proof-writer

Generate structured mathematical proofs with dependency mapping and status classification.

1|Updated Jul 21, 2026
One-click install
npx skills add https://github.com/dogekiki/SP-test --skill proof-writer-dogekiki
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: proof-writer
Source: https://github.com/dogekiki/SP-test/tree/main/.trae/skills/proof-writer
Command: npx skills add https://github.com/dogekiki/SP-test --skill proof-writer-dogekiki

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill addresses the difficulty of formalizing mathematical arguments, ensuring that proofs for theorems, lemmas, and propositions are logically sound, complete, and free of hand-wavy justifications.

Core Features & Use Cases

  • Rigorous Drafting: Generates structured proof packages with explicit assumptions, dependency maps, and step-by-step logical verification.
  • Feasibility Triage: Automatically classifies claims as provable, provable with weakening, or currently unjustified to prevent the fabrication of false proofs.
  • Use Case: When developing a new loss function or optimization bound, use this Skill to formalize your proof sketch, identify missing assumptions, and ensure all boundary cases are handled.

Quick Start

Use the proof-writer skill to draft a formal proof for the convergence theorem stated in the current project notes.

Frequently Asked Questions about proof-writer

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

FAQPage Schema
How do I formalize a mathematical proof sketch for an ML theorem?

To formalize a mathematical proof sketch, provide structured input of your claims and assumptions to generate a standardized proof package with explicit dependency mapping and logical verification.

What is the best way to identify hidden assumptions in machine learning derivations?

Identifying hidden assumptions in machine learning derivations requires formalizing proof sketches to expose missing conditions, ensuring all boundary cases are handled and logical consistency is verified across complex derivations.

How can I verify the logical consistency of complex mathematical proofs for AI research?

Verifying the logical consistency of complex mathematical proofs involves generating a structured proof package that maps dependencies, verifies step-by-step logic, and eliminates hand-wavy justifications in AI research contexts.

Can I check if a convergence theorem is provable before drafting the full mathematical proof?

Yes, you can check if a convergence theorem is provable by using feasibility triage to automatically classify claims as provable, provable with weakening, or currently unjustified, preventing the fabrication of false proofs.

What limitations exist when generating rigorous mathematical proofs for optimization bounds?

Limitations when generating rigorous mathematical proofs for optimization bounds include the inability to prove claims classified as currently unjustified, requiring users to weaken claims or add missing assumptions to achieve logical soundness.