skills.rest
dmitryprg-ai
dmitryprg-aiCOMMUNITY
Explore all skills by this author →
GitHub

research

Analyze CSV, Parquet, SQL, or pandas datasets through structured profiling and hypothesis testing.

9|2|Updated Jan 9, 2026
Search Tags:#data#sql#pandas#analyze#parquet#datasets
One-click install
npx skills add https://github.com/dmitryprg-ai/cursor-develop-autorules --skill research-dmitryprg-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/dmitryprg-ai/cursor-develop-autorules/tree/main/.cursor/skills/research
Command: npx skills add https://github.com/dmitryprg-ai/cursor-develop-autorules --skill research-dmitryprg-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analysts and AI agents waste time reasoning through messy data; this protocol provides a structured approach to load, schema-verify, profile, hypothesize, experiment, and document findings to produce reliable insights.

Core Features & Use Cases

  • Workflow steps: LOAD, SCHEMA, PROFILE, HYPOTHESIS, EXPERIMENT, DOCUMENT for repeatable analyses.
  • Multi-language support: SQL, TypeScript, and Python/pandas workflows for schema inspection, profiling, and experimentation.
  • Use Case: When you have a dataset in CSV or Parquet, use this protocol to build a quick data quality report and validate hypotheses with a small experiment.

Quick Start

Load your dataset, validate its schema, run a small experiment, and document results.

Frequently Asked Questions about research

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

FAQPage Schema
How do I analyze a CSV or Parquet dataset to validate data quality and test hypotheses?▼

SQL and pandas are fully supported for data exploration, schema inspection, and profiling. You can use SQL queries or Python pandas pipelines to load datasets, verify schemas, run experiments, and document analytical findings across multiple languages.

What is the best way to structure a data analysis workflow for reproducible results?▼

A structured data analysis workflow follows sequential steps: LOAD, SCHEMA, PROFILE, HYPOTHESIS, EXPERIMENT, and DOCUMENT. Applying this protocol ensures repeatable analyses, reliable insights, and consistent documentation across CSV, Parquet, SQL, and Python pipelines.

Can I use SQL and pandas together for dataset profiling and schema verification?▼

SQL and pandas are fully supported for data exploration, schema inspection, and profiling. You can use SQL queries or Python pandas pipelines to load datasets, verify schemas, run experiments, and document analytical findings across multiple languages.

Does this data analysis approach work for experiment design and hypothesis testing?▼

Yes, the workflow explicitly supports hypothesis formulation, experiment design, and testing. After loading and profiling your dataset, you define hypotheses, execute experiments to validate them, and document the results for structured analytical insights.

How do I build a quick data quality report from a messy dataset?▼

Build a data quality report by loading your dataset and running the schema verification and profiling workflow steps. This process inspects data structure, identifies risks, and documents anomalies to produce a reliable quality assessment quickly.

Related Skills

Explore More Data & Analytics Skills→
winstonkoh87winstonkoh87
558

data-analysis

Ingest JSON, CSV, and Parquet files into DuckDB for SQL-based analysis.

Community
Intermediate
pluginagentmarketplacepluginagentmarketplace
3

red-team-reporting

Generate security assessment reports from structured findings in Markdown, HTML, PDF, or DOCX.

Community
Basic
Phife726Phife726

data-analyst

Analyze datasets with SQL, pandas, and statistical methods.

Community
Intermediate
anton-abyzovanton-abyzov
156

anomaly-detector

Detect anomalies and outliers using statistical methods, Isolation Forest, and autoencoders.

Community
Advanced