startups

Migrate workloads from Google Cloud Platform to AWS — including AI and agentic workloads regardless of cloud provider. Triggers on: migrate from GCP, GCP to AWS, move off Google Cloud, migrate Terraform to AWS, migrate Cloud SQL to RDS, migrate GKE to EKS, migrate Cloud Run to Fargate, Google Cloud migration, migrate from OpenAI to Bedrock, move off OpenAI, switch from ChatGPT API to AWS, migrate from Gemini to Bedrock, migrate LangChain to Bedrock, migrate LangGraph to AWS, migrate agentic workloads to AWS, move AI workloads to AWS, migrate my AI app to AWS. Runs a 6-phase process: discover GCP resources from Terraform files, app code, or billing exports, clarify migration requirements, design AWS architecture, estimate costs, generate migration artifacts, and collect optional feedback. Clarify must finish before Design, Estimate, or Generate. Includes AI provider migration guidance (for example, OpenAI to Amazon Bedrock) by selecting closest-fit Bedrock model families for required modality, latency/quality

Migrate workloads from Heroku to AWS. Triggers on: migrate from Heroku, Heroku to AWS, move off Heroku, migrate Heroku app, migrate Heroku Postgres to RDS, migrate Heroku Redis to ElastiCache, migrate Heroku Kafka to MSK, migrate dynos to Fargate, Heroku migration, move from Heroku to AWS, migrate Heroku Private Space, Heroku to ECS, Heroku to Fargate, leave Heroku, migrate off Heroku platform. Runs a 6-phase process: discover Heroku resources from Terraform files, Procfile/app.json, and optional billing exports, clarify migration requirements, design AWS architecture, estimate costs, generate migration artifacts, and collect optional feedback. Clarify must finish before Design, Estimate, or Generate. Uses a flat resource model (no clustering or dependency graphs) with deterministic mapping tables for core services (Dynos → Fargate, Postgres → RDS/Aurora, Redis → ElastiCache, Kafka → MSK) and a fast-path table for 13+ common add-ons. Cedar/Fir generation detection is detect-only in v1. Pipeline/Review Apps ar

Lightweight AI development lifecycle for building on AWS. A simplified take on the AI-DLC philosophy — think together, then build fast. Acts as a design partner that understands intent, proposes alternatives with trade-offs, and ships working code without the ceremony of full requirements/design/spec documents. Use when a founder says "build X on AWS", "add Y to my stack", "scaffold an API", or "write the CDK for Z".

Pre-verified fixes for Amazon Bedrock pitfalls — response key casing, IAM inference profile ARNs, model ID format, vision image normalization. Load during Bedrock-related migration work (Track 2 LLM migration or app code touching Bedrock).

Detect user-visible parameter-surface differences between source LLM provider and Bedrock. Loaded by ai-code-analyzer (Track 2) when source_provider is openai or google and same_model_family is false; consumed by ai-code-rewriter to apply the resolutions the user confirmed at the orchestration checkpoint.

Allowlist gate that blocks the rewriter from removing customer-pre-existing dependencies during dependency edits. Load before committing manifest changes. Complements ai-code-rewriter §12's lockfile regeneration; does not replace it.

Use when the user wants to migrate code that calls OpenAI, Gemini/Google AI, or the Anthropic API to Amazon Bedrock. End-to-end: assesses the codebase, then rewrites SDK calls, evaluates output quality against Bedrock, and delivers a ready-to-merge git branch. Not for standalone Bedrock cost estimates or infrastructure-only migration. Requires the migration-to-aws plugin for the Assess phase.

Validate a plan-supplied Bedrock model ID against live inference profiles in the target AWS account and correct it if stale. Load this when a plan's target_model_id needs to be used for the first time (ai-code-analyzer §10), or when a Bedrock call returns "invalid model identifier".

Re-run a JSONL of golden prompts against the live source LLM provider (OpenAI, Anthropic, or Gemini) on the local host and write per-prompt responses to <repo>/.saws-migrate/eval-results/source_baselines.jsonl. Load this from ai-prompt-evaluator §9 when source_baseline_available == true and same_model_family == false; the produced JSONL gives the evaluator real source-vs-Bedrock side-by-side outputs instead of comparing Bedrock against agent-synthesized baselines.

AWS Startups reference content — Activate FAQ, credits guide, programs, partner offers, sample architectures, and hundreds of learn articles spanning generative AI, cloud architecture, cost optimization, security, fundraising, go-to-market, and real-world startup case studies. Use when the user asks factual questions about AWS Activate (eligibility, credits, programs, providers), wants a sample architecture or solution guide, or needs an AWS-curated learn article on a specific startup topic. For copy-paste AI prompts (RAG chatbot, MVP scaffold, security baseline, GPU quota, etc.), see the prompt-library-for-startups skill. Do not use for: account-specific lookups (credits balance, Activate membership status, application status), real-time event listings beyond the events stub, or content not present in the bundled `references/` tree.

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.

Design, deploy, and operate a service mesh on Amazon EKS with Istio. Use when working with service mesh, mTLS between services, east-west traffic management, canary or blue/green traffic shifting, sidecar vs ambient data planes, or migrating off the deprecated AWS App Mesh.

AWS architecture advisor tailored specifically for startups. Alters AWS architecture recommendations based on startup stage (pre-revenue through Series B+), team size, runway, and credits. ALWAYS use when asked about building on AWS, choosing services, planning infrastructure, managing costs with credits, or preparing architecture for fundraising.

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.

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.

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.

This skill should be used when the user asks to "deploy containers on ECS", "set up an ECS service", "choose between Fargate and EC2", "configure ECS task definitions", "set up ECS auto-scaling", "use ECS Express Mode", "migrate from App Runner", or mentions ECS load balancing, deployment strategies, or container orchestration on AWS.

Generate a complete ECS Fargate SOCI (Seekable OCI) example with Terraform. Demonstrates lazy-loading container images for faster task startup using SOCI index v2 manifests. Includes a heavy ML inference container (PyTorch + FastAPI) with and without SOCI for comparison. Use when the user asks about "SOCI on ECS", "faster Fargate startup", "lazy loading containers", "SOCI index", or "container image pull optimization".

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.

Guided migration from AWS App Runner to Amazon ECS Express Mode. Covers IAM setup, deployment, custom domains, DNS cutover, cost comparison, and troubleshooting. Use when the user asks to "migrate from App Runner", "move to ECS Express Mode", "replace App Runner", or mentions App Runner deprecation.

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.

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.

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.