What problem does it solve?
This Skill provides expert guidance for building, managing, and orchestrating data pipelines on Google Cloud Platform (GCP), helping users select the appropriate tool for their needs and clarifying requirements for creating, updating, and running data pipelines.
Core Features & Use Cases
- Guidance for Tool Selection: Offers a clear framework for choosing between tools like dbt, Dataflow, Dataform, Spark, BigQuery DTS, and Cloud Composer based on user requirements.
- Pipeline Detection: Scans the workspace for existing pipeline indicators (e.g.,
.java, .py, workflow_settings.yaml) to provide targeted recommendations.
- Task Execution Workflow: Outlines a structured approach for executing tasks such as detecting existing pipelines, presenting tool options, and confirming selections.
- Run Request Clarification: Provides a systematic way to understand the user's intent when asking to "run the pipeline" by clarifying scope and method.
Quick Start
Use the gcp-data-pipelines skill to detect and manage your data pipelines on Google Cloud Platform.