aws-dev-toolkit

Amazon Bedrock AgentCore subject matter expert for building production-ready AI agents. Use when prototyping new agents, hardening PoC agents for production, setting up agent observability and evaluation pipelines, or architecting multi-agent systems on AWS.

Read-only AWS environment explorer. Use proactively when you need to understand the current state of AWS resources, investigate infrastructure, or gather context about deployed services before making changes.

Amazon Bedrock subject matter expert emphasizing cost-efficient usage patterns. Use when designing Bedrock-based solutions, selecting models, architecting agent workflows, configuring knowledge bases, or when you need practical Bedrock guidance that won't blow the budget.

Container expert for ECS, EKS, and Fargate. Use when choosing between container orchestrators, designing deployment strategies, configuring networking and auto-scaling, or setting up CI/CD for containerized workloads on AWS.

Deep AWS cost optimization expert. Use when analyzing AWS spend, rightsizing resources, evaluating Reserved Instances or Savings Plans, optimizing data transfer costs, or building a cost governance strategy.

Reviews infrastructure-as-code changes for correctness, security, and best practices. Use proactively after IaC code changes to catch issues before deployment.

Cloud migration expert. Use when assessing workloads for migration to AWS, planning migration waves, identifying dependencies, estimating effort, or selecting the right migration strategy and AWS tools.

AWS networking expert covering VPC design, hybrid connectivity, DNS, CDN, load balancing, and service connectivity. Use when designing network architectures, troubleshooting connectivity, planning hybrid/multi-account networking, or optimizing network performance and cost.

AWS observability expert covering CloudWatch, X-Ray, and OpenTelemetry. Use when designing monitoring strategies, building dashboards, setting up alarms, troubleshooting with distributed tracing, or implementing log aggregation patterns.

Serverless architecture expert for Lambda, API Gateway, Step Functions, EventBridge, and DynamoDB. Use when designing event-driven architectures, optimizing Lambda performance, modeling serverless costs, or building serverless workflows.

Conducts deep AWS Well-Architected Framework reviews of workloads. Use when performing a formal Well-Architected review, auditing architecture against the six pillars, identifying high-risk issues in an AWS environment, or creating improvement plans. Runs assessment commands to gather evidence.

Deep-dive into Amazon Bedrock AgentCore platform design, service selection, deployment, and production operations. This skill should be used when the user asks to "design an AgentCore architecture", "deploy agents on AgentCore", "configure AgentCore Runtime", "set up AgentCore Memory", "use AgentCore Gateway", "configure AgentCore Identity", "set up AgentCore Policy", "plan agent observability", "evaluate agent quality", "move agent PoC to production", or mentions AgentCore, AgentCore Runtime, AgentCore Memory, AgentCore Gateway, AgentCore Identity, AgentCore Policy, AgentCore Evaluations, AgentCore Code Interpreter, AgentCore Browser, A2A protocol, or multi-agent orchestration on AWS.

Design and configure Amazon API Gateway APIs. Use when choosing between REST and HTTP APIs, setting up authorizers, configuring throttling, managing custom domains, implementing WebSocket APIs, or troubleshooting API Gateway issues.

Design and review AWS architectures following Well-Architected Framework principles. Use when planning new infrastructure, reviewing existing architectures, evaluating trade-offs between AWS services, or when asked about AWS best practices.

Compare 2-3 AWS architecture options side-by-side across cost, complexity, performance, security, and operational burden. Use when evaluating trade-offs between approaches or when the user is deciding between options.

Debug AWS infrastructure issues, deployment failures, and runtime errors. Use when troubleshooting CloudFormation stack failures, Lambda errors, ECS task failures, permission issues, networking problems, or any AWS service misbehavior.

Generate AWS architecture diagrams in Mermaid or ASCII from a description, existing IaC, or conversation context. Use when the user wants to visualize an architecture.

Quick health check on the current AWS account — security posture, cost waste, reliability gaps, and operational readiness. Lighter than a full Well-Architected review.

Guided migration assessment and planning — discover source environment, map services, estimate effort, and plan migration waves. Orchestrates gcp-to-aws, azure-to-aws, and the migration-advisor agent.

End-to-end AWS architecture planning — discovery, design, security review, cost estimate, and SCP recommendations. Use when someone wants to build something on AWS, plan infrastructure, or design a new workload.

Azure to AWS migration guidance with service mappings, gotchas, and assessment. Use when migrating from Microsoft Azure, mapping Azure services to AWS equivalents, assessing Azure environments, or planning Azure-to-AWS migrations.

Deep-dive into Amazon Bedrock — model selection, agents, knowledge bases, guardrails, prompt engineering, and cost modeling. This skill should be used when the user asks to "build with Bedrock", "select a Bedrock model", "design a Bedrock agent", "set up a knowledge base", "configure guardrails", "estimate Bedrock costs", "optimize Bedrock pricing", "use prompt caching", "compare Bedrock models", or mentions Amazon Bedrock, foundation models, RAG on AWS, or generative AI on AWS.

Adversarial reviewer that stress-tests other agents' outputs for reasoning gaps, unsupported assumptions, over-engineering, and missed alternatives. Use when validating an architecture recommendation, questioning a migration plan, challenging a cost estimate, or ensuring any agent output is battle-tested before acting on it.

Design and configure Amazon CloudFront distributions. Use when setting up CDN for web applications, configuring cache behaviors, origins, Lambda@Edge, CloudFront Functions, signed URLs, WAF integration, or debugging cache issues.

