data-profiler

Generate a data dictionary and profile report from CSV or Excel files.

8|Updated Mar 18, 2026

Search Tags:#data-dictionary #missing-values #data-profile #data-profiler #variable-hierarchy #populations

Ready to run

npx skills add https://github.com/TerryFYL/ai-research-army --skill data-profiler

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-profiler
Source: https://github.com/TerryFYL/ai-research-army/tree/main/skills/data-profiler
Command: npx skills add https://github.com/TerryFYL/ai-research-army --skill data-profiler

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

数据探查与数据字典生成。触发条件: (1) 用户提供新的 CSV/Excel 数据文件, (2) 说"探查数据"/"数据画像"/"data profile"/"生成数据字典", (3) 在分析之前需要全面了解数据结构。核心能力: 自动生成数据字典、检测变量层级关系、评估缺失模式、定义分析人群，为后续所有分析结除"盲猜列名"和"NaN崩溃"的风险。

Core Features & Use Cases

自动生成 data_dictionary.md 和 data_profile_report.md，提供完整的数据字典和数据质量概览。
自动化变量层级关系检测，帮助区分细粒度变量与聚合变量，避免混淆。
缺失模式分析与分析人群定义，为后续分析和统计建模提供稳健的输入。
适用于新数据导入、研究设计准备、数据清洗前的探索性分析。

Quick Start

Provide a CSV or Excel file path and command the system to generate the data dictionary and population definitions.

Frequently Asked Questions about data-profiler

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

FAQPage Schema

How do I automatically generate a data dictionary for a CSV file?▼

To automatically generate a data dictionary for a CSV file, provide the file path and trigger the data profiling process, which outputs a structured data_dictionary.md detailing variable types and descriptions.

What is data profiling and how does it reveal variable hierarchies?▼

Data profiling is the automated examination of datasets to assess structure and quality. It reveals variable hierarchies by distinguishing granular variables from aggregated ones, preventing confusion during analysis.

Can I use automated data profiling for Excel files before statistical modeling?▼

Yes, you can use automated data profiling for Excel files before statistical modeling. It evaluates missing patterns and defines analysis populations, providing robust inputs to prevent NaN-related crashes.

What is the best way to profile new datasets without manually inspecting columns?▼

The best way to profile new datasets without manual column inspection is running an automated profiling command. It generates a data_profile_report.md and analysis_populations.md, handling numeric, categorical, and datetime types.

Does automated data profiling handle missing values and datetime types?▼

Yes, automated data profiling handles missing values and datetime types. It assesses missing patterns across the dataset and correctly processes datetime columns alongside numeric and categorical variables.

Why define analysis populations before exploratory data analysis?▼

Defining analysis populations before exploratory data analysis is crucial because it segments data into coherent groups, mitigating blind guesses on column names and ensuring robust statistical modeling inputs.