Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions .claude-plugin/marketplace.json
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
{
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
"name": "nvidia-data-designer",
"name": "nemo-data-designer",
"owner": {
"name": "NVIDIA-NeMo",
"email": "data-designer@nvidia.com"
Expand All @@ -9,7 +9,7 @@
"plugins": [
{
"name": "data-designer",
"source": "./skills/data-designer",
"source": "./claude-plugin",
"description": "Claude Code skill for generating high-quality synthetic data from scratch or based on seed data using NeMo Data Designer.",
"keywords": ["synthetic-data", "nvidia", "nemo", "data-generation", "sdg", "data-designer"],
"category": "development"
Expand Down
20 changes: 20 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -110,6 +110,26 @@ data-designer config models # Set up your model configurations
data-designer config list # View current settings
```

### 🤖 Agent Skill

Data Designer has a [skill](https://nvidia-nemo.github.io/DataDesigner/latest/devnotes/posts/data-designer-got-skills/) for coding agents. Just describe the dataset you want, and your agent handles schema design, validation, and generation.
Comment on lines +113 to +115
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

seemed reasonable to add this too


**Via the [Claude Code](https://code.claude.com) marketplace:**

```
/plugin marketplace add NVIDIA-NeMo/DataDesigner
/plugin install data-designer@nemo-data-designer
/reload-plugins
```

**Via [skills.sh](https://skills.sh):**

```bash
npx skills add NVIDIA-NeMo/DataDesigner
```

After installation, type `/data-designer` or describe the dataset you want and the skill will kick in.

### 🤝 Get involved

- **[Contributing Guide](https://nvidia-nemo.github.io/DataDesigner/latest/CONTRIBUTING)** – Help improve Data Designer
Expand Down
10 changes: 10 additions & 0 deletions claude-plugin/.claude-plugin/plugin.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
{
"name": "nemo-data-designer",
"version": "0.1.0",
"description": "Claude Code skill for generating high-quality synthetic data from scratch or based on seed data using NeMo Data Designer.",
"author": {"name": "The NeMo Data Designer Team"},
"homepage": "https://github.com/NVIDIA-NeMo/DataDesigner",
"repository": "https://github.com/NVIDIA-NeMo/DataDesigner",
"keywords": ["synthetic-data", "nvidia", "nemo", "data-generation", "sdg", "data-designer"],
"category": "development"
}
1 change: 1 addition & 0 deletions claude-plugin/skills
11 changes: 7 additions & 4 deletions docs/devnotes/posts/data-designer-got-skills.md
Original file line number Diff line number Diff line change
Expand Up @@ -193,22 +193,25 @@ In our experiment setup, each session started from a clean slate (new directory,

First, you will need to install Data Designer and set up your model providers. The [quickstart guide](https://github.com/NVIDIA-NeMo/DataDesigner#quick-start) in our README walks through this. We recommend using a virtual environment to manage dependencies.

Then install the skill. There are two ways:
Next, install the skill. Note that while the skill should work with other coding agents that support skills, our development and testing has focused on Claude Code at this stage. There are two ways to install:

**Via the Claude Code marketplace:**

```
/plugin marketplace add NVIDIA-NeMo/DataDesigner

/install data-designer
/plugin install data-designer@nemo-data-designer
/reload-plugins
```

**Via npx:**
**Via [skills.sh](https://skills.sh):**

```bash
npx skills add NVIDIA-NeMo/DataDesigner
```

!!! tip
When prompted, make sure to select **Claude Code** as an additional agent.

After installation, open Claude Code and type `/data-designer`, or just tell it you want to generate a dataset along with a description of what you want and the skill will kick in.

The skill has two modes. In interactive mode, the agent asks clarifying questions and has you make key design decisions (diversity axes, sampling strategies, model selection). You review sample records, give feedback, and iterate until it's right.
Expand Down
2 changes: 1 addition & 1 deletion skills/data-designer/.claude-plugin/plugin.json
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
"name": "data-designer",
"version": "0.1.0",
"description": "Claude Code skill for generating high-quality synthetic data from scratch or based on seed data using NeMo Data Designer.",
"author": "The NeMo Data Designer Team",
"author": {"name": "The NeMo Data Designer Team"},
"homepage": "https://github.com/NVIDIA-NeMo/DataDesigner",
"repository": "https://github.com/NVIDIA-NeMo/DataDesigner",
"keywords": ["synthetic-data", "nvidia", "nemo", "data-generation", "sdg", "data-designer"],
Expand Down
Loading