Develops, optimizes and runs PySpark/Spark code on Managed Spark (Dataproc clusters and Serverless) on Google Cloud. Use when: - Authoring or running Spark/PySpark notebooks (any kernel), incl. data analysis, reports and visualizations. - Writing Spark ETL pipelines or preparing workloads for production. - Training or running inference with ML models on Spark.
安装
npx skills add GoogleCloudPlatform/data-agent-kit-plugin --skill gcp-sparknpx skills add GoogleCloudPlatform/data-agent-kit-plugin --skill gcp-spark -a claude-code -gnpx skills add GoogleCloudPlatform/data-agent-kit-plugin --skill gcp-spark -a codex -ggemini skills install https://github.com/GoogleCloudPlatform/data-agent-kit-plugin.git --path skills/gcp-sparkgh skill install GoogleCloudPlatform/data-agent-kit-plugin gcp-sparkgit clone --depth 1 https://github.com/GoogleCloudPlatform/data-agent-kit-plugin /tmp/GoogleCloudPlatform__data-agent-kit-plugin
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/GoogleCloudPlatform__data-agent-kit-plugin/skills/gcp-spark ~/.claude/skills/gcp-spark # Claude Code
cp -R /tmp/GoogleCloudPlatform__data-agent-kit-plugin/skills/gcp-spark ~/.agents/skills/gcp-spark # Codex, Cursor, Gemini CLI, Copilot, OpenCode