skills.rest
EvolutionAPI
EvolutionAPIOFFICIAL
Explore all skills by this author →
GitHub

data-explore

Profile PostgreSQL tables or uploaded files to identify data quality issues.

520|175|Updated Apr 8, 2026
Search Tags:#postgresql#csv#data-quality#anomaly-detection#data-exploration#data-profiling
One-click install
npx skills add https://github.com/EvolutionAPI/evo-nexus --skill data-explore-evolutionapi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-explore
Source: https://github.com/EvolutionAPI/evo-nexus/tree/main/.claude/skills/data-explore
Command: npx skills add https://github.com/EvolutionAPI/evo-nexus --skill data-explore-evolutionapi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a fast, structured way to inspect a new table or uploaded file to understand shape, data quality, distributions, and obvious anomalies before deeper analysis or reporting. It reduces guesswork by automatically computing coverage, null rates, cardinality, common values, numeric and temporal summaries, and naming likely identifiers and dimensions.

Core Features & Use Cases

  • Automated profiling: Counts, column-type breakdowns, null rates, distinct counts, top/bottom values and sampling for large tables.
  • Quality checks and alerts: Flags high null rates, placeholder values, duplicates, impossible values, and encoding/format inconsistencies.
  • Relationship discovery: Suggests candidate foreign keys, derived columns, redundant fields, correlations and natural hierarchies for analysis.
  • Use cases: Onboard a new PostgreSQL table, inspect CSV/Excel uploads, or sample data from Stripe/Omie/Evo CRM to decide dimensions, metrics and follow-up queries.

Quick Start

Use the data-explore skill to profile the target table or uploaded file by naming it, for example run the data-explore operation on customers_2024.csv

Frequently Asked Questions about data-explore

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

FAQPage Schema
How do I profile a CSV file to check data quality and null rates?▼

Data profiling for CSV files involves automated column classification, null rate checks, and cardinality analysis. This identifies high null rates, placeholder values, and duplicates to surface data issues quickly.

What is data exploration and how does it find anomalies in a PostgreSQL table?▼

Data exploration inspects dataset shape and distributions to identify obvious anomalies. It performs numeric and temporal summaries alongside anomaly detection to flag impossible values and format inconsistencies in PostgreSQL tables.

Can I inspect uploaded Parquet or Excel files for data profiling?▼

Yes, you can inspect uploaded CSV, Excel, Parquet, and JSON files for data profiling. The tool performs initial discovery and analysis on these formats, computing coverage, cardinality, and common values.

How do I discover relationships and candidate foreign keys in a dataset?▼

Relationship discovery analyzes your dataset to suggest candidate foreign keys, derived columns, and natural hierarchies. It identifies redundant fields and correlations to recommend dimensions and metrics for follow-up analysis.

Does data exploration work with Stripe or CRM sources for initial analysis?▼

Yes, data exploration works with Stripe, Omie, Licensing, and Evo CRM sources. You can sample data from these platforms to decide on dimensions, metrics, and follow-up queries before deeper reporting.

What's the best way to identify data quality issues before reporting?▼

The best way to identify data quality issues is running automated quality checks and alerts. These flag duplicates, impossible values, encoding inconsistencies, and high null rates to reduce guesswork before deeper analysis.

Related Skills

Explore More Data & Analytics Skills→
frumu-aifrumu-ai
114

data-explore-data

Profile datasets from warehouses and uploaded files to generate table and column metrics.

Official
Intermediate
anthropicsanthropics
23.4k

explore-data

Profile tables and files to assess structure, quality, and patterns.

Official
Intermediate
EvolutionAPIEvolutionAPI
520

pm-metrics-review

Compile product metrics from Stripe, Licensing, and Evo CRM into a structured review.

Official
Advanced
milasaurusmilasaurus

ml-anomalies

Detect and explain anomalies in datasets using Isolation Forest and Local Outlier Factor.

Community
Advanced