Skip to content
Get packs

Data Lineage Summary

Summarizes where BigQuery and Cloud Storage data comes from and where it goes, as a readable report

Source Download skill
Repository
google/skills
Stars
21,782
Licence
Apache-2.0
Files
3 files

What it does

Once installed, the agent can investigate a specific table or column in Google Cloud and trace its upstream sources and downstream consumers using Google's data lineage service. It then writes a plain-English, left-to-right Markdown report covering the systems involved, the data flow, and the search limits used, which helps when debugging data quality problems or tracing provenance.

Great for

  • Data engineers tracing where a BigQuery table's data originates while debugging quality issues
  • Analysts who need a readable overview of how a dataset is produced and consumed
  • Teams documenting data provenance for a specific table or column

Skip it if

  • Downstream blast-radius or impact analysis for planned changes; the skill says to use the separate datalineage-bigquery-asset-impact-analysis skill instead
  • Generic BigQuery querying or editing lineage relationships, which this skill explicitly excludes
  • Users without a configured Google Cloud data lineage MCP server, since the skill cannot work without it

Try asking

  • “Summarize the upstream and downstream lineage of my BigQuery table project.dataset.orders and explain the flow in plain English”
  • “Trace where the efficiency_score column in project.dataset.sensor_readings comes from (column-level lineage)”
  • “Why does my customer_churn table look wrong? Show me what feeds into it”
  • “Give me a lineage report for this Cloud Storage-backed BigQuery table, including the locations searched and depth limits”
Step-by-step guide: how to use Data Lineage SummaryInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 3 original files, the Apache-2.0 licence and an attribution note.

    datalineage-summary.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip datalineage-summary.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip datalineage-summary.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give the full asset name in the form bigquery:project.dataset.table, and name a specific column if you only care about one field.
  • Ask the agent to rerun with more locations or a higher depth if the report says the search may be incomplete.
  • Check the Analysis Metadata section to see exactly which regions and limits were used before trusting the summary.

What's inside

  • references/attribution.md
  • references/mcp-usage.md
  • SKILL.md

Redistributed unmodified from google/skills under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.