skills.rest
fredmilhome
fredmilhomeCOMMUNITY
Explore all skills by this author →
GitHub

diagnose

Diagnose root causes of empirical research code errors in R, Stata, and Python.

Updated Jun 27, 2026
Search Tags:#root cause analysis#data analysis#code debugging#research code#empirical research
One-click install
npx skills add https://github.com/fredmilhome/laffer_tobacco --skill diagnose-fredmilhome
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: diagnose
Source: https://github.com/fredmilhome/laffer_tobacco/tree/main/.claude/skills/diagnose
Command: npx skills add https://github.com/fredmilhome/laffer_tobacco --skill diagnose-fredmilhome

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of identifying the root cause of empirical research code errors, streamlining the debugging process for research code (R/Stata/Python).

Core Features & Use Cases

  • Root Cause Analysis: Provides a structured approach to diagnose and identify the root cause of empirical research code errors.
  • Symptom-Driven: Uses a symptom-driven approach to focus on specific issues like silent wrong numbers, script errors, and reproducibility issues.
  • Use Case: When a research code fails to reproduce, returns an unexpected number, or exhibits other issues, this Skill can help pinpoint the source of the problem.

Quick Start

Run the 'diagnose' skill on your research code with the error symptom as the input, e.g., 'diagnose "My script errors out" --no-fix'.

Frequently Asked Questions about diagnose

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

FAQPage Schema
How do I diagnose the root cause of empirical research code errors?▼

To diagnose empirical research code errors, use a structured debugging loop applying reproduce-minimise-hypothesise-instrument-fix approaches to pinpoint root causes across R, Stata, and Python scripts.

Why does my research script return a silent wrong number during data analysis?▼

A silent wrong number during data analysis often stems from undetected logical flaws. A symptom-driven diagnostic approach isolates the specific data issue by minimising the failing code to reveal the root cause.

Can I use a structured debugging loop for Stata and Python reproducibility issues?▼

Yes, structured debugging loops support reproducibility issues in Stata and Python. By hypothesising and instrumenting the code, you can identify why the empirical research script fails to reproduce expected outputs.

What is the best way to debug deterministic task failures in R scripts?▼

The best way to debug deterministic task failures in R scripts is applying a disciplined reproduce-minimise-hypothesise-instrument-fix approach to systematically isolate and resolve the root cause of the error.

Do I need to provide error symptoms to debug empirical research code?▼

Yes, you need to provide error symptoms to debug empirical research code effectively. Supplying the specific symptom, like a script error, allows the diagnostic process to accurately target the underlying issue.

Related Skills

Explore More Education & Research Skills→
wangyouanwangyouan

stata-regression-workflow

Automate Stata regression workflows with log inspection and CSV/XLSX result reporting.

Community
Intermediate
naj2rnaj2r

review-r

Review R scripts and Quarto chapters for reproducibility and correctness.

Community
Intermediate
kriangkraiiikriangkraiii
2

systematic-debugging

Apply a four-phase debugging process for root cause analysis and verification.

Community
Intermediate
w020316w020316

bugfix-workflow

Automate bug-fix workflows from reproduction through reporting.

Community
Advanced