syntherklaas

Syntherklaas: interactive synthetic data generator

Real data is the fastest way to prototype.
GDPR is the fastest way to get blocked.

A good synthetic dataset is a gift — and you don't have to wait until December.

The problem

On most projects the first question is: what data do you have? And the answer is usually "none", "not enough", or "we have it but GDPR makes it off-limits".

syntherklaas skips the input-data step entirely: you have a short conversation about the shape you need — tables, columns, foreign keys, volumes, distributions — and it generates a coherent synthetic dataset from scratch.

Built on Faker (locale-aware) plus NL-locked providers for BSN (11-proof), IBAN (mod-97), postcode, and phone formats — fake values that still pass real validators. Packaged as a Claude Code skill: the dialog runs in chat, the schema is captured as a YAML, and a small Python generator turns that YAML into CSV, XLSX, SQLite, or a SQL dump.

Watch the 2-minute intro

▶ Watch on Veed — a quick tour: define two related tables, see the data model, pick volume distributions, and pick an output format.

Installation

Only tested with Claude Code.

npx skills@latest add baswenneker/syntherklaas

Restart Claude Code (or open a new session). The skill registers via .claude-plugin/plugin.json.

What a conversation looks like

The dialog is the product. You name the tables and columns; Claude picks the providers, infers the foreign keys, renders the model, and asks the right follow-ups. Here's a session — slightly compressed, but faithful to the real flow.

You: /syntherklaas

Claude: Which table do we start with? You can paste sample data, define columns together, or just give me a table name and I'll propose one.

You: users — user_id, first_name, last_name, bsn, email

Claude: Inferred for users:

col	provider	constraint	example
user_id	sequential	PK	1, 2, 3, ...
first_name	faker.first_name		Pieter
last_name	faker.last_name		Jansen
bsn	nl.bsn	UNIQUE	391171823
email	faker.email		[email protected]

Look right? (ok / change <col>)

You: ok. Next: invoices — invoice_id, user_id, description, amount, iban

Claude: Inferred for invoices:

col	provider	constraint	example
invoice_id	sequential	PK	1, 2, 3, ...
user_id	fk → users.user_id	NOT NULL	1..1000
description	faker.text		"Lorem ipsum..."
amount	numeric_range (uniform)		137.42
iban	nl.iban		NL34RABO0382...

Model so far:

┌─────────────────────────┐         ┌─────────────────────────┐
│ users                   │ 1     * │ invoices                │
├─────────────────────────┤─────────┤─────────────────────────┤
│ user_id (PK)   INT      │         │ invoice_id (PK)  INT    │
│ first_name     STR      │         │ user_id (FK)     INT ───┤
│ last_name      STR      │         │ description      STR    │
│ bsn (UQ)       STR      │         │ amount           FLOAT  │
│ email          STR      │         │ iban             STR    │
└─────────────────────────┘         └─────────────────────────┘

Another table, or done?

You: done.

Claude: Volumes per table — pick a distribution:

• Fixed — exact row count
• Poisson λ — natural variation around λ (e.g. "around 5 invoices per user")
• Normal μ ± σ — bell-shaped
• Uniform [min, max] — or just describe it in words

How many users? And how many invoices per user?

You: 1000 users; around 5 invoices per user.

Claude: Preview (10 rows per table)...

users (1000 total)
| user_id | first_name | last_name        | bsn       | email                  |
| 1       | Ali        | Schellekens      | 391171823 | leonholthuis@example…  |