Automation & Ops ✓ Google · Official google-cloudsolution-architecturerequirements-discoverytechnical-decompositionarchitecture-validationinfrastructure-as-code

Google Cloud Solution Architect

Plan, validate, and package end-to-end architectures for complex multi-product Google Cloud workloads.

FollowSkills review · FSRS-2.0
Not recommended
57/ 100 5-point scale 2.9 / 5
Trust16 / 25 · 3.2/5

The process requires approval of the technical decomposition, product choices, diagrams, descriptions, recommendations, and validation plan, and requests permission before validation execution or writing code. However, least-privilege permissions, sensitive-data handling, external data flows, dependency isolation, rollback, and recovery boundaries are not specified, so points are deducted.

Reliability8 / 20 · 2.0/5

The document defines ordered phases, ambiguity resolution, approval loops, and troubleshooting after validation issues, making the happy path coherent. It provides no committed test suite, CI coverage, pinned dependencies, reproducible procedures, or standardized diagnostic failures, and execution depends on undeclared tool availability, so points are deducted.

Adaptability11 / 15 · 3.7/5

The skill clearly identifies holistic Google Cloud architecture use cases, non-fit cases for specialized or narrowly focused skills, required discovery inputs, and staged outputs. It does not declare Chinese-language support, mainland-China service reachability, or fallbacks when Google Cloud or MCP services are unavailable, and its trigger boundary remains broad, so points are deducted.

Convention10 / 15 · 3.3/5

The documentation is well structured, uses progressive phases, includes an output template and official reference indexes, documents repository installation, states Apache-2.0 licensing, and provides README maintenance and issue-reporting paths. The skill itself lacks dependency setup details, compatibility/version policy, changelog, explicit maintenance ownership, and known limitations, so points are deducted.

Effectiveness7 / 15 · 2.3/5

The stated workflow covers requirements discovery, architecture design, deployment guidance, validation, and packaging, with intended outputs including a usable architecture document, Mermaid diagram, and deployment guidance. Static source material does not verify correctness, completeness, deployability, or marginal benefit over manual work, so the score is capped by static calibration and reduced for missing evidence.

Verifiability5 / 10 · 2.5/5

The skill requires citations to official Google Cloud documentation and supplies architecture, decision-making, and best-practice reference indexes plus a fixed output template, providing some auditability. There are no test results, CI execution records, representative verified outputs, or independent corroboration, so the score reaches the static ceiling but not beyond it.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 513a7a51e85f
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
Before you use it
  • The core workflow depends on the Google Developer Knowledge MCP, Google Cloud documentation, and tools such as gcloud or curl, without defined fallbacks or failure feedback for service reachability, quotas, authentication, or documentation changes.
  • The skill can generate and, after approval, write deployment code, but it does not specify handling, redaction, permissions, or rollback for credentials, secrets, personal data, or sensitive architecture information.
  • No verified example outputs, automated tests, or CI evidence are provided; deployment guidance and product-status decisions require human review.
  • Chinese-language quality and availability of Google Cloud and related MCP services from mainland-China networks are not documented.
Review evidence [1][2][3][4][5][6][7][8]
See the full review method →

What does this skill do, and when should you use it?

This skill is designed for specific, complex workloads that require holistic guidance across multiple Google Cloud products. It begins by collecting functional, non-functional, current-state, and dependency requirements, then produces a technical decomposition, product choices, architecture diagram, architecture description, design guidance, and deployment guidance. The workflow requires explicit approval at key transitions and includes pre-deployment static validation plus optional runtime validation. Product-specific and Google Cloud recipe skills are preferred when they directly address the workload.

It interactively gathers workload requirements, identifies ambiguities or contradictions, and requests clarification before architectural recommendations continue. It then generates a technical decomposition, Google Cloud product and feature recommendations, a Mermaid architecture diagram, an architecture description, design recommendations, and deployment guidance. It grounds Phase 2 content with the Google Developer Knowledge MCP server, relevant skills, and official Google Cloud documentation, adding citations to generated guidance. It also creates and runs pre-deployment dry-run and static policy checks, can provide runtime verification commands after deployment, and can consolidate the output into solution-architecture-guide.md before writing code files with user permission.

  1. A cloud architect needs a multi-product Google Cloud design for a workload currently running on-premises or with another cloud provider.
  2. A platform engineering team needs structured discovery of security, reliability, cost, performance, operations, and sustainability requirements before design begins.
  3. A technical lead wants approval checkpoints for product selection, diagrams, architecture descriptions, recommendations, and deployment guidance.
  4. A cloud team needs dry-run, network-topology, firewall, and IAM checks before provisioning live resources.

What are this skill's strengths and limitations?

