skills.rest
Sir-chawakorn
Sir-chawakornCOMMUNITY
Explore all skills by this author →
GitHub

profile-dataset

Analyze structured datasets to generate summary statistics and data quality reports.

9|3|Updated Jun 13, 2026
Search Tags:#profiling#statistics#eda#data-quality#data-cleaning#outlier-detection
One-click install
npx skills add https://github.com/Sir-chawakorn/sanook-cli --skill profile-dataset-sir-chawakorn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: profile-dataset
Source: https://github.com/Sir-chawakorn/sanook-cli/tree/main/skills/profile-dataset
Command: npx skills add https://github.com/Sir-chawakorn/sanook-cli --skill profile-dataset-sir-chawakorn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the uncertainty of working with new or unknown datasets by providing an automated, comprehensive exploratory data analysis that identifies hidden quality issues and statistical characteristics.

Core Features & Use Cases

  • Automated EDA: Generates summary statistics, distribution insights, and correlation analysis without manual coding.
  • Data Quality Auditing: Automatically flags missing values, outliers, disguised data, and structural anomalies with severity ratings.
  • Use Case: When you receive a raw CSV or database export and need to understand its health, schema, and potential pitfalls before starting your analysis or modeling pipeline.

Quick Start

Use the profile-dataset skill to analyze the provided data file and generate a quality report highlighting any high-severity issues.

Frequently Asked Questions about profile-dataset

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

FAQPage Schema
How do I perform exploratory data analysis on a CSV file to check data quality?▼

Exploratory data analysis on a CSV file automatically surfaces summary statistics, distribution patterns, and data quality issues like missing values and outliers. This process performs schema inference and non-destructive inspection to identify potential pitfalls before modeling pipelines.

Can I use automated profiling to detect outliers and missing values in a Parquet dataset?▼

Automated profiling detects outliers and missing values in a Parquet dataset by applying comprehensive statistical analysis. It identifies missing-value patterns and structural anomalies, providing severity ratings to help you understand the health of your structured data.

What is the best way to audit the schema and quality of an unknown database table export?▼

Auditing an unknown database table export is best handled by automated exploratory data analysis. This approach performs rapid schema inference, flags disguised data, and highlights structural anomalies with severity ratings, ensuring non-destructive inspection of the structured dataset.

Does automated dataset profiling work without writing manual code for statistical analysis?▼

Automated dataset profiling works without manual coding by automatically generating summary statistics, distribution insights, and correlation analysis. It conducts comprehensive exploratory data analysis on structured datasets to surface hidden quality issues and statistical characteristics directly.

What are the limitations of using automated EDA for data cleaning and outlier detection?▼

The primary limitation of automated EDA for data cleaning is that it performs non-destructive inspection only. While it effectively flags outliers, disguised data, and missing-value patterns with severity ratings, it surfaces issues for review rather than automatically modifying or cleaning the raw dataset.

Related Skills

Explore More Data & Analytics Skills→
FunnelEnvyFunnelEnvy
1

gcp-bq-data-loading

Load CSV, JSON, Avro, and Parquet data into BigQuery.

Official
Advanced
Veloxia-agencyVeloxia-agency

data-quality-auditor

Audit CSV datasets for completeness, consistency, validity, uniqueness, and timeliness.

Community
Advanced
Weiwei-MaoWeiwei-Mao
2

csv-data-summarizer

Analyze CSV files to generate statistical summaries and visualizations.

Community
Intermediate
hung-phanhung-phan
1

eda

Perform exploratory data analysis with statistical summaries, correlation, and outlier detection.

Community
Advanced