derivation-verify

Verify mathematical derivations by clustering independent re-derivations by equivalence.

14|6|Updated Feb 24, 2026
One-click install
npx skills add https://github.com/fkguo/nullius --skill derivation-verify
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: derivation-verify
Source: https://github.com/fkguo/nullius/tree/main/skills/derivation-verify
Command: npx skills add https://github.com/fkguo/nullius --skill derivation-verify

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Claude, Codex, Gemini, OpenCode, Kimi, review-swarm, and includes scripts (resource) and workflows (resource) and references (resource) components.

What problem does it solve?

This Skill verifies the correctness of derived mathematical results by independently re-deriving them multiple times and ensuring agreement among the results.

Core Features & Use Cases

  • Independent Verification: Runs multiple independent re-derivations of a mathematical result.
  • Mathematical Equivalence: Clusters results by mathematical equivalence, not string equality.
  • Adversarial Comparator: Ensures convergence by requiring agreement among at least two independent derivations.
  • Use Case: When you have derived a complex mathematical result and want to ensure its correctness before using it in further work.

Quick Start

Use the derivation-verify skill to verify the correctness of the derived formula 'A(q)=arctan(q/2m)/2q' by providing the context and the formula to derive.

Frequently Asked Questions about derivation-verify

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

FAQPage Schema
How do I verify the correctness of a mathematical derivation?

Verify a mathematical derivation by independently re-deriving the result multiple times and clustering outcomes by mathematical equivalence. This process requires agreement among at least two independent derivations to ensure correctness.

What is independent mathematical verification and how does it work?

Independent mathematical verification performs multiple independent re-derivations of a symbolic result and clusters them by mathematical equivalence. An adversarial comparator enforces convergence by requiring agreement among at least two independent derivations.

Can I use derivation verification for physics formulas like arctan(q/2m)/2q?

Yes, derivation verification applies to any field requiring verification of symbolic results. You can verify derived formulas like arctan(q/2m)/2q by providing the context and the formula to re-derive independently.

Do I need multiple AI models to perform independent verification of formulas?

Yes, independent verification requires Claude, Codex, Gemini, Kimi, or OpenCode CLI multi-backend executors. These enforce cross-model agreement to ensure convergence among at least two independent derivations.

What's the best way to check mathematical equivalence instead of string equality in derived results?

Check mathematical equivalence by clustering multiple independent re-derivations of a symbolic result rather than comparing string equality. An adversarial comparator ensures convergence by requiring agreement among at least two independent derivations.

Why does independent derivation verification require cross-model agreement?

Independent derivation verification requires cross-model agreement to enforce convergence among at least two independent derivations. This adversarial comparison ensures the correctness of derived mathematical results by eliminating single-model bias.