fix: Claude Code marketplace plugin structure and install docs (#458)

Author: johnnygreco

.claude-plugin/marketplace.json

@@ -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"
@@ -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"

README.md

@@ -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.
+
+**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

claude-plugin/.claude-plugin/plugin.json

@@ -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"
+}

claude-plugin/skills

@@ -0,0 +1 @@
+../skills

docs/devnotes/posts/data-designer-got-skills.md

@@ -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.

skills/data-designer/.claude-plugin/plugin.json

@@ -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"],