skills.rest
bcmcpher
bcmcpherCOMMUNITY
Explore all skills by this author →
𝕏@bcmcpherGitHub

gen-data-dict

Generate a JSON data dictionary describing variables in merged CSV, TSV, or Parquet datasets.

1|Updated Feb 25, 2026
Search Tags:#metadata#generate#dataset#data-dictionary#tabular#bids
One-click install
npx skills add https://github.com/bcmcpher/my-skills --skill gen-data-dict
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gen-data-dict
Source: https://github.com/bcmcpher/my-skills/tree/main/plugins/stat-analysis/skills/gen-data-dict
Command: npx skills add https://github.com/bcmcpher/my-skills --skill gen-data-dict

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This tool automatically generates a standardized, human-readable data dictionary for every variable in a merged or analysis-ready dataset, enabling consistent metadata documentation and sharing in BIDS-style formats.

Core Features & Use Cases

  • Annotates each column with a descriptive label, data type, cardinality, sample values, and null fraction.
  • Produces a JSON data dictionary named <input_stem>_data_dictionary.json that can be used for data governance, reproducibility, and data sharing.
  • Useful when preparing merged TSV/CSV or Parquet files for neuroimaging, clinical, or analytics projects, or when documenting a dataset for publication.

Quick Start

Provide a merged input file (e.g., merged.tsv) to generate the data dictionary in the same directory.

Frequently Asked Questions about gen-data-dict

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

FAQPage Schema
How do I generate a data dictionary for a CSV or TSV dataset?▼

You can generate a data dictionary by providing a merged CSV, TSV, or Parquet file, which produces a JSON file annotating each variable with type, cardinality, sample values, and null fraction.

What is a BIDS-style data dictionary and when do I need one?▼

A BIDS-style data dictionary is a standardized JSON metadata file describing dataset variables. You need one for consistent data governance, sharing, and reproducibility in neuroimaging or clinical projects.

Does generating a data dictionary modify my original dataset file?▼

Generating a data dictionary does not modify your original file. It creates a separate JSON output named <input_stem>_data_dictionary.json in the same directory, leaving the source data untouched.

Can I use this tool to document a Parquet file for data governance?▼

Yes, you can document a Parquet file for data governance. The tool reads common tabular formats like Parquet and outputs a JSON dictionary with descriptive labels and null fractions for every column.

What metadata does an automated data dictionary capture for each column?▼

An automated data dictionary captures descriptive labels, data types, cardinality, sample values, and null fractions for each column, providing a comprehensive overview of your merged dataset's schema.

What happens if my merged dataset schema evolves after generating the dictionary?▼

If your merged dataset schema evolves, you can re-run the tool on the updated file to regenerate the JSON data dictionary, ensuring your metadata documentation stays synchronized with the current data structure.

Related Skills

Explore More Data & Analytics Skills→
bcmcpherbcmcpher

merge-data

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

Community
Advanced
galeepgaleep

bids

Organize, query, validate, and convert neuroscience datasets to BIDS standards.

Community
Advanced
GACLoveGACLove
2

data-exploration

Profile tabular datasets to assess structure, quality, and distribution.

Community
Intermediate
ScottHMcKeanScottHMcKean

databricks-unstructured-pdf-generation

Generates synthetic PDFs and JSON metadata for RAG datasets via generate_pdf_documents MCP tool.

Community
Intermediate