General skillResearch and knowledge
AntiApophenia-Claude-Skill
Test pattern claims with null models, controls, and falsification
Test pattern claims with null models, controls, and falsification
Anti-Apophenia makes an agent treat an appealing pattern as a hypothesis rather than a finding. It requires a claim, evidence, null model, alternatives, prediction, and disconfirmation loop, while penalizing post-hoc fitting, repeated attempts, cherry-picking, and vague resemblance. Evidence grades and explicit verdicts separate strong, weak, rejected, and unknown results, and tempting branches stay parked instead of steering the investigation. Speculative exploration is allowed only in a clearly marked sandbox.
Resource types
Use cases
Platforms
Runtime
Generate study-design-aware clinical Table 1 outputs in HTML, Word, and LaTeX.
Retrieve cited Quran and Sahih hadith texts through a RAG-backed Claude skill.
Public GitHub facts last synced Jul 10, 2026.
Define product problems through six research lenses before proposing solutions.
Review ML and AI papers with evidence-based critiques and verified references.