skills.rest
gerardovitale
gerardovitaleCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

quant-review

Automate review of analytics pipelines for mathematical correctness, statistical validity, and data quality.

Updated Oct 8, 2024
Search Tags:#code review#data quality#data science#statistical analysis#analytics review
One-click install
npx skills add https://github.com/gerardovitale/travel-assistant --skill quant-review-gerardovitale
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: quant-review
Source: https://github.com/gerardovitale/travel-assistant/tree/main/.claude/skills/quant-review
Command: npx skills add https://github.com/gerardovitale/travel-assistant --skill quant-review-gerardovitale

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the review of analytics pipelines and reports for mathematical correctness, statistical validity, and data quality, streamlining the process of ensuring high-quality data and analyses.

Core Features & Use Cases

  • Data Quality Audit: Performs a comprehensive audit of analytics files, evaluating them against six dimensions of data quality.
  • Statistical Soundness Review: Ensures the statistical validity of analyses, including checks for Markov chain assumptions and sample size adequacy.
  • Performance Review: Identifies potential performance bottlenecks in queries and data processing.
  • Report Generation: Automatically generates new analytics reports based on project patterns and data quality best practices.
  • Use Case: For a data team working on complex analytics, this Skill can quickly validate the quality of their pipelines and reports, saving time and reducing errors.

Quick Start

Run the 'quant-review' skill on your analytics file 'brand_comparison.py' to perform a targeted audit.

Frequently Asked Questions about quant-review

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

FAQPage Schema
How do I automate data quality audits for analytics pipelines?▼

You can review analytics pipelines for statistical soundness by executing a targeted audit script that checks your Python files for mathematical correctness, sample size adequacy, and Markov chain assumptions.

What does a statistical soundness review check for in data science workflows?▼

A statistical soundness review in data science workflows checks for mathematical correctness, statistical validity, sample size adequacy, and Markov chain assumptions to validate the quality of your analytical reports.

Can I use Python and pandas to validate the mathematical correctness of analytics reports?▼

Yes, you can validate the mathematical correctness of analytics reports using Python with pandas, numpy, scipy, and sqlalchemy dependencies to process data and audit pipeline outputs automatically.

What is the best way to identify performance bottlenecks in data processing queries?▼

The best way to identify performance bottlenecks in data processing queries is through an automated review that analyzes your analytics files and flags potential inefficiencies in queries and data pipelines.

Does this data quality audit work with sqlalchemy database connections?▼

Yes, the data quality audit works with sqlalchemy database connections as a required dependency, allowing you to review analytics pipelines that pull from relational databases for statistical validity and performance issues.

How do I generate new analytics reports based on data quality best practices?▼

Generate new analytics reports based on data quality best practices by running an automated review that analyzes your project patterns and outputs validated reports reflecting statistical soundness and mathematical correctness.

Related Skills

Explore More Data & Analytics Skills→
echo-iceecho-ice

python-model-code-generator

Generate executable Python modeling code from validated method plans and cleaned data.

Community
Advanced
viniruggeriviniruggeri

seaborn

Create publication-quality statistical visuals from Pandas DataFrames.

Community
Advanced
einverneeinverne
119

performance-optimizer

Profile code and systems to identify and resolve performance bottlenecks.

Community
Advanced
MuhammadUAMuhammadUA

exploration

Profile unknown datasets for structure, quality, and patterns.

Community
Intermediate