What problem does it solve? Texts often contain formulations whose literal wording is broader, narrower, or more ambiguous than the argument actually supports, leading readers to misinterpret claims about causality, agency, modality, or scope. This Skill systematically detects overstatement, understatement, unresolved ambiguity, and terminological drift so authors can align wording with intended meaning. ## Core Features & Use Cases - Scope and Modality Analysis: Compares literal scope, contextual scope, and likely reader interpretation, checking modal verbs and quantifiers against the evidence provided. - Distinction and Attribution Checking: Verifies that key distinctions (possibility/inevitability, influence/determination, behavior/understanding) survive the wording and that attributions do not shift unsupportedly between functional and intentional levels. - Terminological Drift Tracking: Follows recurring terms across sections to detect semantic drift, disappearing qualifications, or tentative claims becoming categorical. - Use Case: A researcher drafts a paper claiming "AI systems determine knowledge production." The Skill flags that the argument only supports influence, not determination, and reports the mismatch with literal scope, contextual scope, and diagnosis. ## Quick Start Analyze the attached essay for semantic precision and report any formulations whose wording overstates or understates the intended claims.
