What problem does it solve? Comparing speculative theories of everything and fundamental-physics frameworks is hard to do consistently, and it is easy to confuse novelty or hype with scientific strength. This Skill provides a structured rubric, output contract, and clash protocol so every theory is evaluated on the same auditable criteria. ## Core Features & Use Cases - Dual-tier evaluation: Assigns separate scientific_tier and interest_tier grades (S/A/B/C/D/F) with explicit confidence levels and written justification, keeping scientific strength distinct from novelty. - Structured arena entries: Produces a complete record per theory covering claims, scope, evidence for and against, predictions, provenance, and tier movement history, following the YAML schema in references/schema.md. - Clash protocol: Runs head-to-head comparisons between theories on a single battleground (e.g., UV completion, black-hole entropy, Standard Model incorporation) and records whether the clash warrants a tier change. - Use Case: A new preprint claims to unify gravity and the Standard Model. Use this Skill to catalogue it, grade it against the ten evidence dimensions, and clash it against loop quantum gravity to decide its initial Arena placement. ## Quick Start Evaluate this new theory-of-everything preprint, assign scientific and interest tiers with justification, and clash it against an existing Arena entry.
