dataproc Plugin
Plugin Claude Code Database Data Engineering & AnalyticsCloud, Deployment & CI/CDThe explanation below is AI-generated. Please verify it against the sources.
dataproc is a GitHub repository (gemini-cli-extensions/dataproc) that provides agent skills for managing Google Cloud Dataproc clusters and jobs through natural-language prompts. According to the README, it is currently in beta (pre-v1.0) and may include breaking changes before v1.0. The skills can be installed and used with AI agents such as Antigravity, Claude Code, and Codex. It requires a Google Cloud project with the Dataproc API enabled, Application Default Credentials, and IAM permissions of Dataproc Viewer or Dataproc Editor. Configuration requires setting the DATAPROC_PROJECT and DATAPROC_REGION environment variables.
Overview
According to the README, this is not a SaaS itself but a set of agent skills (a plugin/extension) that lets AI coding agents (Antigravity, Claude Code, Codex) interact with Google Cloud Dataproc clusters and jobs using natural language instead of gcloud commands.
What you can do with dataproc
- List Dataproc clusters in a specified region (e.g., "List all my Dataproc clusters in us-central1.")
- Check the status of a specific job by ID (e.g., "Show me the status of the job with ID 'my-spark-job-123'.")
- List all failed jobs in a project
- Get details for a named cluster (e.g., "Get details for the cluster named 'my-cluster'.")
- Install and configure the skills for Antigravity, Claude Code, or Codex per the README's setup instructions
Sources
Original description (English)
Manage Dataproc clusters and jobs.
History of dataproc
- Plugin Added dataproc