> browse/registry

> aws-ecs

Run containerized applications with Amazon ECS. Define tasks and services, deploy on Fargate for serverless containers or EC2 for full control. Configure load balancing, auto-scaling, and service discovery for production workloads.

> aws-rds

Manage Amazon RDS for fully managed relational databases. Provision MySQL, PostgreSQL, and Aurora instances with automated backups and patching. Configure read replicas for scaling, snapshots for recovery, and Aurora Serverless for variable workloads.

> aws-ses

Send transactional and marketing emails with Amazon SES. Verify domains and identities, create reusable email templates, configure receipt rules for incoming mail, and handle bounces and complaints with SNS notifications.

> aws-sns

Use Amazon SNS for pub/sub messaging and notifications. Create topics and manage subscriptions across protocols (SQS, Lambda, HTTP, email, SMS). Configure message filtering, mobile push notifications, and fan-out architectures.

> aws-sqs

Work with Amazon SQS for reliable message queuing. Create standard and FIFO queues, configure dead-letter queues for failed messages, send and receive messages in batches, and build decoupled event-driven architectures.

> eventbridge

You are an expert in Amazon EventBridge, the serverless event bus for building event-driven architectures. You help developers route events between AWS services, SaaS applications, and custom microservices using event rules, patterns, transformations, dead-letter queues, and scheduling — decoupling producers from consumers with content-based routing that scales automatically.

> nitropack

You are an expert in Nitro (NitroJS), the universal server engine powering Nuxt, Analog, and SolidStart. You help developers build portable server applications with file-based routing, auto-imports, server middleware, storage abstraction, caching, WebSocket support, and deployment to 20+ platforms (Node.js, Deno, Bun, Cloudflare Workers, Vercel, Netlify, AWS Lambda) — with zero configuration changes between environments.

> porter

Expert guidance for Porter, the platform that provides a Heroku-like experience on your own AWS, GCP, or Azure account. Helps developers deploy applications on managed Kubernetes clusters provisioned in their own cloud accounts, with the simplicity of `git push` deployment and the control of owning your infrastructure.

> powertools-lambda

You are an expert in AWS Lambda Powertools, the developer toolkit for implementing serverless best practices. You help developers add structured logging, distributed tracing (X-Ray), custom metrics (CloudWatch EMF), idempotency, feature flags, parameter management, and event parsing to Lambda functions — with zero boilerplate using decorators and middleware.

> pulumi

Assists with defining and managing cloud infrastructure using Pulumi with TypeScript, Python, Go, or C#. Use when provisioning AWS, GCP, Azure, or Kubernetes resources with real programming languages instead of HCL. Trigger words: pulumi, infrastructure as code, iac, pulumi up, pulumi stack, cloud infrastructure, component resource.

> react-email

You are an expert in React Email, the library for building responsive HTML emails using React components. You help developers create beautiful, cross-client-compatible email templates with type-safe components, live preview, and integration with email providers (Resend, SendGrid, Postmark, AWS SES) — replacing fragile HTML table layouts with a modern component-based workflow.

> s3-storage

Manages S3-compatible object storage (AWS S3, MinIO, Cloudflare R2, DigitalOcean Spaces, Backblaze B2, Wasabi, Supabase Storage). Use when the user wants to create buckets, upload/download files, set up lifecycle policies, configure CORS, manage presigned URLs, implement multipart uploads, set up replication, handle versioning, configure access policies, or build file management features on top of S3-compatible APIs. Trigger words: s3, minio, r2, object storage, bucket, presigned url, multipart

> sqs

You are an expert in Amazon SQS (Simple Queue Service), the fully managed message queuing service. You help developers build decoupled, event-driven architectures using standard queues (at-least-once, best-effort ordering) and FIFO queues (exactly-once, ordered), dead-letter queues for failed messages, and Lambda triggers for serverless processing — scaling from zero to millions of messages per second.

> sst-ion

You are an expert in SST (Ion), the framework for building full-stack serverless applications on AWS. You help developers deploy Next.js, Remix, Astro, and API services with infrastructure-as-code defined in TypeScript, automatic IAM permissions, live Lambda debugging, secrets management, and zero-config deployments — replacing CDK/Terraform complexity with a developer-friendly abstraction over AWS services.

> sst

Assists with building and deploying full-stack serverless applications on AWS using SST. Use when defining Lambda functions, API Gateway routes, DynamoDB tables, S3 buckets, or deploying Next.js/Remix/Astro with SSR on AWS. Trigger words: sst, serverless stack, sst dev, sst deploy, aws lambda, sst ion, resource linking.

> terragrunt

You are an expert in Terragrunt, the thin wrapper for Terraform and OpenTofu that provides extra tools for keeping configurations DRY, managing remote state, and orchestrating multi-module deployments. You help platform teams manage large-scale infrastructure across multiple environments and AWS accounts using Terragrunt's hierarchical configuration, dependency management, and before/after hooks.

> upstash

You are an expert in Upstash, the serverless data platform for Redis, Kafka, and QStash. You help developers add caching, rate limiting, session storage, message queuing, and scheduled jobs to serverless and edge applications — with HTTP-based APIs that work on Vercel Edge, Cloudflare Workers, and AWS Lambda without persistent connections.

> aws-lambda

You are an expert in AWS Lambda, Amazon's serverless compute service. You help developers build event-driven applications using Lambda functions triggered by API Gateway, S3 events, SQS queues, DynamoDB streams, and scheduled events — with support for Node.js, Python, Go, Rust, Java, and container images, automatic scaling from zero to thousands of concurrent executions, and pay-per-invocation pricing.

> scientific-critical-thinking

Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review writing use peer-review.

> pufferlib

High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.