Skip to content

aws/aws-startup-advisor

v2.1.0Apache-2.0

AWS Startup Advisor puts an AWS Startups Solutions Architect in your coding assistant. It recommends the smallest architecture that fits your stage, credits, and team, then can scaffold it, migrate you from Azure, Google Cloud, Heroku, or Render, move your model calls to Amazon Bedrock, and investigate production incidents. It also answers your AWS Activate credits eligibility questions and finds startup offers you can use.

agent-advisor

Entry point for AI-agent work on AWS: pick a runtime, plan a migration, and build a POC. Triggers on: which runtime for my agent, AgentCore vs ECS vs EKS vs Lambda, AgentCore vs Lambda MicroVMs, deploy an AI agent on AWS, agent architecture on AWS, is my agent on the right runtime, I have an agent idea what do I build, move/migrate my agents to AWS (including from GCP, Azure or Heroku), agent migration plan, add AgentCore services (memory, gateway, identity, policy, observability) to an agent already on AWS, Temporal on AWS (migrate/run Temporal workers, a service orchestrated by Temporal, Temporal Cloud vs self-hosted). Temporal Workflow code is never rewritten into Step Functions. Requires at least one agentic component; non-agent systems (plain services, batch jobs, HTTP endpoints, non-agent Activities) go to gcp-to-aws / heroku-to-aws / llm-to-bedrock, and self-hosted LLM batch inference to self-hosted-llm-batch-inference. Not for: pure LLM SDK rewrite; per-model pricing; Well-Architected reviews.

architect-for-startups

Startup-tailored AWS architecture advice for non-agent workloads, adjusted to stage (pre-revenue through Series B+), team size, runway, and credits. Not for AI agents: deploying one, picking its runtime, or any agentic architecture is agent-advisor. Use when a founder wants guidance or a recommendation rather than code changes: which services to choose, designing or reviewing an architecture, tenant isolation for a multi-tenant SaaS, stretching credits and controlling cost, or preparing for a fundraise or technical diligence. Interactive scaffolding into the codebase is start-building-for-startups. Do not use for: writing code, Activate / programs / credits lookups (knowledge-base-for-startups), a copy-paste prompt (prompt-library-for-startups), pricing an infrastructure change before it ships (cost-regression-check), self-hosted LLM batch inference (self-hosted-llm-batch-inference), or migration intent (gcp-to-aws, azure-to-aws, heroku-to-aws, llm-to-bedrock).

azure-to-aws

Migrate Microsoft Azure workloads to AWS. Triggers on: Azure to AWS, move off Azure, AKS to EKS, App Service or Azure VMs to AWS compute, Azure SQL/Database to RDS, Cosmos DB to DynamoDB, Azure OpenAI to Bedrock, Azure cost estimates, or what-if workshops. Discovery uses the authenticated read-only az CLI, Terraform, a Resource Discovery for Azure (RDfA) report, and app code, with optional consent-gated OpenAI, OpenRouter, and Anthropic usage APIs. Terraform is optional. Runs Discover, Clarify, Design, Estimate, optional repricing, Generate, and Feedback; Clarify gates later phases and Generate is opt-in. Bicep/ARM discovery is not implemented; billing-export discovery is not implemented. Do not use for GCP or Heroku migrations, reverse migrations, general AWS architecture, or Azure-to-Azure refactoring.

bedrock-migration-assessment

Source-cloud-neutral assessment of AI/LLM usage for a migration to Amazon Bedrock. Use when the user wants to find which OpenAI (direct or Azure OpenAI), Anthropic, Google/Gemini, or OpenRouter calls their code makes, or already has a provider-neutral ai-workload-profile.json (schema 1.0 or 1.1), and wants to choose and price Bedrock models for it. It scans the code or validates the profile, can measure OpenAI, Anthropic, and OpenRouter usage read-only with the user's consent and an admin or management key, shows a short preview, runs Clarify, designs a Bedrock target, endpoint, and client API per workload, then estimates the monthly Bedrock cost against the current provider, and needs no infrastructure skill installed. This release stops after Estimate: it does not generate artifacts or rewrite code. To rewrite SDK calls to Bedrock and get a branch, use llm-to-bedrock; for infrastructure migrations use gcp-to-aws, azure-to-aws, or heroku-to-aws.

