skills.rest
BeopsooKim
BeopsooKimCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

research-code-simulation-reviewer

Review research code and simulation scripts for units, solver settings, reproducibility, and scientific validity.

2|1|Updated May 5, 2026
Search Tags:#code review#research#python#simulation#reproducibility#matlab#power systems
One-click install
npx skills add https://github.com/BeopsooKim/Research-Bot --skill research-code-simulation-reviewer-beopsookim
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: research-code-simulation-reviewer
Source: https://github.com/BeopsooKim/Research-Bot/tree/main/.agents/skills/research-code-simulation-reviewer
Command: npx skills add https://github.com/BeopsooKim/Research-Bot --skill research-code-simulation-reviewer-beopsookim

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? Research code often runs without errors while producing scientifically weak or non-reproducible results. This Skill reviews MATLAB, Python, Julia, and simulation scripts for physical assumptions, unit consistency, solver configuration, and reproducibility before publication or thesis submission. ## Core Features & Use Cases - Scientific validity review: Checks model assumptions, units (MW/MVar/kV/p.u./Hz), sign conventions, and solver tolerances in power-flow, OPF, MCMC, and control code. - Reproducibility audit: Evaluates dependency declaration, data provenance, random seed control, and validation tests, then issues a verdict from "Looks reproducible" to "Likely scientifically invalid". - Static triage script: Includes a Python scanner that flags hardcoded paths, randomness usage, solver settings, and silent failures across a repository. - Use Case: Before submitting a paper, run the reviewer on your OPF simulation repository to catch inconsistent per-unit conventions, missing convergence checks, and undocumented solver settings. ## Quick Start Ask the assistant to review your research code repository for units, assumptions, solver settings, reproducibility, and result validity, providing the code path, study goal, and expected outputs.

Frequently Asked Questions about research-code-simulation-reviewer

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

FAQPage Schema
How do I review research code for reproducibility before publication?▼

Provide the code path, study goal, and expected outputs, and the reviewer checks dependency declaration, data provenance, random seed control, units, solver settings, and validation tests. It returns a verdict plus a reproducibility checklist and minimal patch plan.

What does the scan_research_code.py script check?▼

The script statically scans Python, MATLAB, Julia, and notebook files for hardcoded paths, randomness usage, power-system units, solver settings, time-sampling parameters, TODO markers, and silent failure patterns. It is a triage aid only and does not replace manual scientific review.

Can this review MATLAB power-flow and OPF simulation code?▼

Yes, it covers power-flow, OPF, fault analysis, VSC, and hybrid AC-DC simulations. It checks slack bus treatment, AC/DC approximation boundaries, per-unit conventions, converter limits, and sign conventions for injections and flows.

Does the code review support Korean language research workflows?▼

Yes, it responds in Korean when the user writes in Korean and in English for English input. Technical identifiers, equations, units, variable names, and citations are preserved in their original form regardless of response language.

When should I not use this code review skill?▼

Do not use it for generic web application code or pure writing review, since it targets research code and simulation pipelines. It also must not be used to fabricate results, hide anomalies, or bypass research-integrity requirements.

Related Skills

Explore More Education & Research Skills→
spiriMirrorspiriMirror
307

simulation-dev

Provides best practices for simulation code correctness, stability, and debuggability across CPU/GPU paths.

Official
Advanced
Weilong-QinWeilong-Qin

thesis-advisor-review

Review master's thesis sections and return executable revision guidance.

Community
Advanced
nahisahonahisaho
3

scientific-research-methodology

Creates structured research study designs with FINER ethics evaluation and bias control.

Community
Advanced
growilabsgrowilabs
1.5k

essential-test-design

Guide test authors to verify observable behavior instead of internal implementation details.

Official
Intermediate