math-olympiad

Solve IMO, Putnam, and USAMO problems via adversarial proof verification.

Updated Nov 3, 2016
One-click install
npx skills add https://github.com/xleliberty/mydotfiles --skill math-olympiad-xleliberty
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: math-olympiad
Source: https://github.com/xleliberty/mydotfiles/tree/main/.config/.claude/plugins/marketplaces/claude-plugins-official/plugins/math-olympiad/skills/math-olympiad
Command: npx skills add https://github.com/xleliberty/mydotfiles --skill math-olympiad-xleliberty

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill solves complex competition math problems (IMO, Putnam, USAMO, AIME) while preventing the common pitfalls of AI reasoning, such as hallucinated logic, incorrect interpretations, and overconfidence.

Core Features & Use Cases

  • Adversarial Verification: Employs a multi-pass, fresh-context verification system that attacks proofs using specific failure patterns to ensure logical integrity.
  • Tight-Budget Reasoning: Uses a structured, thinking-only workflow to solve problems without relying on external tools that can lead to computation errors.
  • Use Case: Use this Skill to verify a complex proof for a Putnam problem or to solve a challenging IMO geometry problem where you need to ensure every step is rigorously justified.

Quick Start

Activate the math-olympiad skill to solve this IMO problem and verify the proof for correctness.

Frequently Asked Questions about math-olympiad

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

FAQPage Schema
How do I verify a mathematical proof for logical soundness and prevent AI reasoning hallucinations?

To verify a mathematical proof and prevent AI hallucinations, this system applies multi-pass adversarial testing that attacks proofs using specific failure patterns in fresh contexts to ensure rigorous logical integrity.

What is the best way to solve IMO and Putnam competition mathematics problems using AI?

The best way to solve IMO and Putnam problems is using a structured, thinking-only reasoning workflow that derives numeric answers and generates proofs without relying on external computation tools that introduce errors.

Can I use this approach to solve USAMO and AIME problems that require strict proof generation?

Yes, you can solve USAMO and AIME problems because the approach is specifically designed for high-level competition mathematics, handling both complex proof generation and numeric answer derivation with adversarial verification.

How does adversarial verification work when checking complex geometry proofs?

Adversarial verification works by running a multi-agent workflow that attacks complex geometry proofs using pattern-based adversarial testing across fresh contexts to identify hallucinated logic and ensure every step is rigorously justified.

Do I need external mathematical computation tools to process competition math reasoning?

No, you do not need external computation tools; the system uses a tight-budget reasoning protocol that relies strictly on internal thinking-only workflows to process competition math and avoid external computation errors.