Download for MacApple silicon, macOS 14+
Skill

datarobot-predictions

@datarobot-oss Updated 2026-10-23

Tools and guidance for making predictions with DataRobot deployments, including real-time predictions, batch scoring, prediction dataset generation, and prediction explanations (SHAP/XEMP). Use when making predictions, running batch scoring, generating prediction datasets, or explaining individual predictions from a deployment.

agy-pluginagy-skillantigravity-pluginantigravity-skillantigravity-skillschatgpt-pluginclaude-skillscodex-plugin

Install

With your agent

Install OMGSkills skill "datarobot-oss/datarobot-agent-skills:skills/datarobot-predictions" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.

Manual command

git clone https://github.com/datarobot-oss/datarobot-agent-skills /tmp/datarobot-agent-skills && ln -s /tmp/datarobot-agent-skills/skills/datarobot-predictions ~/.claude/skills/datarobot-predictions

From README

DataRobot Predictions Skill This skill provides comprehensive guidance for working with DataRobot predictions, including real-time predictions, batch scoring, and generating prediction datasets. Most common use case: Generate predictions for a deployment Get deployment features: getdeploymentfeatures(deploymentid) to understand required columns Generate template: generatepredictiondatatemplate(deploymentid, nrows) to create CSV structure Make predictions: Use deployment.predictbatch(...) (works for both single-row “real-time” and batch scoring) Example: "Generate a prediction dataset template for deployment abc123 with 10 rows" To also explain predictions: pass --max-explanations N to makeprediction.py (or the maxexplanations=N kwarg in code). See Prediction Explanations below.