Skip to the content
Agent Tools

AWS Startup Advisor

Partner, reviewed

Personalized AWS guidance built on patterns from 350,000+ startups—architecture, cost, security, and migration, from day-one account setup to production-ready infrastructure. Migrate to AWS from GCP or Heroku—including your entire AI stack: OpenAI/Gemini/Anthropic SDK rewrites to Amazon Bedrock,…

Plugin · by awslabs · runs in Claude Code, Cowork, claude.ai · 9 skills, 4 MCP servers, 6 agents, 1 hook · listed 2026-06-01

Claude Code

claude plugin install aws-startup-advisor

Skills (9)

  • Skill agent-advisor

    Unified entry point for AI-agent work on AWS: evaluate and pick a runtime, generate a full migration plan (for existing workloads), and build an executable POC — all in one flow.

    Any agent

    npx skills add awslabs/startups --skill agent-advisor
  • Skill architect-for-startups

    Startup-tailored AWS architecture advice that adjusts recommendations to the company's stage (pre-revenue through Series B+), team size, runway, and available credits.

    Any agent

    npx skills add awslabs/startups --skill architect-for-startups
  • Skill gcp-to-aws

    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…

    Any agent

    npx skills add awslabs/startups --skill gcp-to-aws
  • Skill heroku-to-aws

    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…

    Any agent

    npx skills add awslabs/startups --skill heroku-to-aws
  • Skill 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…

    Any agent

    npx skills add awslabs/startups --skill knowledge-base-for-startups
  • Skill llm-to-bedrock

    Use when the user wants to migrate code that calls OpenAI, Gemini/Google AI, or the Anthropic API to Amazon Bedrock — a pure model/SDK rewrite.

    Any agent

    npx skills add awslabs/startups --skill llm-to-bedrock
  • Skill prompt-library-for-startups

    AWS-curated copy-paste prompts for AI coding agents (MVP scaffolding, RAG chatbot with Claude on Bedrock, security baseline evaluation, cost anomaly detection, GPU quota requests, EKS deployment…

    Any agent

    npx skills add awslabs/startups --skill prompt-library-for-startups
  • Skill 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…

    Any agent

    npx skills add awslabs/startups --skill start-building-for-startups
  • Skill 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"…

    Any agent

    npx skills add awslabs/startups --skill tf-best-practices

Agents (6)

  • Agent generic-phase-worker-rw

    Generic, phase-AGNOSTIC worker that runs ONE migration phase's work (its fragments + assembler) in an isolated context and writes the phase's artifact(s) to disk.

  • Agent llm2bedrock-code-analyzer

    Analyze the local source repo, detect the AI framework and LLM SDK usage, map all call sites, identify prompts, and enumerate user-visible behavior-deltas for the Bedrock migration.

  • Agent llm2bedrock-code-rewriter

    Rewrite LLM SDK calls to Amazon Bedrock on a dedicated git branch, swap dependencies, generate tests, and apply the user-confirmed behavior-delta decisions. Returns a structured rewrite object.

  • Agent llm2bedrock-log-ingestor

    Parse LLM API logs from the local repo, extract prompt/response pairs, and build a golden dataset (prompts.jsonl) for evaluation. Returns a structured ingestion object.

  • Agent llm2bedrock-prompt-evaluator

    Run each golden prompt against the target Bedrock model via the pinned uv harness, score with LLM-as-judge, and report a pass rate.

  • Agent llm2bedrock-report-generator

    Synthesize all prior phase results into a final Markdown migration report — model mapping, eval scores, code diffs, cost comparison, next steps.

From Anthropic's public plugin directory, read on 2026-10-15. Find a skill by task.