proof-writer

Draft rigorous mathematical proofs for ML/AI theory claims.

1|Updated Mar 24, 2026
One-click install
npx skills add https://github.com/kitcaf/skills --skill proof-writer-kitcaf
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: proof-writer
Source: https://github.com/kitcaf/skills/tree/main/skills/skills-codex/skills/proof-writer
Command: npx skills add https://github.com/kitcaf/skills --skill proof-writer-kitcaf

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Writes rigorous mathematical proofs for ML/AI theory upon request, including handling lemmas, propositions, corollaries, and proof sketches, and can formalize incomplete steps for further refinement.

Core Features & Use Cases

  • Generate complete, rigorous proofs for the exact claims provided, given explicit assumptions.
  • Provide proof sketches or corrected claims when a claim cannot be justified as stated.
  • Produce a structured proof package with a clear status, dependency map, and step-by-step justification.

Quick Start

Provide the exact claim, assumptions, and any sketch, and ask me to draft a complete, justified proof package.

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 draft a rigorous mathematical proof for an ML/AI theorem, provide the exact claim, explicit assumptions, and any existing notation or dependencies to generate a complete proof package with step-by-step justifications.

What is a blockage report in formal theorem proving?▼

A blockage report in formal theorem proving is generated when a claim cannot be justified as stated, providing a proof sketch or corrected claims to help you refine the incomplete steps of the mathematical argument.

Can I get a proof sketch for a machine learning proposition if the full formalization fails?▼

Yes, if a machine learning proposition cannot be justified as stated, the system provides a proof sketch or corrected claims, allowing you to formalize incomplete steps for further refinement and analysis.

Does the proof package include notation definitions and dependency maps for lemmas?▼

Yes, the proof package includes explicit assumptions, notation definitions, a complete dependency map, and step-by-step justifications for theorems, lemmas, propositions, and corollaries.

What is the best way to formalize a partial proof for an AI theory corollary?▼

The best way to formalize a partial proof for an AI theory corollary is to provide the exact claim and assumptions, allowing the system to produce a structured proof package that fills in incomplete steps with rigorous justifications.