Guides feature engineering in DataRobot including automated feature creation, importance analysis, and feature set optimization for ML models.
How this skill is triggered — by the user, by Claude, or both
Slash command
/datarobot-agent-skills:datarobot-feature-engineeringThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill provides guidance for working with features in DataRobot, including understanding automated feature engineering, analyzing feature importance, and optimizing feature sets.
This skill provides guidance for working with features in DataRobot, including understanding automated feature engineering, analyzing feature importance, and optimizing feature sets.
Most common use case: Analyze feature importance for a model
get_feature_importance(model_id) to get importance scoresexport_feature_list(project_id) to document featuresExample: "Show me the top 10 most important features for model xyz123"
Use this skill when you need to:
User request: "Show me the top 10 most important features for model xyz123 and explain what they mean."
Agent workflow:
User request: "Create a simplified feature set for deployment abc123, keeping only features with importance > 0.1."
Agent workflow:
This skill guides you to use the DataRobot Python SDK directly. Install the SDK if needed:
pip install datarobot
Use these DataRobot SDK methods for feature analysis:
Feature Information:
model.get_features() - List all features in a modelmodel.get_feature_impact() - Get feature importance scoresproject.get_features() - List features in a projectFeature Analysis:
feature.name - Feature namefeature.feature_type - Feature type (Numeric, Categorical, etc.)feature.importance - Feature importance scoreSee the Common Patterns section below for complete examples.
import datarobot as dr
import os
# Initialize client
client = dr.Client(
token=os.getenv("DATAROBOT_API_TOKEN"),
endpoint=os.getenv("DATAROBOT_ENDPOINT")
)
# Get model and feature importance
model = dr.Model.get("xyz123")
feature_impact = model.get_feature_impact()
# Sort by importance
sorted_features = sorted(
feature_impact,
key=lambda x: x.get('impactNormalized', 0),
reverse=True
)
# Get top 10 features
top_features = sorted_features[:10]
for feature in top_features:
print(f"{feature['featureName']}: {feature.get('impactNormalized', 0):.3f}")
import datarobot as dr
# Get model and feature importance
model = dr.Model.get("xyz123")
feature_impact = model.get_feature_impact()
# Filter by importance threshold (> 0.1)
important_features = [
f for f in feature_impact
if f.get('impactNormalized', 0) > 0.1
]
print(f"Found {len(important_features)} features with importance > 0.1")
Feature importance scores indicate:
Note: Importance thresholds vary by model type and problem domain.
Common errors and solutions:
pip install datarobot
import datarobot as dr
import os
client = dr.Client(
token=os.getenv("DATAROBOT_API_TOKEN"),
endpoint=os.getenv("DATAROBOT_ENDPOINT", "https://app.datarobot.com")
)
npx claudepluginhub datarobot-oss/datarobot-agent-skills --plugin datarobot-agent-skillsGenerates and executes Python code to create, select, and transform ML features including interactions, scaling, encoding, and importance analysis.
Guides DataRobot model training: project creation, dataset upload, AutoML configuration, time series setup, and model selection.
Automates Datarobot tasks via Rube MCP (Composio). Always searches tools first for current schemas before executing workflows.