菜单
Use when working with AWS, GCP, or Azure resource management, permissions, or deployments
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | cloud-operations |
| description | Use when working with AWS, GCP, or Azure resource management, permissions, or deployments |
tooling/cloud/. Scaffold IAM policies, cloud configs.# Check current identity
aws sts get-caller-identity
# List resources
aws ec2 describe-instances --query 'Reservations[].Instances[].[InstanceId,State.Name,Tags[?Key==`Name`].Value|[0]]' --output table
# CloudWatch logs
aws logs describe-log-groups
aws logs tail /aws/lambda/my-function --follow
# ECS
aws ecs describe-services --cluster my-cluster --services my-service
aws ecs describe-tasks --cluster my-cluster --tasks <task-arn>
| Error | Fix |
|---|---|
AccessDenied | Add required action to IAM policy |
ThrottlingException | Implement exponential backoff retry |
InvalidClientTokenId | Check AWS credentials and region config |
NoSuchBucket | Wrong region or bucket name |
Always scope policies to specific resources:
{
"Effect": "Allow",
"Action": ["s3:GetObject", "s3:PutObject"],
"Resource": "arn:aws:s3:::my-bucket/*"
}
# Check current identity
gcloud auth list
gcloud config get-value project
# View logs
gcloud logging read "severity>=ERROR" --limit=50
# GKE
gcloud container clusters get-credentials my-cluster --zone us-central1-a
kubectl get nodes
# Check current identity
az account show
# View resources
az resource list --output table
# AKS
az aks get-credentials --resource-group my-rg --name my-cluster
tooling/cloud/aws/ — IAM, ECS, Lambda, S3 configstooling/cloud/gcp/ — GKE, Cloud Run, IAM configstooling/cloud/azure/ — AKS, App Service configsUse before any DevOps build, change, or new feature — refine requirements through dialogue before touching infrastructure or code
Use when working with Docker — building images, writing Dockerfiles, debugging container issues
Use to execute a written implementation plan via subagents with review checkpoints
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Use when working with Kubernetes or Helm — authoring, reviewing, hardening, or debugging manifests, Deployments, Services, Ingress, RBAC, NetworkPolicy, or cluster operations
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation