merge-data

Merge tabular data files into a single analysis-ready dataframe.

1|Updated Feb 25, 2026
One-click install
npx skills add https://github.com/bcmcpher/my-skills --skill merge-data
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: merge-data
Source: https://github.com/bcmcpher/my-skills/tree/main/plugins/stat-analysis/skills/merge-data
Command: npx skills add https://github.com/bcmcpher/my-skills --skill merge-data

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Helps users merge and harmonize a folder of tabular data files into a single analysis-ready dataframe without modifying the source files.

Core Features & Use Cases

  • Automatic discovery and inventory of supported formats (CSV, TSV, Excel, JSON, Parquet, and more).
  • Per-file profiling, schema alignment, and optional data-quality checks to prepare a consistent merged dataset.
  • Generate a runnable Python (or R/Julia) script that reads, merges, validates, and optionally outputs a data dictionary.

Quick Start

Provide the path to a folder of tabular files when prompted and run the generated script to merge all recognized files.

Frequently Asked Questions about merge-data

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

FAQPage Schema
How do I merge multiple CSV and Excel files into a single dataset?

To merge multiple CSV and Excel files into a single dataset, you provide a folder path to the Skill. It automatically discovers supported tabular files, profiles them, and generates a runnable script that consolidates the data into one analysis-ready dataframe.

What is the best way to consolidate mixed tabular data formats like Parquet, TSV, and JSON?

Consolidating mixed tabular data formats like Parquet, TSV, and JSON is handled through automatic file discovery and schema alignment. The Skill inspects each file, aligns the schemas, and outputs a runnable script to harmonize the diverse formats into a unified dataframe.

Does merging tabular data files modify the original source exports?

Merging tabular data files does not modify the original source exports. The Skill enforces a strict read-only constraint on your source data, ensuring all profiling, schema alignment, and consolidation happen without altering the initial files.

How do I generate a data dictionary and perform validation when combining datasets?

To generate a data dictionary and perform validation when combining datasets, the Skill profiles each file and applies optional data-quality checks. The final runnable script includes commands to validate the merged dataframe and optionally output a data dictionary.

Can I use this approach to combine a folder of tabular exports for Python analysis?

You can use this approach to combine a folder of tabular exports for Python analysis. The Skill generates a ready-to-run Python script that handles file discovery, merging, and validation, producing an analysis-ready dataframe immediately available for your projects.

What are the limitations when profiling and harmonizing a folder of tabular data files?

Limitations when profiling and harmonizing a folder of tabular data files include relying on supported formats like CSV, TSV, Excel, JSON, and Parquet. The Skill handles schema alignment and optional quality checks but requires all target files to be accessible within the specified folder path.