Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mkurman/sdv
Synthetic Data Vault (SDV) — generate synthetic tabular data. Single-table, multi-table, and sequential data synthesis. CTGAN, TVAE, CopulaGAN, GaussianCopula. Privacy metrics and evaluation.
Passed 19 of 21 test cases with the skill, and 14 of 21 without it.
and 4 more in the full report
6 fixed14 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
From which module path should the load_demo helper function be imported when pulling demonstration datasets for tabular synthesis?
| Checked | Without skill | With skill |
|---|---|---|
| imports load_demo from sdv.datasets.demo | Missed | Passed |
The instructions your model reads when the skill loads.
The Synthetic Data Vault (SDV) generates synthetic tabular data that preserves statistical properties while protecting privacy. Supports single-table, multi-table, and sequential data generation with CTGAN, TVAE, CopulaGAN, and GaussianCopula models.
uv pip install sdv
from sdv.single_table import CTGANSynthesizer
from sdv.datasets.demo import load_demo
data, metadata = load_demo(dataset="census")
synth = CTGANSynthesizer(metadata)
synth.fit(data)
synthetic = synth.sample(num_rows=500)
print(synthetic.head())
print(f"Original columns: {data.shape}, Synthetic: {synthetic.shape}")
from sdv.multi_table import HMA1Synthesizer
synth = HMA1Synthesizer(multi_table_metadata)
synth.fit(multi_table_data)
synthetic = synth.sample(scale=0.5)
from sdv.evaluation import evaluate
test cases passed, vs 14 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.