Analyze and optimize AWS costs. Use when reviewing infrastructure for cost savings, estimating costs for new architectures, investigating unexpected charges, or comparing pricing between service options.

Guide customers from idea to AWS architecture with structured discovery, service selection, and Well-Architected review. Use when brainstorming new projects on AWS, helping customers choose AWS services, designing new architectures, or when someone says "I have an idea" or "I want to build something on AWS".

Deep-dive into Amazon DynamoDB table design, access patterns, and operations. Use when designing DynamoDB schemas, choosing partition keys, planning GSI/LSI strategies, implementing single-table design, configuring capacity modes, or troubleshooting performance issues.

Design, configure, and optimize Amazon EC2 workloads. Use when selecting instance types, configuring auto-scaling groups, working with launch templates, managing Spot instances, choosing storage (EBS vs instance store), or troubleshooting EC2 issues.

Design, deploy, and troubleshoot Amazon ECS workloads. Use when working with container orchestration on AWS, choosing between Fargate and EC2 launch types, configuring task definitions, services, load balancing, auto-scaling, or deployment strategies.

Design, deploy, and troubleshoot Amazon EKS clusters. Use when working with Kubernetes on AWS, configuring managed node groups or Fargate profiles, setting up IRSA or Pod Identity, managing EKS add-ons, autoscaling with Karpenter, or troubleshooting cluster issues.

GCP to AWS migration guidance with service mappings, gotchas, and assessment. Use when migrating from Google Cloud Platform, mapping GCP services to AWS equivalents, assessing GCP environments, or planning GCP-to-AWS migrations.

Scaffold new AWS infrastructure-as-code projects using CDK, Terraform, SAM, or CloudFormation. Use when creating new IaC projects, adding new stacks/modules, or setting up deployment pipelines for AWS infrastructure.

Design and review AWS IAM configurations. Use when creating IAM policies, roles, permission boundaries, SCPs, configuring Identity Center (SSO), analyzing access with Access Analyzer, implementing least privilege, or debugging permission issues.

Deep-dive into AWS IoT architecture, device connectivity, edge computing, and fleet management. This skill should be used when the user asks to "design an IoT solution", "connect devices to AWS", "set up MQTT messaging", "configure IoT rules", "provision a device fleet", "use Greengrass at the edge", "build a device shadow", "set up IoT security", "manage OTA updates", "store telemetry data", "create IoT topic rules", "configure fleet provisioning", or mentions IoT Core, MQTT, Greengrass, Device Shadow, IoT Rules Engine, IoT Events, IoT SiteWise, fleet indexing, or device certificates.

Design, build, and optimize AWS Lambda functions. Use when creating new Lambda functions, troubleshooting cold starts, configuring event sources, optimizing performance, managing layers and concurrency, or choosing deployment strategies.

Deep-dive into AWS messaging services including SQS, SNS, and EventBridge. Use when designing event-driven architectures, choosing between messaging services, configuring queues and topics, implementing fan-out patterns, setting up dead-letter queues, or troubleshooting message delivery issues.

End-to-end MLOps guidance on AWS — platform selection, training, inference, pipelines, monitoring, and cost optimization. This skill should be used when the user asks to "build an ML pipeline", "deploy a model on SageMaker", "set up MLOps", "configure SageMaker Pipelines", "choose between SageMaker and Bedrock", "deploy ML models to production", "set up model monitoring", "use MLflow on AWS", "train a model with Spot instances", "configure inference endpoints", "set up distributed training", or mentions SageMaker, MLflow, Kubeflow, ML pipelines, model registry, model monitoring, hyperparameter tuning, inference endpoints, or MLOps on AWS.

Design and troubleshoot AWS networking. Use when planning VPC architectures, configuring subnets, security groups, NACLs, VPC endpoints, Transit Gateway, VPC peering, Route53, NAT Gateways, or debugging connectivity issues.

Design and implement AWS observability solutions. Use when configuring CloudWatch metrics, logs, alarms, dashboards, Logs Insights queries, X-Ray tracing, anomaly detection, or debugging monitoring gaps.

Deep-dive into Amazon RDS and Aurora database design, engine selection, high availability, and operations. This skill should be used when the user asks to "design an RDS database", "choose between RDS and Aurora", "configure Aurora Serverless", "set up read replicas", "plan a database migration", "configure RDS Proxy", "tune database parameters", "set up Multi-AZ", "plan blue/green deployments", or mentions RDS, Aurora, Aurora Serverless v2, database failover, or relational database design on AWS.

Deep-dive into Amazon S3 bucket configuration, storage optimization, and access control. Use when designing S3 storage strategies, configuring bucket policies and access controls, optimizing performance for large-scale workloads, setting up lifecycle policies, or troubleshooting S3 access issues.

Review AWS infrastructure code and configurations for security issues. Use when auditing IAM policies, reviewing IaC templates for security misconfigurations, checking for exposed resources, or hardening AWS environments.

Design and build AWS Step Functions workflows. Use when orchestrating multi-step processes, implementing saga patterns, coordinating parallel tasks, handling retries and error recovery, or choosing between Standard and Express workflows.

Scaffold and build AI agents using the Strands Agents SDK with Bedrock AgentCore. Use when creating new agent projects, building greenfield AgentCore applications, prototyping agents with Strands, or when asked about the Strands framework. Covers both TypeScript and Python.

Run formal AWS Well-Architected Framework reviews against workloads. Use when conducting a Well-Architected review, evaluating architecture against the six pillars, identifying high-risk issues, creating improvement plans, or when someone asks about Well-Architected best practices, lenses, or the WA Tool.