Ontological Consistency Verification

Audits terminology and categorical frameworks for consistent usage across DATS documents.

Updated Apr 11, 2026
One-click install
npx skills add https://github.com/gozonerd/shadow-ai-assessment --skill ontological-consistency-verification-gozonerd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Ontological Consistency Verification
Source: https://github.com/gozonerd/shadow-ai-assessment/tree/main/.claude/skills/dmis/task_type/TT-18_Ontological_Consistency_Verification
Command: npx skills add https://github.com/gozonerd/shadow-ai-assessment --skill ontological-consistency-verification-gozonerd

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) and references (resource) components.

What problem does it solve? Documents that use the same term with different meanings, or different terms for the same concept, create semantic confusion and undermine analytical credibility. This Skill systematically verifies that terminology, frameworks, and categories are used consistently within and across DATS output documents. ## Core Features & Use Cases - Terminology Inventory: Builds a comprehensive glossary of all key terms with definitions, scope notes, and usage frequency counts. - Consistency Audit: Detects semantic drift, definition mismatches, category errors, and scope violations, each classified by severity with remediation recommendations. - Framework Alignment Verification: Confirms categorical structures (such as office attribution across SMU, SMZ, SMG, and SM-US) are applied consistently, with a 0-1 consistency score. - Use Case: Before distributing a final DATS report, run this verification to catch issues like a section incorrectly calling a scaled deployment a "pilot" or conflating Digital Public Goods with open-source software, then apply the specified remediation. ## Quick Start Verify the ontological consistency of the attached DATS document set against the terminology registry and produce a consistency audit report conforming to the TT-18 output schema.

Frequently Asked Questions about Ontological Consistency Verification

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I check terminology consistency across multiple documents?

Extract every key term with its definition and scope, then audit each usage instance for semantic drift, definition mismatch, or category errors. This Skill automates that process and outputs a structured YAML report with remediation recommendations.

What is an ontological consistency audit?

An ontological consistency audit verifies that terms, frameworks, and categories are used with the same meaning throughout a document set. It distinguishes acceptable context-dependent variation from problematic inconsistency and classifies each issue by type and severity.

How is the TT-18 output validated?

Run the included validate_output.py script against the YAML output file. It checks for required sections (terminology_inventory, consistency_audit, framework_alignment), required fields per term, and that consistency scores fall between 0 and 1.

What types of inconsistency does this verification detect?

It classifies inconsistencies as semantic drift, definition mismatch, category error, or scope violation. Each finding includes usage instances, severity, and a specific remediation recommending which usage to standardize.

When should ontological consistency verification not flag variation?

Acceptable context-dependent variation should not be flagged as inconsistency. Over-standardization and definition inflation are explicit anti-patterns; only genuine meaning shifts or category misapplications warrant remediation.