What problem does it solve? Academic and analytical writing often overstates causal claims, presenting associations, contributions, or interpretive mappings as demonstrated causality. This Skill audits causal language so that wording strength matches the actual strength and type of supporting evidence. ## Core Features & Use Cases - Three-Level Claim Classification: Distinguishes directly supported causal relations, association/influence/contribution claims, and cartographic interpretations within rhizomatic analysis. - Calibration Audit Rule: Applies a claim → evidence → causal strength → mechanism/conditions → formulation check to every significant causal chain. - Calibration, Not Dilution: Preserves strong causal verbs where evidence supports them instead of weakening all causal language by default. - Use Case: When drafting a rhizomatic analysis of AI systems, run this Skill to ensure statements like "X causes Y" are only used where evidence demonstrates causation, while weaker relations are phrased as "contributes to", "conditions", or "is associated with". ## Quick Start Review the causal claims in my draft analysis and recalibrate any wording that overstates the available evidence.
