meleantonio/prove-that-shit

adversarial-proof-audit

Independently attack a candidate mathematical proof: find gaps, circular lemmas, silent hypothesis changes, insufficient uniformity, and false completions. Use after any draft proof of an open problem, before claiming success, or when the user asks to audit,…

Langue du texte source : anglais

craft-proof-prompt

Build a problem-specific open-problem proof prompt that defines success, bans weaker substitutes, lists traps, and configures multi-agent adversarial search. Use when preparing Codex/Cursor/Claude goals for proving or disproving a conjecture, or when asked to…

Langue du texte source : anglais

formalize-proof

Formalize a natural-language mathematical proof in Lean 4 (or another kernel) incrementally: small goals first, expand, audit mismatches, refactor. Use after an informal proof of an open problem is drafted and audited, or when the user asks for Lean…

Langue du texte source : anglais

prove-open-problem

Attack an open mathematical problem end-to-end using the Wang/Codex Erdős workflow: select tractability, craft a problem-specific proof prompt, run a long attempt→audit→repair research loop with multi-agent search, and emit LaTeX/Python/Lean artifacts. Use…

Langue du texte source : anglais

select-tractable-problem

Filter open math problems for agent attackability: prefer actively discussed problems, demote those tied to major conjectures or requiring new theory. Use before long proof runs or when the user asks which Erdős/open problems to attempt.

Langue du texte source : anglais