proof-writer

Generate a structured proof package with assumptions, notation, and dependency map.

1|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/HeXiao-55/Auto-SurveyMind --skill proof-writer-hexiao-55
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: proof-writer
Source: https://github.com/HeXiao-55/Auto-SurveyMind/tree/main/skills/skills-codex/proof-writer
Command: npx skills add https://github.com/HeXiao-55/Auto-SurveyMind --skill proof-writer-hexiao-55

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Writes rigorous mathematical proofs for ML/AI theory. It assists when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof sketch, or determine whether a claimed proof can actually be completed under the stated assumptions.

Core Features & Use Cases

  • Generate a complete, defendable proof package: exact claim, explicit assumptions, notation, and a dependency map.
  • Debug and refine: identify gaps, propose fixes, and handle edge cases or weaker versions of the claim.
  • Use Case: researchers draft proofs for theorems in ML/AI literature or convert sketches into formal proofs, with option to produce a blockage report if the claim is not justified.

Quick Start

Ask me to draft a complete proof package for a specified theorem.

Frequently Asked Questions about proof-writer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write a rigorous mathematical proof for an ML/AI theorem?

To write a rigorous ML/AI proof, analyze the theorem statement and assumptions to generate a structured proof package containing exact claims, explicit assumptions, notation, a dependency map, and step-by-step justification.

Can I formalize a proof sketch into a complete, machine-checkable format?

Yes, you can formalize a proof sketch by refining it into a structured proof package that ensures formal rigor and traceability through explicit assumptions and step-by-step justification.

What should I do when I cannot justify a claimed lemma under the stated assumptions?

When a claimed lemma cannot be justified, generate a blockage report to identify gaps, propose fixes, and handle edge cases or weaker versions of the original claim.

How do I debug missing steps in an existing mathematical proof?

Debug a mathematical proof by analyzing its dependency map and step-by-step justification to identify gaps, propose fixes, and refine lemmas for formal rigor.

Does this proof generation approach handle edge cases and weaker versions of a claim?

Yes, proof generation handles edge cases by proposing fixes and refining the claim into weaker versions when the original statement cannot be fully justified under the explicit assumptions.

What is included in a structured proof package for AI theory?

A structured proof package for AI theory includes the exact claim, explicit assumptions, notation, a dependency map, and step-by-step justification to ensure formal rigor and traceability.