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…
Designs, reviews, and debugs DynamoDB data layers from design axioms — enumerates access patterns, chooses partition/sort keys and GSIs, decides single-table vs. multi-table, configures Streams, Global Tables, TTL, and zero-ETL integrations to OpenSearch/Redshift/SageMaker Lakehouse, and produces a defensible…
Guides general use of AWS messaging and streaming services. Covers Amazon SQS, Amazon SNS, Amazon EventBridge, Amazon MQ, Amazon Kinesis Data Streams, Amazon Data Firehose, Amazon Managed Service for Apache Flink, and Amazon Managed Streaming for Apache Kafka (MSK). Use when reasoning about messaging and streaming…
Use when authoring automated tests for .NET / C# code — unit tests, integration tests, mocking collaborators, and code coverage. Covers choosing a framework, structuring test projects, writing focused tests that map to requirements, and gating merges to keep trunk green. Triggers on .NET test, C# test, xUnit, NUnit…
Repo-model decision gate + multi-repo flow — run the gate at the start (single repo / frontend + backend split / other multi-repo). Load when the system spans more than one repository, to capture system-level requirements and design once, freeze the shared API + event contracts, split into per-repo slices, and fan…
Team-practices capture — run once at the start of a workflow (before Phase 1) to record the team's tech stack, testing posture (current vs. target), coding conventions, branching model, and compliance constraints into aidlc-docs/team-practices.md. Load when starting a new workflow, on first session, or when…
A companion steering file for systems whose code spans more than one repository — for example a separate frontend repo and backend repo for one app, or several service repos plus a shared contracts repo. It adds a repo-model decision gate at the start, and — when the system is multi-repo — a two-level flow that…
A companion steering file that adds a lightweight Practices Discovery step at the start of the workflow that captures the team's practices — discover → capture → the workflow honors them for the rest of the engagement. Kept deliberately light for a 3-day workshop. The captured file becomes steering the agent respects…
MCP server "awslabs.eks-mcp-server" as configured in aws-samples/sample-eks-operation-review-skill. Runs locally from the [email protected] Python package. Needs 1 environment variable to run.
MCP server "awslabs.aws-documentation-mcp-server" as configured in aws-samples/sample-eks-operation-review-skill. Runs locally from the [email protected] Python package. Needs 1 environment variable to run.
Run a structured EKS operational excellence assessment against a live cluster. Covers 10 areas — networking, autoscaling, observability, access & identity, add-ons, workload config, deployments, cluster lifecycle, IaC, operational processes — and produces a GREEN/AMBER/RED rated report with prioritized…
AGENTS.md instructions for aws-samples/sample-building-a-conversational-ai-agent-for-aws-waf-analysis-with-agentcore, covering agents.md — deployment playbook for ai agents, what you're deploying, before you start, the procedure and when something breaks.
Convert PDF files to Markdown format and create PDFs from Markdown. Use when the user asks to read, analyze, extract content from PDFs, or generate PDF documents.
Run a managed performance benchmark against a deployed Amazon SageMaker AI endpoint using SageMaker AI inference benchmarking (part of optimized GenAI inference recommendations; NVIDIA AIPerf under the hood). Measures TTFT, ITL, request-latency percentiles, and throughput. Use when the user asks to benchmark /…
Stage any supported open-weight Hugging Face model directly into Amazon S3 and deploy it to an Amazon SageMaker AI real-time endpoint with a compatible vLLM or SGLang Deep Learning Container. Use for model hosting, endpoint creation, direct-to-S3 transfer, smoke testing, and deployment cleanup.
Find an optimized serving configuration for a model with Amazon SageMaker AI inference recommendations, then deploy it and compare against a baseline benchmark. Covers both config search (best instance + serving knobs) and deep optimization (speculative decoding / EAGLE 3, quantization, kernel tuning). Use when the…
5 1mo agoA90 tokens
MIT-0
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: