data-designer
Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.
Install
npx skills add https://github.com/NVIDIA/skills/tree/main/skills/data-designer
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install nvidia-skills@llmmart
git clone https://github.com/NVIDIA/skills.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole nvidia/skills collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
Before You Start
Do not explore the workspace first. The workflow's Learn step gives you everything you need.
Goal
Build a synthetic dataset using the Data Designer library that matches this description:
$ARGUMENTS
Workflow
Use Autopilot mode if the user implies they don't want to answer questions — e.g., they say something like "be opinionated", "you decide", "make reasonable assumptions", "just build it", "surprise me", etc. Otherwise, use Interactive mode (default).
Read only the workflow file that matches the selected mode, then follow it:
- Interactive → read
workflows/interactive.md - Autopilot → read
workflows/autopilot.md
Rules
- Keep all columns in the output by default. The only exceptions for dropping a column are: (1) the user explicitly asks, or (2) it is a helper column that exists solely to derive other columns (e.g., a sampled person object used to extract name, city, etc.). When in doubt, keep the column.
- Do not suggest or ask about seed datasets. Only use one when the user explicitly provides seed data or asks to build from existing records. When using a seed, read
references/seed-datasets.md. - When the dataset requires person data (names, demographics, addresses), read
references/person-sampling.md. - If a dataset script that matches the dataset description already exists, ask the user whether to edit it or create a new one.
Usage Tips and Common Pitfalls
- Sampler and validation columns need both a type and params. E.g.,
sampler_type="category"withparams=dd.CategorySamplerParams(...). - Jinja2 templates in
prompt,system_prompt, andexprfields: reference columns with{{ column_name }}, nested fields with{{ column_name.field }}. SamplerColumnConfig: Takesparams, notsampler_params.- LLM judge score access:
LLMJudgeColumnConfigproduces a nested dict where each score name maps to{reasoning: str, score: int}. To get the numeric score, use the.scoreattribute. For example, for a judge column namedqualitywith a score namedcorrectness, use{{ quality.correctness.score }}. Using{{ quality.correctness }}returns the full dict, not the numeric score.
Troubleshooting
data-designerCLI not found: Tell the user thatdata-designeris not installed in this environment (requires Python >= 3.11). Ask if they would like you to create a virtual environment and install it, or if they prefer to do it themselves. Do not install anything without the user's permission.- Network errors during preview: A sandbox environment may be blocking outbound requests. Ask the user for permission to retry the command with the sandbox disabled. Only as a last resort, if retrying outside the sandbox also fails, tell the user to run the command themselves.
Output Template
Write a Python file to the current directory with a load_config_builder() function returning a DataDesignerConfigBuilder. Name the file descriptively (e.g., customer_reviews.py). Use PEP 723 inline metadata for dependencies.
# /// script
# dependencies = [
# "data-designer", # always required
# "pydantic", # only if this script imports from pydantic
# # add additional dependencies here
# ]
# ///
import data_designer.config as dd
from pydantic import BaseModel, Field
# Use Pydantic models when the output needs to conform to a specific schema
class MyStructuredOutput(BaseModel):
field_one: str = Field(description="...")
field_two: int = Field(description="...")
# Use custom generators when built-in column types aren't enough
@dd.custom_column_generator(
required_columns=["col_a"],
side_effect_columns=["extra_col"],
)
def generator_function(row: dict) -> dict:
# add custom logic here that depends on "col_a" and update row in place
row["name_in_custom_column_config"] = "custom value"
row["extra_col"] = "extra value"
return row
def load_config_builder() -> dd.DataDesignerConfigBuilder:
config_builder = dd.DataDesignerConfigBuilder()
# Seed dataset (only if the user explicitly mentions a seed dataset path)
# config_builder.with_seed_dataset(dd.LocalFileSeedSource(path="path/to/seed.parquet"))
# config_builder.add_column(...)
# config_builder.add_processor(...)
return config_builder
Only include Pydantic models, custom generators, seed datasets, and extra dependencies when the task requires them.