Pros
  • Covers requirements discovery, architecture design, validation, and packaging in one workflow.
  • Explicitly handles conflicting requirements and requires approval before major deliverables and phase transitions.
  • Includes source grounding, official documentation citations, pre-deployment dry-runs, and optional runtime validation.
  • Fits concrete workloads requiring holistic design across multiple Google Cloud products.
Limitations
  • It is not intended for workloads directly covered by a specialized product skill or Google Cloud recipe skill.
  • It depends on access to the Google Developer Knowledge MCP server, relevant skills, and official documentation resources.
  • Runtime validation depends on the user deploying the infrastructure; the source provides no fixed deployment implementation or test suite.
  • It says deployment and code artifacts can be generated, but does not specify a programming language, IaC tool, or supported platform matrix.

How do you install this skill?

Run:

npx skills add google/skills

Select google-cloud-solution-architecture during installation. The repository is a collection of 90 skills; the source does not specify a separate version requirement or dedicated installation command.

How do you use this skill?

After installation, submit a request for a specific complex, multi-product Google Cloud workload, for example: “Discover requirements and design an end-to-end Google Cloud architecture for a complex workload migrating from on-premises.” The skill begins with questions and does not proceed to architecture design until requirements and the technical decomposition are approved. No dedicated trigger command is documented.

How does this skill compare with similar options?

Compared with product-specific skills or google-cloud-recipe-* skills, this skill targets holistic architecture for complex multi-product workloads; use those specialized skills when they directly address the workload or use case.

FAQ

Does it recommend products immediately?
No. It first gathers functional and non-functional requirements, resolves identified ambiguities or contradictions, and obtains approval for the technical decomposition.
Is live deployment required?
No. Pre-deployment static validation and dry-runs are supported without provisioning live resources. Runtime validation requires the user to deploy the infrastructure.
Will it write files to my workspace automatically?
No. The workflow requests permission first and writes code files only after the user grants it.
Is it suitable for a quick single-product configuration?
Usually not. The source recommends using a specialized product or recipe skill when it directly covers the workload.

More skills from this repository

All from google/skills

Automation & Ops ✓ Google · Official

Google Cloud AI Agent Builder

Design, implement, deploy, and validate AI agents and multi-agent systems on Google Cloud.

Automation & Ops ✓ Google · Official

Google Cloud Operational Excellence Advisor

Assesses Google Cloud workloads and recommends improvements using the WAF Operational Excellence pillar.

Data & Analysis ✓ Google · Official

Google Cloud Agentic Data Science Architect

Design and validate a multi-product Google Cloud architecture for agent-based data analytics and machine learning workloads.

Automation & Ops ✓ Google · Official

Google Cloud gcloud CLI Safety Skill

Helps agents manage and troubleshoot Google Cloud resources through validated, scoped gcloud commands.

Automation & Ops ✓ Google · Official

Google Cloud Live Multimodal Streaming Architect

Design and deploy Google Cloud solutions for live, bidirectional multimodal streams.

Data & Analysis ✓ Google · Official

Google Cloud Agent Evaluation Flywheel

Improve model and agent quality through structured evaluation, failure analysis, and iteration.

Automation & Ops ✓ Google · Official

GKE Basics Navigator

A focused entry point for discovering GKE cluster needs and routing each task to the right specialist skill.

Automation & Ops ✓ Google · Official

Google Cloud Secure Serverless Tiers

Guides agents to design, codify, deploy, and validate isolated multi-tier serverless web applications on Google Cloud.

Automation & Ops ✓ Google · Official

Google Cloud Authentication Guide

Choose secure Google Cloud authentication and authorization for local, production, and cross-cloud workloads.

Automation & Ops ✓ Google · Official

Google Cloud Reliability Architect

Evaluate and improve Google Cloud workload reliability using the Well-Architected Framework.

Automation & Ops ✓ Google · Official

Google Cloud Workload Manager Evaluator

Evaluate Google Cloud workloads against best-practice rules and review actionable findings.

Automation & Ops ✓ Google · Official

GKE Production Golden Path

Set production-oriented GKE defaults, readiness checks, and decision guardrails for cluster design.

Automation & Ops ✓ Google · Official

Google Cloud WAF Security Advisor

Assesses Google Cloud workloads against Well-Architected security principles and produces actionable improvement guidance.

Automation & Ops ✓ Google · Official

GKE Enterprise RAG Search Architect

Designs and validates enterprise RAG search systems built on GKE and AlloyDB.

Dev & Engineering ✓ Google · Official

Gemini LiveAPI Client Service Skill

Generate a resumable, multimodal, bidirectional Gemini LiveAPI client over WebSockets.

Data & Analysis ✓ Google · Official

Cross-Cloud Agentic Analytics Architect

Design governed, secure agentic analytics for distributed data

Automation & Ops ✓ Google · Official

Agent Platform Endpoint Management

Manage Agent Platform serving endpoints and troubleshoot common endpoint failures.

Automation & Ops ✓ Google · Official

AI Workload Migration to GKE Inference

Move existing AI inference workloads to self-hosted inference on Google Kubernetes Engine.

Automation & Ops ✓ Google · Official

Google Cloud Performance Advisor

Assess and improve workload performance using the Google Cloud WAF.

Data & Analysis ✓ Google · Official

Agent Platform RAG Engine Manager

Manage Vertex AI RAG corpora and retrieve grounded context with Python SDKs.

Related skills