#939 by GitHub stars
awslabs/agent-plugins
Agent Plugins for AWS equip AI coding agents with the skills to help you architect, deploy, and operate on AWS.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
plugins/amazon-location-service/skills/amazon-location-service/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/aws-amplify/skills/amplify-workflow/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/aws-serverless/skills/api-gateway/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/aws-serverless/skills/aws-lambda/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/aws-serverless/skills/aws-lambda-durable-functions/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/aws-serverless/skills/aws-lambda-managed-instances/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/aws-serverless/skills/aws-lambda-microvms/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/aws-serverless/skills/aws-serverless-deployment/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/aws-serverless/skills/aws-step-functions/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/aws-transform/skills/aws-transform/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/codebase-documentor-for-aws/skills/document-service/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/databases-on-aws/skills/dsql/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/deploy-on-aws/skills/aws-architecture-diagram/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/deploy-on-aws/skills/deploy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/deploy-on-aws/skills/elastic-beanstalk/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/dataset-evaluation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/dataset-transformation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/directory-management/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/finetuning/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/finetuning-technique/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/hyperpod-cluster-debugger/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/hyperpod-issue-report/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/hyperpod-nccl/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/hyperpod-node-debugger/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/hyperpod-performance-debugger/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/hyperpod-slurm-debugger/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/hyperpod-ssm/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/hyperpod-version-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/model-deployment/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/model-evaluation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/model-selection/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/planning/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/sdk-getting-started/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fbefb3764e67
No earlier version was observed for comparison.
plugins/sagemaker-ai/skills/use-case-specification/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
fbefb3764e67 → fbefb3764e67
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fbefb3764e67
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit fbefb3764e67558fe10ac834dd85db49734aa9b6
git clone --filter=blob:none --no-checkout https://github.com/awslabs/agent-plugins.git .hotskills/awslabs-agent-plugins && git -C .hotskills/awslabs-agent-plugins checkout --detach fbefb3764e67558fe10ac834dd85db49734aa9b6
# Copy each selected skill directory from .hotskills/awslabs-agent-plugins into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/awslabs/agent-plugins.git .hotskills/awslabs-agent-plugins && git -C .hotskills/awslabs-agent-plugins checkout --detach fbefb3764e67558fe10ac834dd85db49734aa9b6
# Copy each selected skill directory from .hotskills/awslabs-agent-plugins into .agents/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/awslabs/agent-plugins.git .hotskills/awslabs-agent-plugins && git -C .hotskills/awslabs-agent-plugins checkout --detach fbefb3764e67558fe10ac834dd85db49734aa9b6
# Copy each selected skill directory from .hotskills/awslabs-agent-plugins into .github/skills/<skill-name>/937GitHub stars
5stars in 7 days
34skills in this repository
1commit in 30 days
Heat
5.1- Star growth, last 7 daysAhead of 71% of tracked repositories
- Star growth, last 24 hoursAhead of 86% of tracked repositories
- Rank movement, last 7 daysAhead of 6% of tracked repositories
- Commits, last 30 daysAhead of 54% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- amazon-location-service
plugins/amazon-location-service/skills/amazon-location-service - amplify-workflow
plugins/aws-amplify/skills/amplify-workflow - api-gateway
plugins/aws-serverless/skills/api-gateway - aws-lambda
plugins/aws-serverless/skills/aws-lambda - aws-lambda-durable-functions
plugins/aws-serverless/skills/aws-lambda-durable-functions - aws-lambda-managed-instances
plugins/aws-serverless/skills/aws-lambda-managed-instances - aws-lambda-microvms
plugins/aws-serverless/skills/aws-lambda-microvms - aws-serverless-deployment
plugins/aws-serverless/skills/aws-serverless-deployment - aws-step-functions
plugins/aws-serverless/skills/aws-step-functions - aws-transform
plugins/aws-transform/skills/aws-transform - document-service
plugins/codebase-documentor-for-aws/skills/document-service - dsql
plugins/databases-on-aws/skills/dsql - aws-architecture-diagram
plugins/deploy-on-aws/skills/aws-architecture-diagram - deploy
plugins/deploy-on-aws/skills/deploy - elastic-beanstalk
plugins/deploy-on-aws/skills/elastic-beanstalk - dataset-evaluation
plugins/sagemaker-ai/skills/dataset-evaluation - dataset-transformation
plugins/sagemaker-ai/skills/dataset-transformation - directory-management
plugins/sagemaker-ai/skills/directory-management - finetuning
plugins/sagemaker-ai/skills/finetuning - finetuning-technique
plugins/sagemaker-ai/skills/finetuning-technique - hyperpod-cluster-debugger
plugins/sagemaker-ai/skills/hyperpod-cluster-debugger - hyperpod-issue-report
plugins/sagemaker-ai/skills/hyperpod-issue-report - hyperpod-nccl
plugins/sagemaker-ai/skills/hyperpod-nccl - hyperpod-node-debugger
plugins/sagemaker-ai/skills/hyperpod-node-debugger - hyperpod-performance-debugger
plugins/sagemaker-ai/skills/hyperpod-performance-debugger - hyperpod-slurm-debugger
plugins/sagemaker-ai/skills/hyperpod-slurm-debugger - hyperpod-ssm
plugins/sagemaker-ai/skills/hyperpod-ssm - hyperpod-version-checker
plugins/sagemaker-ai/skills/hyperpod-version-checker - model-deployment
plugins/sagemaker-ai/skills/model-deployment - model-evaluation
plugins/sagemaker-ai/skills/model-evaluation - model-selection
plugins/sagemaker-ai/skills/model-selection - planning
plugins/sagemaker-ai/skills/planning - sdk-getting-started
plugins/sagemaker-ai/skills/sdk-getting-started - use-case-specification
plugins/sagemaker-ai/skills/use-case-specification
How it works
amazon-location-service
When your agent uses it
Integrates Amazon Location Service APIs for AWS applications. Use this skill when users want to add maps (interactive MapLibre or static images); geocode addresses to coordinates or reverse geocode coordinates to addresses; calculate routes, travel times, or service areas; find places and businesses through text search, nearby search, or autocomplete suggestions; retrieve detailed place information including hours, contacts, and addresses; monitor geographical boundaries with geofences; or track device locations. Covers authentication, SDK integration, and all Amazon Location Service capabilities.
