proof-plan

Package raw proof ideas into GPT-pro-ready prompt bundles with claims and materials.

2|1|Updated May 7, 2026
One-click install
npx skills add https://github.com/shenmuxing/EtaSkill --skill proof-plan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: proof-plan
Source: https://github.com/shenmuxing/EtaSkill/tree/main/skill-examples/proof-plan
Command: npx skills add https://github.com/shenmuxing/EtaSkill --skill proof-plan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill helps you turn a rough proof idea into a compact, reviewable GPT-pro prompt bundle so you can validate the task before spending model budget.

Core Features & Use Cases

  • Proof task packaging: Organizes the target claim, notation, source materials, user-given assumptions, and open questions into a clean handoff.
  • Mechanical local checks: Verifies basic issues such as file existence, notation normalization, and obvious inconsistencies without attempting to solve the proof locally.
  • Use Case: If you have a theorem statement and some references, this Skill prepares task.md and materials.md for a reviewer model to diagnose or complete the proof.

Quick Start

Use the proof-plan skill to package my proof idea into a GPT-pro-ready task bundle for review.

Frequently Asked Questions about proof-plan

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

FAQPage Schema
How do I package a mathematical proof idea for a reviewer model?

To package a proof idea for a reviewer model, this Skill organizes the target claim, notation, source materials, user-given assumptions, and open questions into a review-ready task bundle.

What is proof planning and how does notation normalization work?

Proof planning standardizes mathematical tasks for review by preparing a prompt bundle, while notation normalization ensures consistent mathematical symbols across the target claim and source materials.

Does proof-plan complete gaps or solve the proof locally?

No, proof-plan does not solve the proof or complete gaps locally. It strictly separates supported claims from unsupported ones and packages the task for a downstream reviewer model to diagnose.

Can I use proof-plan to verify cited files and check basic consistency?

Yes, you can use proof-plan to perform mechanical local checks such as verifying cited file existence, normalizing notation, and identifying obvious inconsistencies without attempting to solve the proof.

What files do I need to start packaging a theorem statement and references?

You need a target theorem statement and your reference materials. The Skill uses these to prepare task.md and materials.md files for a reviewer model to diagnose or complete the proof.

Why does my proof handoff prompt bundle need unresolved questions separated?

Separating unresolved questions in a proof handoff prompt bundle ensures the reviewer model receives a clean task boundary, distinguishing between user-stated givens and gaps that require actual mathematical diagnosis.