What problem does it solve? Philosophical and analytical texts often contain claims whose strength, scope, or modality exceeds what their evidence and arguments support. This Skill systematically identifies which claims are vulnerable to empirical challenge, counterexample, conceptual objection, or evidential insufficiency—without forcing philosophical writing into a scientific falsifiability model. ## Core Features & Use Cases - Claim Reconstruction and Classification: Decompose each strong claim into subject, predicate, scope, modality, evidence, and mechanism, then classify it as empirical, causal, conceptual, philosophical, interpretive, or mixed. - Vulnerability Typing: Distinguish empirical, evidential, causal, scope, modal, counterexample, interpretive, internal, and methodological vulnerabilities instead of collapsing them into generic weakness. - Graded Findings with Recommendations: Rate each finding from Critical to Non-problematic with confidence levels and concrete recommendations (qualify, narrow scope, add conditions, or leave unchanged). - Use Case: Given an essay claiming "AI will inevitably transform biology," the audit flags the modal jump from possibility to necessity, classifies it as a modal vulnerability, and recommends narrowing the claim to match the evidence. ## Quick Start Audit the attached essay for claims whose strength, scope, or modality exceeds the support provided in the text.
