Skip to content
Get packs

Agentic Analytics Solution Designer

Guides an agent through designing a governed analytics pipeline on Google Cloud Knowledge Catalog and Spark

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

What it does

When installed, the agent follows a structured four-phase workflow to help you plan a data analytics solution: it asks questions about your data sources, security and compliance needs, and dependencies, then proposes an architecture, a validation plan with test scripts, and a consolidated solution guide. It is built around Google Cloud Knowledge Catalog for metadata governance and Managed Service for Apache Spark for large-scale processing, and it also covers data spread across AWS S3, Azure Blob, and AlloyDB.

Great for

  • Data engineers and architects designing governed analytics across several clouds or on-premises systems
  • Teams that want a guided requirements-to-architecture process before provisioning anything
  • Developers using VS Code or Antigravity who want the agent grounded in Google Cloud Data Agent Kit

Skip it if

  • Provisioning actual infrastructure: the skill is for design and validation, and points to a different skill for borderless data lakehouse provisioning
  • Users who want a quick answer without answering many requirement questions, since the workflow deliberately asks one question at a time and stops until ambiguities are resolved
  • Non-technical users without access to Google Cloud accounts, because validation steps assume a real cloud environment

Try asking

  • “Help me design a governed analytics solution for product inventory data stored in S3 and Iceberg tables on Google Cloud”
  • “Walk me through requirements discovery for a Spark-based forecasting pipeline over AlloyDB and Azure Blob data”
  • “Generate validation scripts for the architecture we approved for our agentic analytics workflow”
  • “Compile a solution guide from our completed requirements and product selection”
Step-by-step guide: how to use Agentic Analytics Solution DesignerInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 6 original files, the Apache-2.0 licence and an attribution note.

    google-cloud-solution-agentic-analytics-spark-knowledge-catalog.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip google-cloud-solution-agentic-analytics-spark-knowledge-catalog.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip google-cloud-solution-agentic-analytics-spark-knowledge-catalog.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

  • Answer the requirement questions fully and resolve any contradictions the agent flags (for example zero-copy versus copying data) before asking for architecture.
  • Review every gcloud, REST, or MCP command the agent proposes before running it, since the skill directs it to execute those commands during validation.
  • State explicitly if a phase is already complete, such as 'requirements are approved', so the agent skips to the remaining task.

What's inside

  • assets/output-template.md
  • references/attribution.md
  • references/design-recommendations.md
  • references/knowledge-catalog-documentation.md
  • references/product-selection-guidance.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.