contextual-offers-for-startups

Surfaces a single, genuinely relevant AWS Activate partner offer as optional context AFTER another AWS Startup Advisor skill has finalized its recommendation, plan, or build — never influencing the technical advice. Consulted by architect-for-startups, start-building-for-startups, agent-advisor, gcp-to-aws, heroku-to-aws, and llm-to-bedrock: once their output is final, this skill checks whether a relevant Activate offer exists for what the founder is building or migrating and, if so, appends one quiet, dismissible line with a tracked redeem link. Merit-first (offers never change the recommendation), relevance-gated to what the founder actually surfaced, at most one per response and often none, muteable. Offer content is read live from the sibling knowledge-base-for-startups skill (references/offers.md). Do NOT use for account-specific lookups (credits balance, Activate membership, application status) — send those to https://aws.amazon.com/startups.

cost-regression-check

This skill should be used when a company that pays its AWS bill from a fixed monthly ceiling, often funded by credits, asks what a pull request or other infrastructure-as-code change (Terraform, AWS CDK, or AWS CloudFormation) will add to that bill before apply, or wants that cost on every pull request, including through Infracost or another estimator in CI. It reports two numbers at list price before credits: the fixed monthly floor added at zero traffic, and the change in cost per unit of the team's own usage, against absolute thresholds derived from the ceiling and kept in the repository. It sets up a CI job and a repository-owned script so the author and the bill owner decide on each pull request. Not for spend that already happened (aws-core:aws-billing-and-cost-management), price lookups with no change under review, advice on infrastructure code as it stands, general release risk, or choosing services that avoid a floor.

gcp-to-aws

Migrate GCP workloads to AWS, including AI and agentic workloads from any provider. Triggers on: migrate from GCP, GCP to AWS, move off Google Cloud, Cloud SQL to RDS, GKE to EKS, Cloud Run to Fargate, App Engine to Elastic Beanstalk, or OpenAI/Gemini/agentic workloads to Bedrock. Discovery uses the authenticated read-only gcloud CLI, Terraform, app code, or billing exports, with optional consent-gated OpenAI, OpenRouter, and Anthropic usage APIs. Terraform is optional. Runs Discover, Clarify, Design, Estimate, Generate, and Feedback; Clarify gates later phases. Do not use for Azure migrations (see azure-to-aws), reverse migrations, general AWS architecture without migration intent, or GCP-to-GCP refactoring.

heroku-to-aws

Migrate workloads from Heroku to AWS. Triggers on: migrate from Heroku, Heroku to AWS, move off Heroku, migrate Heroku Postgres to RDS, migrate Heroku Redis to ElastiCache, migrate Heroku Kafka to MSK, migrate dynos to Elastic Beanstalk, migrate dynos to Fargate, migrate Heroku Private Space, Heroku to ECS, leave Heroku, what-if workshop, compare migration scenarios, workshop mode. Runs a 6-phase process: discover Heroku resources live via the authenticated Heroku CLI (read-only, consent-gated) and/or from Terraform, Procfile/app.json, and billing exports; Terraform is optional. Then clarify, design, estimate costs, generate artifacts, and collect feedback. Clarify must finish before Design, Estimate, or Generate. An optional post-Estimate what-if workshop reprices region/HA/compute/Graviton scenarios. Do not use for: GCP migrations (see gcp-to-aws), Azure migrations (see azure-to-aws), AWS-to-Heroku reverse migration, general AWS architecture advice without migration intent, or Heroku-to-Heroku refactoring.

knowledge-base-for-startups

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.

llm-to-bedrock

Use to migrate code that calls OpenAI, Gemini/Google AI, or the Anthropic API to Amazon Bedrock — a pure model/SDK rewrite. End-to-end: assesses the codebase, optionally captures OpenAI, OpenRouter, or Anthropic cost and token usage through consent-gated provider APIs, rewrites SDK calls, evaluates output quality against Bedrock, and delivers a ready-to-merge branch. Also has an access-only mode for checking or enabling Bedrock model access for specific models (e.g. 'request access to Claude on Bedrock', 'which models do I turn on') with no code migration — it checks each model and walks the access step, then stops. Not for agent runtime selection or agent migration planning (use agent-advisor), self-hosted LLM batch inference (use self-hosted-llm-batch-inference), nor standalone cost estimates or infra-only migration. The full migration REQUIRES gcp-to-aws OR azure-to-aws installed alongside this skill (gcp-to-aws preferred when both are present); access-only mode needs neither.

