
Multi-Cloud Architecture Advisor
Guides choosing and combining AWS, Azure, GCP and OCI services for multi-cloud designs
- Repository
- wshobson/agents
- Stars
- 42,095
- Licence
- MIT
- Files
- 3 files
What it does
This skill gives an AI assistant a reference framework for designing applications that span several cloud providers (Amazon AWS, Microsoft Azure, Google GCP and Oracle OCI). Once installed, the agent can compare equivalent services across the providers, suggest architecture patterns such as disaster recovery across clouds or picking the best service from each provider, and outline a phased migration plan and cost-saving ideas. It is advisory: it works from included comparison tables and written guidance rather than connecting to your accounts.
Great for
- Architects or engineers early in planning a system that may run on more than one cloud
- Teams weighing vendor lock-in against the extra complexity of multiple clouds
- People who need a quick side-by-side of equivalent AWS, Azure, GCP and OCI services
Skip it if
- Teams that only use one cloud and need hands-on deployment help, since the skill contains no provisioning scripts or provider-specific instructions
- Anyone relying on its service tables or cost percentages as current pricing or feature facts, because cloud offerings change and the files give general figures such as 30-70% savings without sources
- Safety-critical or regulated decisions such as data sovereignty compliance, which the skill mentions only briefly and should be verified with specialists
Try asking
- “Compare the equivalent of AWS Lambda, Azure Functions and Google Cloud Functions for a small event-driven service”
- “Propose a disaster recovery pattern that replicates a database into a second cloud provider”
- “Draft a four-phase migration plan from one cloud to another with a dual-run period”
- “List the cost optimization levers available on each provider for a steady-state workload”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 3 original files, the MIT licence and an attribution note.
multi-cloud-architecture.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip multi-cloud-architecture.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip multi-cloud-architecture.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 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 agent your actual workload details (traffic, data size, compliance needs) so the pattern recommendation is specific rather than generic
- Ask the agent to check current service names and pricing against each provider's official documentation, since the included tables are a snapshot
- Treat the suggested cost percentages and best practices as starting points and validate them with your own cloud cost tools
What's inside
- references/multi-cloud-patterns.md
- references/service-comparison.md
- SKILL.md
Redistributed unmodified from wshobson/agents under the MIT 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.