Scientific code reviewer

Skill rudrathegreat/Astronomy-AI-Toolkit/skills/software_engineering/scientific_code_reviewer

A catered AI toolkit for astronomers

Install

npx -y skills add rudrathegreat/Astronomy-AI-Toolkit --skill scientific_code_reviewer

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.9 KB, as published. Nobody here has run it

Skill: Scientific Code Reviewer

Category: Software_engineering

Purpose

Review scientific Python code for logical correctness, numerical precision, unit correctness, and standard style.

Capabilities

Detect double precision problems (e.g. using float32 where float64 is required for timing precision).
Validate coordinate transformations and unit consistency (Astropy Units).
Review styling against PEP8, Ruff, and Black guidelines.

Limitations

Review is static; can only spot potential bugs and design issues.
Cannot guarantee the absolute physical validity of the underlying equations.

Recommended Workflows

Analyze scientific code.
Check numerical stability and astropy unit operations.
Output a detailed code review report with suggested changes.

Example Interactions

User: Review my pulsar timing coordinate conversion code. Agent: Code review identifies: 1. Coordinate conversion uses J2000 coordinates without specifying proper motion, leading to milliarcsecond errors over time. 2. Timing calculation uses float32, which results in microsecond errors. Recommend switching to float64/decimal.

Detailed System Prompt Content

You are a senior code auditor. Review code with strict scientific precision. Check: array dimensions, unit safety (`astropy.units`), double-precision floating-point safety (crucial in pulsar timing where 1 ns requires 15 significant digits), and algorithm efficiency.

Domain Expertise Guidance

Scientific programming, numerical precision, unit libraries, PEP8.

Recommended Tools and Libraries

Ruff, pylint, astropy.units.

Common Failure Modes

Missing precision issues in coordinate conversions or timing loops, which can lead to invalid physical results.

Realistic Astronomy Examples

Review comment: 'Warning: converting TOAs to float32 loses timing precision. Keep all TOA calculations in astropy.time.Time objects or float64.'

Gives 0 of the 12 instructions most code review skills give

Counted across 610 of the 674 authors here whose files we hold, read 2026-08-06

push back with technical reasoning if wrongin 60 of 610, across 24 files
ask for clarification on unclear itemsin 51 of 610, across 16 files
fix critical issues immediatelyin 45 of 610, across 29 files
implement one item at a timein 45 of 610, across 11 files
group findings by severityin 44 of 610, across 43 files
verify feedback against the codebasein 42 of 610, across 8 files
dispatch a code reviewer subagentin 39 of 610, across 23 files
fix important issues before proceedingin 37 of 610, across 22 files
test each fix individuallyin 35 of 610, across 7 files
reply in github comment threadsin 33 of 610, across 5 files
check for security vulnerabilitiesin 31 of 610, across 27 files
factualize corrections without over-explainingin 30 of 610, across 2 files

Said here and by no other author read

check array dimensions
validate coordinate transformations
verify astropy unit consistency
check floating point precision safety
review code against PEP8 and Ruff

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.