Automated summary

This skill reviews code with a specific focus on the mathematical and physical correctness of the implemented computations.

Strengths

Checks unit handling (astropy.units, quantities) and dimensional consistency of operations
Cross-checks implemented equations against reference papers or standard textbooks
Flags numerical stability issues such as division by zero and floating-point precision loss, plus edge cases
Suggests a small script to test conservation laws, e.g. Parseval's theorem for an FFT

Limitations

Review quality depends heavily on domain physics knowledge that the skill itself does not supply
Does not substitute for experimental validation or comparison against real data
Generated sanity-check scripts are lightweight and still need human review

When to use it

Use it when auditing scientific or simulation code whose physical and mathematical soundness must be confirmed before production use.

When not to use it

Skip it for application code with no substantive math or physics content, where the review adds little value.

Security analysis

Safe

Quality score80/100

The skill is purely advisory: it instructs the agent to review code for dimensional consistency, mathematical correctness, numerical stability, and physical sanity. There are no destructive commands, no network or secret access, no obfuscation, and no attempts to disable safety controls. The only execution-adjacent step is writing small sanity-check scripts, which is a normal and bounded testing activity, not a risk.

Findings

•Step 3 suggests creating and running small test scripts to check conservation laws; this is a legitimate verification activity, but without declared tools its execution scope is unspecified.

How this analysis is made

Examples

Review FFT power spectrum code

Review my FFT power spectrum implementation for dimensional consistency and numerical stability, and write a small test that verifies Parseval's theorem holds.

Check unit operations in orbital simulation

My orbital simulation uses astropy.units — check that every operation is dimensionally valid and that no Length is added to a Time.

Verify equation against reference paper

Compare the heat diffusion equation implemented in solver.py against the standard literature form and flag any suspect terms or edge cases at f=0.

name: check_physics description: 実装内容が数学的・物理学的に妥当か検証する

Verify Physics

Name: Physics and Mathematics Verification
Author: Skills Guide Bot

This skill performs a review of the code specifically focusing on physics and math correctness.

Instructions

Dimensional Analysis:
- Check if unit handling (e.g., astropy.units, quantities) is used correctly.
- Ensure operations are physically valid (e.g., not adding Length to Time).
Mathematical Inspection:
- Verify equations against known reference papers or standard textbooks.
- Check for numerical stability issues (e.g., division by zero, floating point precision loss).
- Check edge cases (e.g., $f=0$, infinite limits).
Sanity Checks:
- Create a small script to test conservation laws (e.g., Parseval's theorem for FFT).
- Verify that reasonable inputs produce physically reasonable outputs.
Report:
- Provide a summary of the analysis, pointing out any suspect logic or confirming validity.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/physics-and-mathematics-verification-mm8o532r/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/physics-and-mathematics-verification-mm8o532r' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/physics-and-mathematics-verification-mm8o532r/download' --output '.skill-downloads/physics-and-mathematics-verification-mm8o532r/SKILL.md.part' && mv '.skill-downloads/physics-and-mathematics-verification-mm8o532r/SKILL.md.part' '.skill-downloads/physics-and-mathematics-verification-mm8o532r/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/physics-and-mathematics-verification-mm8o532r/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.