audit-structure-consistency

SkillAI & models

Lets your agent check a knowledge model for cycles, contradictions, orphans, and broken structural rules.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the audit-structure-consistency skill

About this skill

Detect cycles, contradictions, orphans, type violations, and structural incoherence in a knowledge model.

What this skill tells your AI

The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/audit-structure-consistency/SKILL.md and read by ahel’s review.

Purpose

Audit whether a concept, argument, or graph preserves its declared structural relations and constraints.

Input contract

required: [structure, relation_schema, consistency_rules]
optional: [source_structure, version_history, exception_rules]
constraints: [each inconsistency identifies nodes, relation, and violated rule]

Procedure

  1. Validate node types, relation types, direction, and required fields.
  2. Check hierarchy, dependency, cardinality, and cycle constraints.
  3. Compare versions or source structure where supplied.
  4. Emit inconsistencies, valid exceptions, and repair questions.

If the structure is internally consistent but leaves required areas unrepresented, consider detect-coverage-gap as the next tactic.

Output contract

produces: [consistency_report, violated_rules, valid_exceptions, repair_questions]
delta_fields: [findings, uncertainties, open_questions]

Quality gates

  • Rules and exception policy are declared before checking.
  • Structural validity is separated from semantic truth.

Failure and counterexamples

Do not repair a graph silently or call a semantically weak structure consistent merely because it parses.

Provenance map

  • resolved: audit-structure-consistency

Signals

GitHub stars
501
Forks
41
Last commit
Sep 2026
Advanced
Catalog kind
skill
Key
audit-structure-consistency
Source
github.com/yogsoth-ai/de-anthropocentric-research-engine