Open Prompts
Submit a prompt
Analysis

Build A Full Data Dictionary

Documents a dataset column by column for a team about to receive it, using its name, source system, refresh frequency, and column list as inputs. - Per column: type, business meaning, source, valid values or range, null handling - Also covers: dependencies, known quality issues, and 3-5 example values - Output: a clean markdown table plus a JSON schema ready for automated validation

Prompt
Build a thorough data dictionary for this dataset:

Dataset name: {dataset_name}
Source system: {source_system}
Refresh frequency: {refresh_frequency}
Columns:
{column_list}

Known information:
{existing_docs}

For every column, document:
1. Column name and any aliases
2. Data type (string, integer, float, date, boolean, etc.)
3. Business-language description of what the field represents
4. Source (user input, calculated, system-generated, etc.)
5. Possible values (categorical) or valid range (numeric)
6. Null handling (is null allowed, and what does it mean?)
7. Business rules (transformations, validations, dependencies)
8. Related columns (foreign keys, calculated-from relationships)
9. Known data quality issues
10. 3-5 representative example values

Format this as both a clean markdown table and a JSON schema for automated validation.
Download .md

Variables

Related prompts

Analysis

Assess Dataset Quality Before Analysis

Audits a dataset's health before analysis starts, using its columns, row count, source, time range, and a sample of rows to spot missing values, type mismatches, likely outliers, duplicate rows, and inconsistent categorical entries. Returns a 1-10 quality score with reasoning and a concrete cleaning step for every issue found, making it a natural first pass before writing any cleaning script.

Analysis

Build A Data Validation Framework

Builds a repeatable validation suite for a dataset you'll keep receiving, based on its description, columns, and stated business rules. Produces per-column checks, cross-column business-logic rules, and statistical sanity checks, then wraps them into a Python script that reports failure counts per rule, sample bad rows, an overall quality score, and a priority order for fixes.

Analysis

Create A Reusable KPI Report Template

Builds a fill-in-ready KPI report template for a business area, its KPI list, reporting frequency, and audience, meant to be generated once and reused every period. Includes a header section, a red/yellow/green scorecard, per-KPI detail with trend and variance from target, a commentary section, action items for underperforming metrics, and a data-definitions appendix explaining how each number is calculated.