cloud-architect
An agent skill by Jeffallan, from Jeffallan/claude-skills. Tags: automation, cloud, devops, performance, security, strategy.
What it does
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost optimization, disaster recovery, landing zones, security architecture, serverless design.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add Jeffallan/claude-skills --skill cloud-architect
Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/Jeffallan/claude-skills
cp -r claude-skills/skills/cloud-architect ~/.claude/skills/cloud-architect
Safety box score
Grade C, moderate risk: 37 of 100 risk points, rated 2026-09-23. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This is a documentation-only cloud architecture skill for AWS, Azure, and GCP. Its main risk is that it includes concrete CLI/Terraform examples that can change cloud accounts, create IAM roles, and even purchase or subscribe to billing-related services if an agent runs them verbatim.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 1 (low) | There are no shipped executables or native scripts, but the markdown embeds shell and CLI commands such as `aws ec2 describe-vpc-peering-connections` and `az network vnet peering list` that an agent could run. |
| Network access | 2 (moderate) | It routinely calls cloud control planes and includes a link-local metadata URL (`http://169.254.169.254/latest/meta-data/spot/termination-time`), so running examples can reach remote services. |
| Filesystem reach | 0 (none) | The skill does not describe local file edits or deletes outside the workspace; its writes are to cloud resources or buckets, not the host filesystem. |
| Secrets & credentials | 1 (low) | It references secret-management systems and shows credential-bearing environment variables in `references/multi-cloud.md` (`ACCESS_KEY`, `SECRET_KEY`), but it does not ask the user to paste secrets. |
| Privilege & persistence | 2 (moderate) | It includes account-level access-control changes such as `aws iam create-role` and `aws iam put-role-policy`, which can alter permissions in the cloud account. |
| Instruction hijack surface | 0 (none) | There is no prompt-injection content, instruction-skipping text, or hidden remote instruction fetching in the files provided. |
| Irreversible actions | 3 (high) | The skill includes irreversible cloud operations like `az reservations reservation-order purchase`, plus billing/report and anomaly-subscription commands, so an agent could spend money or change account configuration without a separate approval step. |
| Transparency | 0 (none) | All shipped files are plain markdown and readable; there are no binaries, minified blobs, or runtime-downloaded code. |
Before installing
- Read `references/cost.md` first if you do not want the agent to touch billing or purchase commitments.
- Run it only against a sandbox cloud account or read-only credentials until you trust the workflow.
- Confirm that IAM changes like `aws iam create-role` and `aws iam put-role-policy` are acceptable in your environment.
- Decide whether you are comfortable with the agent querying cloud control planes and the metadata endpoint example.
Rated 2026-09-23 by an automated review of 6 files from the skill's repository.
Source
- Repository
- Jeffallan/claude-skills (all skills from this repository)
- Path
- skills/cloud-architect/SKILL.md
- Branch
- main
- Updated
- 2026-09-19
Related skills
- chaos-engineer — Designs chaos experiments, creates failure injection frameworks, and facilitates game day exercises for distributed systems — producing runbooks.
- kubernetes-specialist — Use when deploying or managing Kubernetes workloads.
- monitoring-expert — Configures monitoring systems, implements structured logging pipelines, creates Prometheus/Grafana dashboards, defines alerting rules.
- sre-engineer — Defines service level objectives, creates error budget policies, designs incident response procedures, develops capacity models.
- agents-deploy — Use when deploying your agent to AWS, or when a deploy has failed.
- aws-cloudformation — Authors, validates, and troubleshoots AWS CloudFormation templates.