operate-on-aws

Operate a live AWS workload with AWS DevOps Agent — incident investigation, root-cause analysis, and release-readiness review — for startups with no dedicated DevOps or SRE engineer. Use when a live AWS workload is misbehaving (production is down, 5xx errors, latency spike, timeouts, it broke after the last deploy, an alarm fired, a pasted CloudWatch alarm or stack trace, find the root cause, write a postmortem, no one on call), for pre-merge review (is this PR safe to ship, blast radius), or to set up, pause, stop, or check the cost of AWS DevOps Agent. Detects existing setup first and never re-onboards. Asks one explicit Yes/No covering cost (two-month trial, Activate credits) and account access before any setup; code egress stays off unless asked. Do not use for: new architecture (architect-for-startups), scaffolding (start-building-for-startups), migrations (gcp-to-aws, azure-to-aws, heroku-to-aws, llm-to-bedrock), or general Activate and credits questions (knowledge-base-for-startups).

prompt-library-for-startups

AWS-curated copy-paste prompts for AI coding agents (MVP scaffolding, RAG chatbot with Claude on Bedrock, security baseline evaluation, read-only cost audit, GPU quota requests, EKS on Spot, OWASP ZAP scan, etc.) plus downloadable installable agents (Multi-Account Transition Advisor, Bill Shock Preventer, Service Quota Agent, Bedrock Model Availability Agent, Kiro Strands AgentCore Agent). Use when the user asks for a prompt to do X on AWS, wants an installable agent for multi-account / cost monitoring / quota management / Bedrock model availability / a Strands agent on AgentCore, or asks how to use AWS prompts. Bundles an approved subset; for any other prompt or agent, point to startups.aws.com/prompt-library. For migration intent (GCP to AWS, Azure to AWS, OpenAI/Gemini to Bedrock), route to the migration skills in this plugin (gcp-to-aws, azure-to-aws, heroku-to-aws, llm-to-bedrock). Do not use for: factual AWS Activate / programs / credits questions, learn articles, or sample architectures.

render-to-aws

Migrate Render workloads to AWS through consented read-only discovery, mandatory clarification, architecture design, cost estimation, an optional what-if workshop, and opt-in artifact generation. Covers Render Blueprints, services, static sites, workers, cron jobs, private services, Workflows, PostgreSQL, Key Value, persistent disks, Build Sources, projects, environments, and provider-neutral AI workload discovery. Does not use Render MCP or perform Render-side mutations.

self-hosted-llm-batch-inference

This skill should be used when a startup without a dedicated ML platform team needs recurring, latency-tolerant offline inference for a self-hosted 1B to 8B generative language model on AWS while minimizing GPU spend and recovering automatically from Spot interruption. It prescribes AWS Batch backed by Amazon ECS Managed Instances Spot, with model artifacts staged in Amazon S3, deterministic input shards, vLLM offline inference on one GPU, bounded retries, and output reconciliation before success. Covers sizing from the real prompt and model footprint, choosing networking without an avoidable idle cost floor, and verifying that results are complete and GPU capacity is gone. Not for online endpoints, training, embeddings, other inference engines, multi-GPU or distributed inference, or one-off experiments where manual rerun is acceptable.

start-building-for-startups

Interactive discovery + implementation workflow that gathers requirements through picker-based questions (intent, scope, constraints, preferences), scans the codebase for what it can already infer, then writes an AWS architectural scaffold and implementation directly into the project. Use when the user wants to build a new app, scaffold a project, or expand/refactor an existing one on AWS — anything that calls for a structured discovery flow followed by code changes, not a one-off lookup. Do not use for: factual lookups about AWS Activate / programs / credits, requests for a single copy-paste prompt, non-AWS architectural work, architecture advice/recommendations without code changes (see architect-for-startups), a new idea centered on an AI agent — runtime selection, agentic architecture, or an agent POC (see agent-advisor), or migrating an existing GCP/Azure/Heroku workload or an LLM SDK rewrite (see gcp-to-aws / azure-to-aws / heroku-to-aws / llm-to-bedrock).

tf-best-practices

Best-practice authoring guidance AND a read-only policy gate for AWS Terraform generated by a migration skill. Load during any phase that writes a terraform/ directory — first as the "what to emit" posture rules + security-baseline spec, then after writing as the deterministic policy verdict. Read-only: it reports whether the generated Terraform passes; it never edits .tf files, never touches .phase-status.json, and never decides phase completion. Complements (does not replace) terraform fmt/init/validate.