aws-specialist
Deep-dive AWS architecture review, debugging, and service design. Use for structured investigations of AWS-specific issues, cost or IAM audits, and multi-service design reviews. Triggers on: "AWS audit", "AWS design review", "IAM review", "cost audit AWS", "review my VPC", "AWS troubleshooting", "Lambda deep-dive".
- License 许可
- MIT
- 最近更新
- 2026-10-26
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- aws-specialist
- description
- Deep-dive AWS architecture review, debugging, and service design. Use for structured investigations of AWS-specific issues, cost or IAM audits, and multi-service design reviews. Triggers on: "AWS audit", "AWS design review", "IAM review", "cost audit AWS", "review my VPC", "AWS troubleshooting", "Lambda deep-dive".
- allowed-tools
- Read Grep Glob Bash
- argument-hint
- <account context, service, or problem description>
02 资源文件 7
- 参考文档references/compute.md2.4 KB
- 参考文档references/iac-patterns.md3.0 KB
- 参考文档references/iam.md2.9 KB
- 参考文档references/networking.md3.0 KB
- 参考文档references/observability.md2.7 KB
- 参考文档references/serverless.md2.6 KB
- 参考文档references/storage.md3.1 KB
03 SKILL.md 正文
AWS Specialist
Structured investigation for AWS workloads. Five phases: gather context, diagnose, design, recommend, verify.
Arguments
$0— account context, service scope, or problem description. Required.
Phase 1: Context Gathering
- Identify the account(s), region(s), and services in scope.
- Glob for IaC in the working directory:
**/*.tf,**/*.yaml(SAM/CloudFormation),**/cdk.json,**/template.yaml. - If AWS CLI access is available:
aws sts get-caller-identity aws configure list - Note the service scope (e.g. "EKS cluster + VPC + IAM" vs "Lambda + API Gateway + DynamoDB"). Scope commands to the relevant resource types.
Phase 2: Diagnosis
Compute / containers:
aws ec2 describe-instances --filters Name=instance-state-name,Values=running
aws ecs list-services --cluster <name>
aws eks describe-cluster --name <name>
IAM / identity:
aws iam list-policies --scope Local
aws iam get-role --role-name <role>
aws iam simulate-principal-policy --policy-source-arn <arn> --action-names <action>
Networking:
aws ec2 describe-vpcs
aws ec2 describe-route-tables
aws ec2 describe-security-groups
Serverless / events:
aws lambda list-functions
aws lambda get-function-configuration --function-name <name>
aws apigateway get-rest-apis
Cost / quotas:
aws service-quotas list-service-quotas --service-code ec2
aws ce get-cost-and-usage --time-period Start=<>,End=<> --granularity DAILY --metrics UnblendedCost
Phase 3: Design / Root-Cause Analysis
Map symptoms to causes:
| Symptom | Common Causes | Check |
|---|---|---|
| 5xx from ALB | Unhealthy targets, timeout mismatch, HTTP/S misrouting | Target group health, ALB access logs |
| Lambda throttled | Reserved concurrency, account-wide limit | aws lambda get-function-concurrency |
| EKS pod IAM fails | Missing IRSA, ServiceAccount annotation | OIDC provider + trust policy on role |
| S3 AccessDenied | Bucket policy, SCP, VPC endpoint policy | Use aws s3api get-bucket-policy + IAM simulator |
| RDS CPU spike | Missing indexes, connection storm, runaway query | Performance Insights, slow query log |
| CloudFront caching miss | Incorrect cache key, missing Cache-Control |
Check behaviors + origin headers |
Cite resource ARN or file:line for every finding.
Phase 4: Recommendations
Output findings in priority order:
[CRITICAL] <title>
Resource: <ARN or file:line>
Issue: <one sentence>
Evidence: <CLI output or code snippet>
Fix: <specific change, with IaC diff if applicable>
Trade-off: <alternative and its downside, if meaningful>
- Order: CRITICAL → WARNING → INFO.
- For IaC fixes, show the exact Terraform/CDK/CloudFormation diff.
- Reference relevant docs in
references/where applicable.
Phase 5: Verification
After fixes are applied:
- Re-run the diagnostic command that surfaced the issue.
- For IAM changes:
aws iam simulate-principal-policywith the exact action and resource. - For networking changes:
aws ec2 describe-route-tablesor VPC Reachability Analyzer. - For serverless changes: invoke a test event via
aws lambda invokeor API Gateway test console. - Check CloudWatch metrics and alarms — no new alarms should be triggering.
Reference Docs
Consult references/ for decision guides:
| File | When to use |
|---|---|
compute.md |
EC2, ECS, EKS selection and sizing |
serverless.md |
Lambda, API Gateway, EventBridge, SQS, SNS |
storage.md |
S3, EBS, EFS, RDS, DynamoDB |
networking.md |
VPC, ALB/NLB, Route53, CloudFront, PrivateLink |
iam.md |
Policies, roles, SCPs, permission boundaries |
observability.md |
CloudWatch, X-Ray, Container Insights |
iac-patterns.md |
CloudFormation, CDK, SAM patterns |
04 同仓库更多 Skills
yolo
Start temporary autonomy for the current task or an explicit scope with a required --for expiry. Codex permits scoped pushes, merges, deploys, and releases after strict testing and validation; Full access is a separate runtime setting. Claude Code uses a session permission hook with a protected-action denylist.
veracity-audit
Audit a data pipeline for Veracity and Value. Dispatches data-scientist, compliance-auditor, and data-engineer agents with project context injected at dispatch time. All source paths are supplied via flags — no defaults, no project assumptions. Subcommands: audit (full pipeline walk), score-check (scoring math only), gate-check (gate coverage only), source-trace <label> (single source end-to-end). Invoke when: "audit pipeline", "veracity check", "scoring math correct?", "check gates", "trace source", "verify quality gates", "formula correct?".
validate-spec
Audit an already-implemented spec against the codebase. Walks each constraint (ARCH-N, PERF-N, KD-N, etc.) and acceptance criterion, grounds findings in file:line evidence, runs the spec.json acceptance_commands, and writes a single audit doc to docs/audits/. Use whenever the user asks to "validate a spec", "audit a spec", "check if spec is implemented", "verify the spec is done", "is this spec really done", or otherwise wants closure on spec-driven work. Read-only against the spec — produces an audit, never modifies the spec itself.
terragrunt-specialist
Deep-dive Terragrunt hierarchy review, DRY pattern audits, and run-all orchestration analysis. Use for structured investigations of multi-environment Terragrunt layouts, dependency graphs, remote state config, and hook correctness. Triggers on: "Terragrunt audit", "run-all review", "dependency block", "DRY pattern review", "env hierarchy audit", "mock_outputs", "terragrunt hooks".
terraform-specialist
Deep-dive Terraform architecture review, module design, state management, and migration. Use for structured investigations of Terraform workspaces, provider configuration, module coupling, import workflows, and test coverage. Triggers on: "Terraform audit", "module review", "state management", "Terraform import", "workspace design", "provider config review", "Terraform testing".
spec
Create structured engineering specs through interactive pairing. Use when the user wants to create a spec, design doc, technical specification, architecture document, RFC, or engineering plan. Triggers on "let's spec this out", "create a spec", "design doc", "write a technical plan", "plan the architecture". Works for greenfield and brownfield projects. Outputs to docs/specs/.