.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Does not execute code, run reasoners, or perform SPARQL queries. Requires user-provided documentation for high-accuracy concept extraction. Scope sign-offs require manual management intervention.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 days ago
Permissions
No special permissions declared or detected