data-designer
CommunityGenerate high-quality synthetic datasets.
Data & Analytics#test data#synthetic data#dataset generation#data sampling#llm data generation#data schema
Authorbacoco
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill automates the creation of synthetic datasets, combining statistical methods with LLM capabilities to generate realistic data for various purposes without requiring external API keys.
Core Features & Use Cases
- Statistical Samplers: Generate data from distributions, categories, personas, dates, and more.
- LLM Column Generation: Use Claude to generate text, code, or structured data based on defined prompts.
- Schema-Driven Generation: Define dataset structure, column types, and dependencies in a schema file.
- Use Case: Generate 50 realistic product reviews with associated ratings, categories, and customer information for testing an e-commerce recommendation engine.
Quick Start
Use the data-designer skill to generate 50 product reviews with ratings from 1 to 5.
Dependency Matrix
Required Modules
numpyscipyfakerpyyamljinja2jsonschemapandaspyarrowruff
Components
scriptsreferences
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: data-designer Download link: https://github.com/bacoco/Data-designer-skill/archive/main.zip#data-designer Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.