Terminal
Terminal/Skill
Maps everything downstream of a BigQuery table or view when it breaks or changes, using Google Cloud data lineage.
By Google
Works with
npx skills add google/skills --skill datalineage-bigquery-asset-impact-analysisThis skill guides the agent in performing a downstream impact analysis (blast radius assessment) when a BigQuery table or view is reported as broken, stale, missing, or when a user is planning maintenance and wants to know the consequences of modifying or pausing updates to an asset.
It relies primarily on the data lineage (Knowledge Catalog) MCP Server on Google Cloud to discover relationships between assets.
This skill requires access to the data lineage API on Google Cloud and an active client connection to the Data Lineage MCP Server. For detailed connection configurations and tool schemas, refer to MCP Usage.
bigquery:{project_id}.{dataset_id}.{table_or_view_id}bigquery:my-prod-project.analytics.ordersIdentify the locations to search and construct the Data Lineage API request:
bq show --format=json {project_id}:{dataset_id} and extract the location field (e.g.,
us-central1 or us). If location discovery fails due to permissions or
missing tools, prompt the user for the dataset's location.parent path using the project ID and the
MCP server's location. Consult the DataLineageServer tool definition
to find the configured region or location (e.g., us). The format is:
projects/{project_id}/locations/{mcp_server_location}.locations array of the payload (e.g., ["us-central1"] or ["us", "us-central1"]).Call the DataLineageServer:search_lineage tool to fetch downstream
relationships.
DOWNSTREAM.max_depth = 10 and max_process_per_link = 5
as robust defaults.Traverse the returned lineage links to build the impact graph:
target of each link represents a downstream asset
that depends on your source asset.processes field on each link. This
identifies the ETL pipelines, BigQuery Views, or Scheduled Queries that
propagate the data.dependency_type: EXACT_COPY, mark the target as
"Directly Stale / Identical Copy".Present your findings clearly to the user using the following structure:
Executive Summary: State the total number of downstream assets affected and the maximum depth of the impact.
Critical Path: Highlight high-priority downstream assets (e.g., assets containing "prod", "dashboard", "reporting", or "master" in their names).
Blast Radius Table: A clean Markdown table listing the dependencies. You MUST include all columns:
| Downstream Asset | Transform Process | Depth | Impact Type |
|---|---|---|---|
bigquery:project.dataset.table | projects/p/locations/l/processes/proc | 1 | Direct |
bigquery:project.dataset.view | projects/p/locations/l/processes/view | 2 | Indirect |
Analysis Metadata: Provide transparency on the parameters and boundaries of your search so the user can choose to expand them:
{list_of_locations_queried}{parent_path}{max_depth}{max_process_per_link}DataLineageServer:search_lineage tool.bq show indicates the source table does not exist, stop and report
this directly to the user. Do not attempt to guess alternative table
names unless the user explicitly instructs you to do so.