Borderless open data lakehouse: agentic AI architecture on Google Cloud
Design a multi-cloud Iceberg + BigQuery data lakehouse (Cloud Storage, S3, Azure Blob) with the Gemini agent platform — discovery, architecture, Terraform, validation
- What
- Design a multi-cloud Iceberg + BigQuery data lakehouse (Cloud Storage, S3, Azure Blob) with the Gemini agent platform — discovery, architecture, Terraform, validation
- Cost
- Free
- Needs
- a Google Cloud account with billing enabled (deploying the designed solution provisions real multi-cloud infrastructure and incurs real cloud costs); a data workload to architect — the skill itself needs nothing to read
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — Google's official solution skill for designing a borderless open data lakehouse: a 4-phase agent workflow. Phase 1, requirements discovery — interview the workload (data sources, metadata federation, security, analytical requirements, expected AI-agent queries) and produce a confirmed technical decomposition. Phase 2, solution design — map components to Google Cloud products using the repo's reference docs, draw a Mermaid architecture diagram (ingestion vs serving subsystems, Managed Spark as the shared ETL bridge), and compile a solution-architecture-guide.md. Phase 3, implementation plan — document prerequisites (projects, billing, APIs, IAM), generate Terraform IaC, write step-by-step deployment instructions. Phase 4, validation — dry-runs, connectivity and security checks, verification scripts, and a validation report. Covers Lakehouse for Apache Iceberg, BigQuery data agents, Cross-Cloud Interconnect, and the Gemini Enterprise Agent Platform across Cloud Storage, AWS S3 and Azure Blob. Honest caveats: enterprise-grade design methodology — deploying what it produces provisions real multi-cloud infrastructure, so bring a Google Cloud account with billing enabled (real cloud costs); expects the agent to fetch live Google Cloud documentation to ground its guidance; explicitly not for single-cloud warehouses. Apache-2.0 licensed. Updated October 22, 2026 (version 1.0.1): SKILL.md now carries an Attribution section marked MUST READ — before any gcloud, REST API or MCP command, the agent must read references/attribution.md; the tag itself identifies only the skill and its version, carries no user data, applies to direct terminal commands only, is never persisted, and an opt-out is documented. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version: 1.0.1
Quick answer
Borderless open data lakehouse is a free Muse skill, Google's official solution skill for designing a borderless open data lakehouse: a 4-phase agent workflow starting with requirements discovery, interviewing the workload and producing a confirmed technical decomposition, then solution design, mapping components to Google Cloud products, drawing a Mermaid architecture diagram, and continuing through Terraform and validation.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit 90bb0a8Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: a Google Cloud account with billing enabled (deploying the designed solution provisions real multi-cloud infrastructure and incurs real cloud costs); a data workload to architect — the skill itself needs nothing to read Install "Borderless open data lakehouse: agentic AI architecture on Google Cloud" for me. It gives my agent Google's official 4-phase workflow for a borderless open data lakehouse: requirements discovery and technical decomposition, solution design with product mapping and Mermaid architecture diagrams, an implementation plan with Terraform IaC generation and deployment instructions, and validation with dry-runs and verification scripts — across Lakehouse for Apache Iceberg, BigQuery data agents, Cross-Cloud Interconnect, Managed Spark and the Gemini Enterprise Agent Platform (Cloud Storage, S3, Azure Blob). Apache-2.0 licensed. Repository: https://raw.githubusercontent.com/google/skills/90bb0a8853daa6ab597c303a69d80ad8ee3e44d5/skills/cloud/google-cloud-solution-agentic-ai-borderless-data-lakehouse/SKILL.md Pinned version: install the code at commit 90bb0a8853daa6ab597c303a69d80ad8ee3e44d5 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. Updated October 22, 2026: Skill Harbor regenerated this install prompt for google-cloud-solution-agentic-ai-borderless-data-lakehouse 1.0.1. What changed since 1.0.0, the version the previous prompt described: SKILL.md gains an Attribution section marked MUST READ — before executing any gcloud, REST API, or MCP command, the agent must read and follow references/attribution.md. What that file requires, stated here so nothing is a surprise: for commands executed directly in the terminal — never in generated scripts, Terraform, or user code — prefix gcloud with CLOUDSDK_METRICS_REQUEST_ATTRIBUTION="agent-skills/1.0 (skill:google-cloud-solution-agentic-ai-borderless-data-lakehouse)" set inline on each command, and append agent-skills/1.0 (skill:google-cloud-solution-agentic-ai-borderless-data-lakehouse) to the User-Agent of direct HTTP, REST or MCP requests. The tag identifies only the skill and its version and carries no user data; it must never be persisted with gcloud config set (that would mislabel unrelated later usage); and references/attribution.md documents a user opt-out — if I ask to disable attribution tagging, omit the variable and the User-Agent suffix. Nothing else in what the skill does changed: the 4-phase workflow, the product mapping, the generated Terraform and the validation approach are the same. 1. Fetch the SKILL.md file and the helper files (including the references/ folder) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "google-cloud-solution-agentic-ai-borderless-data-lakehouse". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. describe the workload to architect and confirm the Phase 1 decomposition; set up the GCP project and billing before Phase 3). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 90bb0a8 · 2026-10-22
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-22 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.