gpd-verify-work

Automate physics checks for dimensional consistency, limiting cases, and numerical convergence.

1|Updated Mar 29, 2026

Search Tags:#numerical analysis #computational science #research verification #result validation #physics checks

Ready to run

npx skills add https://github.com/CharGrnmn/roomtemp-superconductor-gpd --skill gpd-verify-work-chargrnmn

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: gpd-verify-work
Source: https://github.com/CharGrnmn/roomtemp-superconductor-gpd/tree/main/.agents/skills/gpd-verify-work
Command: npx skills add https://github.com/CharGrnmn/roomtemp-superconductor-gpd --skill gpd-verify-work-chargrnmn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires gpd, python, numpy, scipy, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the verification of research results through systematic physics checks, ensuring the correctness and trustworthiness of numerical results and physical conclusions.

Core Features & Use Cases

Physics Consistency Checks: Validates research outcomes against established physical principles.
Systematic Verification: Executes a suite of checks, including dimensional analysis, limiting cases, and numerical convergence.
Output Tracking: Generates a .gpd/phases/XX-name/{phase}-VERIFICATION.md file to track all verification results.
Use Case: Imagine you have completed a phase in a research project. Use this Skill to verify the numerical results and physical conclusions against the phase goals and contract requirements.

Quick Start

Verify the results of phase 4 by running: gpd-verify-work 4

Frequently Asked Questions about gpd-verify-work

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

FAQPage Schema

How do I automate physics consistency checks for numerical research results?▼

You can automate physics consistency checks by running systematic verification scripts that validate dimensional consistency, limiting cases, and numerical convergence against benchmark results. This ensures the correctness of numerical outcomes and physical conclusions.

What is the best way to verify dimensional consistency and numerical convergence in computational science?▼

Systematic verification validates computational science results by checking dimensional consistency and numerical convergence automatically. It executes a suite of physics checks and outputs a tracking file to record all validation results for your research phase.

Do I need Python, NumPy, and SciPy to run automated result validation?▼

Yes, automated result validation requires a Python environment with NumPy and SciPy installed, along with the gpd runtime. These dependencies provide the necessary computational frameworks to execute physics checks and benchmark comparisons.

How do I verify research results for a specific project phase?▼

To verify research results for a specific phase, you run the verification command with the phase number as an argument. The Skill checks numerical outcomes against phase goals and contract requirements, generating a dedicated verification markdown file.

What types of physics checks are included in research result validation?▼

Research result validation includes physics checks for dimensional consistency, limiting cases, numerical convergence, and benchmark result comparisons. These systematic checks ensure your numerical analysis and physical conclusions align with established physical principles.

Can I use this verification approach for computational science projects that lack benchmark results?▼

The verification approach relies heavily on comparing against benchmark results to validate physical conclusions. Without established benchmarks, the numerical convergence and limiting case checks still function, but overall validation completeness may be limited.