skills.rest
nahisaho
nahisahoCOMMUNITY
Explore all skills by this author →
GitHub

scientific-data-profiling

Profile datasets with ydata-profiling and Great Expectations to generate EDA reports and quality scores.

3|1|Updated Feb 11, 2026
Search Tags:#eda#data-quality#correlation#great-expectations#type-inference#data-profiling#data-catalog
One-click install
npx skills add https://github.com/nahisaho/satori --skill scientific-data-profiling
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scientific-data-profiling
Source: https://github.com/nahisaho/satori/tree/main/src/.github/skills/scientific-data-profiling
Command: npx skills add https://github.com/nahisaho/satori --skill scientific-data-profiling

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides automated data profiling and quality assessment workflows, combining ydata-profiling for EDA with Great Expectations for validation and automatic metadata generation.

Core Features & Use Cases

  • Automated EDA Reports: generate comprehensive profiling reports from datasets.
  • Data Quality Scoring & Validation: compute quality scores and enforce validation rules.
  • Data Catalog Generation: auto-create a data dictionary for datasets.
  • Use Case: ingest a new dataset and instantly obtain profiling results, quality scores, and a validation plan.

Quick Start

Run automated profiling and quality validation on a dataset to generate a profile_report.html and quality_score.json

Frequently Asked Questions about scientific-data-profiling

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

FAQPage Schema
How do I automate data profiling and quality checks for a new dataset?▼

Automated data profiling generates EDA reports, quality scores, and a data dictionary by applying ydata-profiling and Great Expectations to infer types and validate rules.

What is automated EDA reporting and how does type inference work?▼

Automated EDA reporting analyzes datasets to produce profiling summaries, while type inference automatically detects column data types to generate an accurate data catalog and dictionary.

Can I use Great Expectations with ydata-profiling to validate data quality?▼

Yes, data quality assessment combines ydata-profiling for EDA with Great Expectations to compute quality scores and enforce automated validation rules.

What is the best way to generate a data dictionary and catalog from raw data?▼

Generating a data dictionary is best handled by automated data profiling, which applies type inference to raw datasets to auto-create structured metadata and catalog entries.

What outputs do I get from running automated data profiling on a dataset?▼

Running data profiling outputs an EDA profile report in HTML format and a quality score in JSON, alongside an auto-generated data dictionary and validation plan.

Do I need to install any dependencies to run automated data profiling and validation?▼

No external dependencies are required to run the data profiling and validation workflow, as the Skill integrates the underlying ydata-profiling and Great Expectations logic internally.

Related Skills

Explore More Data & Analytics Skills→
Adelie-SquadAdelie-Squad
17

Data Engineer Agent

Profile, clean, and transform raw datasets into analysis-ready tables with pandas.

Official
Advanced
microsoftmicrosoft
224

emit-sarif

Serialize AI-generated security findings as SARIF v2.1.0 logs.

Official
Advanced
jose-compujose-compu

self-improving-analytics

Log analytics learnings, data issues, and feature requests to markdown files.

Community
Advanced
swarm-ai-researchswarm-ai-research

Programmatic EDA

Profile local CSV, Parquet, and Excel datasets with pandas and numpy, outputting Markdown reports.

Official
Intermediate