sample-ramp-aidlc-mod-starter-packs

Guides users to build optimal agentic AI workflows OR optimize existing agents. Analyzes use cases, recommends patterns, selects frameworks (LangGraph, CrewAI, Strands), generates production-ready code, and optimizes existing implementations based on Amazon's production lessons.

Specialized agent for optimizing existing agentic AI systems based on Amazon's production lessons and AWS best practices

Generates production-ready agentic AI implementations with AWS best practices

Specialized agent for selecting optimal agentic AI frameworks (LangGraph, CrewAI, Strands)

Specialized agent for identifying optimal agentic AI patterns based on AWS prescriptive guidance

Guides AWS development with infrastructure automation and cloud architecture patterns. Use when designing or refactoring cloud-native applications on AWS, automating environment provisioning with Terraform/CDK/CloudFormation, setting up secure CI/CD pipelines, evaluating service choices for cost/scalability/fault tolerance, or preparing production runbooks and observability.

Infrastructure as Code best practices with Terraform, Ansible, Pulumi, and CloudFormation. Use when bootstrapping cloud environments, managing remote state backends, recovering from state issues, automating CI/CD pipelines for infrastructure, modularizing infrastructure for reuse, enforcing drift detection, or performing risk assessments before applying changes.

Comprehensive AWS infrastructure management with Terraform. Covers provider configuration, state management (S3 backend with native locking in Terraform 1.11+), common resource patterns (VPC, IAM, S3, RDS, EKS), module usage, and production best practices. Use when provisioning AWS infrastructure, managing Terraform state, creating VPCs, configuring IAM roles/policies, deploying databases, or troubleshooting Terraform/AWS issues.

Guidance for building modern, maintainable, accessible Android apps. Use when designing UI, structuring app modules, or reviewing Jetpack Compose code.

Guidance for serverless backend infrastructure (Lambda, Step Functions, API Gateway, S3, DynamoDB, Cognito, Textract, Bedrock). Use when designing or reviewing serverless systems.

Conventions for clean, idiomatic, safe Kotlin. Use when writing or reviewing Kotlin code.

How to think about and write correctness properties and property-based tests. Use when defining properties in design docs or implementing property tests.

Guidance for writing clean, maintainable, secure Terraform (HCL). Use when authoring or reviewing Infrastructure as Code with Terraform.

Use when designing, choosing tools for, or writing automated tests for mobile apps — native iOS, native Android, React Native, and Flutter. Covers Appium, Maestro, Detox, Espresso, XCUITest, emulator/simulator vs real device strategy, device farms (AWS Device Farm, BrowserStack, Sauce Labs), gestures, deep links, permissions, app lifecycle, mobile flakiness, and CI. Triggers on mobile testing, app test, iOS test, Android test, Appium, Maestro, Detox, Espresso, XCUITest, emulator, real device, device farm, deep link, app permissions. For web browser tests, use the web-test-automation skill instead.

Use when designing, choosing tools for, or writing automated tests for web applications — E2E and UI tests, visual regression, web accessibility (axe-core), API testing inside browser flows, flaky-test debugging, page object model, and CI integration. Playwright-first, with Cypress and Selenium guidance and migration paths. Triggers on web testing, browser test, E2E, Playwright, Cypress, Selenium, page object, locator, flaky test, visual regression, accessibility testing, network mocking, CI sharding. For native iOS/Android/React Native/Flutter app tests, use the mobile-test-automation skill instead.

Best practices for building a Nova Sonic speech-to-speech voice agent on AWS. Covers (1) when to choose Nova Sonic over a STT→LLM→TTS pipeline, (2) voice-first system prompt design, (3) tool calling for voice, (4) conversation UX patterns (barge-in, confirmation, disfluencies), and (5) common pitfalls. TRIGGER when: user is designing a new Nova Sonic voice agent; user asks how to write a voice prompt; user asks about speech-to-speech vs STT→LLM→TTS; user asks about tool calling, barge-in, or voice UX with Nova Sonic. SKIP when: user is migrating an existing text agent (use text-agent-to-nova-sonic-voice instead); user is debugging latency or cost (use nova-sonic-optimization instead).

Optimize a Nova Sonic voice agent for low latency, cost, and reliability on AWS. Covers (1) measuring end-to-end and per-segment latency, (2) same-region deployment and network path tuning, (3) streaming inference and tool-call patterns that hide latency, (4) cost levers (provisioned vs on-demand, voice pricing), and (5) reliability across multiple regions. TRIGGER when: user wants to reduce voice latency; user mentions Groq-class responsiveness; user asks about same-region deployment, streaming, or cold start; user wants to control Nova Sonic cost. SKIP when: user is designing a new agent for the first time (use nova-sonic-best-practices); user is migrating from text (use text-agent-to-nova-sonic-voice).

Migrate any text-based agent to a Nova Sonic voice agent using Strands BidiAgent. Covers two layers: (1) Frontend — browser WebSocket client with Web Audio API for mic capture and audio playback, (2) Orchestrator — FastAPI + Strands BidiAgent server that takes the text agent's system prompt and tools and runs them as a real-time speech-to-speech agent. TRIGGER when: user wants to add voice to an existing text agent; user asks about converting a chatbot to a Nova Sonic voice agent; user mentions text-to-voice migration, Strands BidiAgent, or Nova Sonic voice agent. SKIP when: user is building a text-only agent; user wants TTS/STT without a live agent loop; user is asking about deployment or infrastructure.

Build, manage, and operate APIs with Amazon API Gateway (REST, HTTP, and WebSocket). Triggers on phrases like: API Gateway, REST API, HTTP API, WebSocket API, custom domain, Lambda authorizer, usage plan, throttling, CORS, VPC link, private API. Also covers troubleshooting API Gateway errors (4xx, 5xx, timeout, CORS failures) and IaC templates containing API Gateway resources. For general REST API design unrelated to AWS, do not trigger.

Author, validate, and troubleshoot AWS CloudFormation templates. Covers template authoring with secure defaults, pre-deployment validation (cfn-lint, cfn-guard, change sets), and root-cause diagnosis of failed stacks using CloudFormation events and CloudTrail correlation.

Design, build, deploy, test, and debug serverless applications with AWS Lambda. Triggers on phrases like: Lambda function, event source, serverless application, API Gateway, EventBridge, Step Functions, serverless API, event-driven architecture, Lambda trigger. For deploying non-serverless apps to AWS, use deploy-on-aws plugin instead.

Builds, configures, debugs, and optimizes AWS observability with CloudWatch (Log Insights, Metrics, Alarms, Dashboards, EMF), X-Ray, CloudTrail, and ADOT (AWS Distro for OpenTelemetry), AND enables/onboards services to Application Signals using ADOT auto-instrumentation SDKs. Covers Log Insights queries, alarms (metric, composite, anomaly), dashboards, custom metrics/EMF, X-Ray tracing and sampling, ADOT collector config, CloudTrail auditing, and end-to-end Application Signals enablement via ADOT SDKs (CloudWatch Observability EKS add-on, CloudWatch Agent IAM, OTLP endpoints, ServiceEvents, Dynamic Instrumentation) on EC2, ECS, EKS, and Lambda in Python, Node.js, Java, and .NET. Applies to CloudWatch, alarms, dashboards, EMF, X-Ray, traces, CloudTrail, ADOT, monitoring, synthetics/canaries, OR enabling/onboarding/instrumenting a service for Application Signals using ADOT, ServiceEvents, auto-instrumentation, or making a service show up in Application Signals. Not for app logging or security threat detection.