Files (skills)
-
evals
-
config.yml 1.5 KB
Loading… -
evals.json 1.4 KB
Loading…
-
-
references
-
person-sampling.md 2.3 KB
Loading… -
preview-review.md 1.8 KB
Loading… -
seed-datasets.md 1.1 KB
Loading…
-
-
scripts
-
get_person_object_schema.py 1.7 KB
Loading…
-
-
workflows
-
autopilot.md 2.6 KB
Loading… -
interactive.md 3.2 KB
Loading…
-
-
BENCHMARK.md 9.1 KB
Loading… -
skill-card.md 4.7 KB
Loading… -
SKILL.md 4.6 KB
--- name: data-designer description: Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline. The argument is the description of the dataset to generate. license: Apache-2.0 metadata: owner: DataDesigner --- # Before You Start Do not explore the workspace first. The workflow's Learn step gives you everything you need. # Goal Build a synthetic dataset using the Data Designer library that matches this description: $ARGUMENTS # Workflow Use **Autopilot** mode if the user implies they don't want to answer questions — e.g., they say something like "be opinionated", "you decide", "make reasonable assumptions", "just build it", "surprise me", etc. Otherwise, use **Interactive** mode (default). Read **only** the workflow file that matches the selected mode, then follow it: - **Interactive** → read `workflows/interactive.md` - **Autopilot** → read `workflows/autopilot.md` # Rules - Keep all columns in the output by default. The only exceptions for dropping a column are: (1) the user explicitly asks, or (2) it is a helper column that exists solely to derive other columns (e.g., a sampled person object used to extract name, city, etc.). When in doubt, keep the column. - Do not suggest or ask about seed datasets. Only use one when the user explicitly provides seed data or asks to build from existing records. When using a seed, read `references/seed-datasets.md`. - When the dataset requires person data (names, demographics, addresses), read `references/person-sampling.md`. - If a dataset script that matches the dataset description already exists, ask the user whether to edit it or create a new one. # Usage Tips and Common Pitfalls - **Sampler and validation columns need both a type and params.** E.g., `sampler_type="category"` with `params=dd.CategorySamplerParams(...)`. - **Jinja2 templates** in `prompt`, `system_prompt`, and `expr` fields: reference columns with `{{ column_name }}`, nested fields with `{{ column_name.field }}`. - **`SamplerColumnConfig`:** Takes `params`, not `sampler_params`. - **LLM judge score access:** `LLMJudgeColumnConfig` produces a nested dict where each score name maps to `{reasoning: str, score: int}`. To get the numeric score, use the `.score` attribute. For example, for a judge column named `quality` with a score named `correctness`, use `{{ quality.correctness.score }}`. Using `{{ quality.correctness }}` returns the full dict, not the numeric score. # Troubleshooting - **`data-designer` CLI not found:** Tell the user that `data-designer` is not installed in this environment (requires Python >= 3.11). Ask if they would like you to create a virtual environment and install it, or if they prefer to do it themselves. Do not install anything without the user's permission. - **Network errors during preview:** A sandbox environment may be blocking outbound requests. Ask the user for permission to retry the command with the sandbox disabled. Only as a last resort, if retrying outside the sandbox also fails, tell the user to run the command themselves. # Output Template Write a Python file to the current directory with a `load_config_builder()` function returning a `DataDesignerConfigBuilder`. Name the file descriptively (e.g., `customer_reviews.py`). Use PEP 723 inline metadata for dependencies. ```python # /// script # dependencies = [ # "data-designer", # always required # "pydantic", # only if this script imports from pydantic # # add additional dependencies here # ] # /// import data_designer.config as dd from pydantic import BaseModel, Field # Use Pydantic models when the output needs to conform to a specific schema class MyStructuredOutput(BaseModel): field_one: str = Field(description="...") field_two: int = Field(description="...") # Use custom generators when built-in column types aren't enough @dd.custom_column_generator( required_columns=["col_a"], side_effect_columns=["extra_col"], ) def generator_function(row: dict) -> dict: # add custom logic here that depends on "col_a" and update row in place row["name_in_custom_column_config"] = "custom value" row["extra_col"] = "extra value" return row def load_config_builder() -> dd.DataDesignerConfigBuilder: config_builder = dd.DataDesignerConfigBuilder() # Seed dataset (only if the user explicitly mentions a seed dataset path) # config_builder.with_seed_dataset(dd.LocalFileSeedSource(path="path/to/seed.parquet")) # config_builder.add_column(...) # config_builder.add_processor(...) return config_builder ``` Only include Pydantic models, custom generators, seed datasets, and extra dependencies when the task requires them. -
skill.oms.sig 6.1 KB · in bundle
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.