Language:JapaneseEnglish

datarobot-agent-skills Claude Code Plugin

Author
DataRobot
Category
Development
Topics
AI Agents & AI App Development · Cloud, Deployment & CI/CD · Monitoring & Observability
First cataloged
2026-07-09 (UTC)
Explanation last updated
2026-07-16 (UTC)
Source (GitHub) last updated
2026-08-26 (UTC) (yesterday)

The explanation below is AI-generated. Please verify it against the sources.

This plugin is a collection of Claude-compatible skills that let a coding agent carry out DataRobot machine-learning and agent-management tasks. According to the README, each skill is an Agent Context Protocol definition with a SKILL. md file and, in many cases, helper Python scripts the agent can run directly. A separate skill also supports building and deploying new agents (using frameworks such as LangGraph, CrewAI, or LlamaIndex) onto the DataRobot platform.

About the service

DataRobot is an enterprise platform for building, running, and governing predictive and agentic AI, offering tools for model training, deployment, monitoring, and agent orchestration across cloud, hybrid, and on-premises environments. This plugin's skills interact with that platform's APIs and SDK to perform ML and agent workflow tasks on a user's behalf.

What you can do with datarobot-agent-skills

  • Create projects, run AutoML training, and list resulting models via the model-training skill
  • Deploy models, configure prediction environments, and manage deployments via the model-deployment skill
  • Generate prediction data templates and run batch or real-time predictions via the predictions skill
  • Analyze and engineer features, including feature discovery and importance, via the feature-engineering skill
  • Monitor deployed models for performance and data drift via the model-monitoring skill
  • Compute explainability outputs such as SHAP values via the model-explainability skill
  • Upload and validate datasets via the data-preparation skill
  • Set up CI/CD pipelines for DataRobot App Framework templates using GitHub Actions or GitLab via the app-framework-cicd skill
  • Instrument external agents (e.g., built with Google ADK, LangChain, LangGraph, CrewAI, LlamaIndex, or PydanticAI) with OpenTelemetry for DataRobot monitoring
  • Build and deploy new agents to DataRobot, optionally bundled with an MCP server, backend APIs, and a React frontend, via the agent-assist skill

Sources

Back to list