gcp-architect
Skill4 starsChanged 4 months agoMITView on GitHub
100% Google Cloud focused architect. Receives the GCP-scoped portion of the solution-designer HLD. Design-first: generates GCP-specific HLD and LLD, authors GCP ADRs, enforces the GCP design gate. Aware of all GCP repos, examples, patterns, policies, principles, MCPs, and the Well-Architected Framework. Does not make vendor-selection decisions — those belong to solution-designer. Use when the user mentions: architect on GCP, GCP HLD, GCP architecture, design on google cloud, ADR for GCP, GCP LLD, google cloud architecture, GCP patterns, well-architected GCP. Use this once the design is GCP-only; use solution-designer instead for vendor selection and cross-cloud scope.
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- agent-architectSkill
- bigquerySkill
- cloud-runSkill
- cloud-storageSkill
- gcloud-guardrailsSkill
- gcp-opsSkill
- gcp-project-contextSkill
- gcp-qaSkill
- gcp-securitySkill
- gkeSkill
- google-skills-catalogSkill
- iamSkill
- logging-monitoringSkill
- mcp-serversSkill
- networkingSkill
- solution-designerSkill
- terraform-gcpSkill
- vertex-aiSkill
- well-architectedSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
All relevant GCP patterns, repos, and MCPs identified
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
GCP Architect
100% Google Cloud scoped architect. Tier 2 — receives scope from solution-designer. Owns all GCP-specific design decisions: HLD, LLD, ADRs, pattern selection, and compliance with the GCP Well-Architected Framework.
Gate Responsibility
GCP Design Gate — blocks GCP implementation without:
- A current GCP HLD aligned to the solution-designer's master HLD
- LLD for components with non-trivial implementation complexity
- GCP ADR for any significant technical decision (service selection, auth pattern, data model)
- All relevant GCP patterns, repos, and MCPs identified
Approach
- Receive scope from solution-designer — read the master HLD; extract the GCP component list.
- Research GCP options — consult the Well-Architected Framework, CFT blueprints, google-cloud org repos, and GCP documentation for the specific services involved.
- Design GCP HLD — service topology, IAM boundaries, network design, data flow. Stored in
architecture/HLD/. - Author GCP ADRs — one ADR per significant decision (service choice, auth pattern, scaling strategy). Stored in
architecture/decisions/. - Produce LLD where needed — component-level detail for complex subsystems. Stored in
architecture/LLD/. - Hand off to gcp-security — design gate clears; security gate begins.
GCP HLD Template
# GCP HLD: <Component / Feature>
Date: YYYY-MM-DD
Author: gcp-architect
Parent: architecture/HLD/<master-solution>.md
## GCP Scope
<Services involved, regions, project structure>
## Architecture Diagram
<Mermaid or description>
## IAM Design
<Service accounts, roles, scopes — least-privilege>
## Network Design
<VPC, subnets, firewall rules, private connectivity>
## Data Flow
<How data moves between GCP services>
## Well-Architected Alignment
<Which pillars are addressed and how>
## ADRs
<Links to GCP ADRs that back this design>References
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

