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, making it impossible to track which environment or client performed the operation. This Skill enforces consistent labeling so resource usage can be traced back to its origin. ## Core Features & Use Cases - BigQuery Labeling: Automatically appends --label datacloud:<ide> to supported bq subcommands (query, load, extract, mk, update, cp) while avoiding invalid flags on read-only commands like bq show or bq ls. - gcloud Environment Attribution: Prepends CLOUDSDK_METRICS_ENVIRONMENT=datacloud.<ide> to every gcloud command, covering both read-only and mutation operations. - Environment Detection: Deduces the correct client identifier (e.g., vscode, cloud-shell, gemini-cli, cursor) with an ai-agent fallback when the environment is unknown. - Use Case: An AI agent running a BigQuery query from VS Code would execute bq query --use_legacy_sql=false --label datacloud:vscode "SELECT 1" instead of the unlabeled equivalent. ## Quick Start Ask the agent to run a BigQuery query or any gcloud command and it will automatically attach the correct attribution label or environment variable for your current client.