What problem does it solve? When AI agents run BigQuery (bq) or Google Cloud SDK (gcloud) commands, the resources they create or modify lack attribution metadata, making it impossible to track which environment or client created them. This Skill enforces consistent labeling so cloud resource usage can be traced back to its origin. ## Core Features & Use Cases - BigQuery Label Enforcement: Automatically appends --label datacloud=<ide> to bq commands such as query, load, extract, mk, and cp. - gcloud Environment Variable Injection: Prepends CLOUDSDK_METRICS_ENVIRONMENT=datacloud.<ide> to every gcloud command, whether read-only or mutating. - Environment Detection Rules: Maps the current client (e.g., vscode, cursor, cloud-shell, workstation, gemini-cli, claude) to the correct label value, falling back to ai-agent when unknown. - Use Case: An AI agent running a bq query inside VS Code automatically produces bq query --use_legacy_sql=false --label datacloud=vscode "SELECT 1", ensuring the query job is attributed in BigQuery audit logs. ## Quick Start Ask the agent to run a BigQuery query or any gcloud command and it will automatically attach the correct datacloud attribution label for your environment.
