What problem does it solve?
Drafting proofs for theorems, lemmas, and propositions in ML/AI research often leads to hidden gaps, unstated assumptions, or overclaimed results. This Skill produces mathematically honest proof packages that either prove the claim, correct it, or explain exactly why it cannot be justified.
Core Features & Use Cases
- Feasibility Triage: Classifies every claim as PROVABLE AS STATED, PROVABLE AFTER WEAKENING / EXTRA ASSUMPTION, or NOT CURRENTLY JUSTIFIED before writing anything.
- Structured Proof Package: Generates a PROOF_PACKAGE.md containing the exact claim, assumptions, notation, proof strategy, dependency map, numbered steps, and open risks.
- Honest Blockage Reports: When a proof cannot be completed, it documents the exact blocker, missing lemma, or counterexample instead of fabricating steps.
- Use Case: You have a convergence lemma for your optimization paper with only a rough sketch. Ask the Skill to formalize it, and it will verify the assumptions, build the dependency map, and write a complete appendix-ready proof—or tell you the claim needs weakening.
Quick Start
Ask the assistant to prove the stated theorem under the given assumptions and write the result into PROOF_PACKAGE.md.