What it loads into context
Frontmatter
136 tokensAlways available to the agent
SKILL.md
3,355 tokensWhen the skill is activated
Reference documents
54,120 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use This Skill
- Amazon Location Service API Overview
- Common Mistakes
- Defaults
- API Selection Guidance
- LLM Context Files
- Key Guidance for Better Recommendations
- MCP Server Integration
- Additional Resources
- Reference Files
Files
../../../../.claude-plugin/marketplace.jsonasset6,703 bytes../../.claude-plugin/plugin.jsonasset625 bytesSKILL.mdcore15,914 bytesreferences/address-input.mddoc10,323 bytesreferences/address-verification.mddoc24,934 bytesreferences/calculate-routes.mddoc42,505 bytesreferences/device-tracking.mddoc13,690 bytesreferences/dynamic-map.mddoc12,860 bytesreferences/google-migration-android.mddoc26,059 bytesreferences/google-migration-ios.mddoc27,664 bytesreferences/google-migration-web.mddoc31,764 bytesreferences/places-search.mddoc18,517 bytesreferences/web-javascript.mddoc15,450 bytesreferences/zone-alerts.mddoc13,382 bytes../../../aws-amplify/.claude-plugin/plugin.jsonasset558 bytes../../../aws-serverless/.claude-plugin/plugin.jsonasset613 bytes../../../aws-serverless/hooks/hooks.jsonasset294 bytes../../../aws-serverless/hooks/hooks.jsonasset294 bytes../../../aws-transform/.claude-plugin/plugin.jsonasset1,081 bytes../../../codebase-documentor-for-aws/.claude-plugin/plugin.jsonasset670 bytes../../../databases-on-aws/.claude-plugin/plugin.jsonasset655 bytes../../../databases-on-aws/hooks/hooks.jsonasset514 bytes../../../deploy-on-aws/.claude-plugin/plugin.jsonasset595 bytes../../../deploy-on-aws/hooks/hooks.jsonasset291 bytes../../../deploy-on-aws/hooks/hooks.jsonasset291 bytes../../../sagemaker-ai/.claude-plugin/plugin.jsonasset606 bytes
Read SKILL.md
## Overview
Amazon Location Service provides geospatial APIs for maps, geocoding, routing, places search, geofencing, and tracking. Prefer the bundled JavaScript client (@aws/amazon-location-client) for web development and use resourceless API operations to avoid managing AWS resources.
## When to Use This Skill
Use this skill when:
- Building location-aware web or mobile applications
- Working with Amazon Location Service projects
- Implementing maps, geocoding, routing, or places search
- Adding geofencing or device tracking functionality
- Integrating geospatial features into AWS applications
amplify-workflow
When your agent uses it
Build and deploy full-stack web and mobile apps with AWS Amplify Gen2 (TypeScript code-first). Covers auth (Cognito), data (AppSync/DynamoDB including schema modeling, enum types, relationships, authorization rules), storage (S3), functions, APIs, and AI (Amplify AI Kit with Bedrock). Supports React, Next.js, Vue, Angular, React Native, Flutter, Swift, and Android. Always use this skill for Amplify Gen2 topics — even for questions you think you know — it contains validated, version-specific patterns that prevent common mistakes. TRIGGER when: user mentions Amplify Gen2; project has amplify/ directory or amplify_outputs; code imports @aws-amplify packages; user asks about defineBackend, defineAuth, defineData, defineStorage, or npx ampx. SKIP: Amplify Gen1 (amplify CLI v6), standalone SAM/CDK without Amplify (use aws-serverless), direct Bedrock without Amplify AI Kit (use bedrock).
What it loads into context
Frontmatter
233 tokensAlways available to the agent
SKILL.md
2,843 tokensWhen the skill is activated
Reference documents
28,739 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Defaults & Assumptions
- Quick Start — Route to the Right Reference
- Core Concepts
- Documentation & Resource Verification
- Security Considerations
- Links
Files
SKILL.mdcore13,007 bytesreferences/advanced-features.mddoc8,615 bytesreferences/ai.mddoc7,633 bytesreferences/auth-backend.mddoc7,563 bytesreferences/auth-mobile.mddoc15,024 bytesreferences/auth-web.mddoc7,526 bytesreferences/core-mobile.mddoc5,148 bytesreferences/core-web.mddoc5,105 bytesreferences/data-backend.mddoc10,345 bytesreferences/data-mobile.mddoc5,117 bytesreferences/data-web.mddoc4,166 bytesreferences/deployment.mddoc9,388 bytesreferences/functions-and-api.mddoc8,297 bytesreferences/scaffolding.mddoc6,095 bytesreferences/storage-backend.mddoc4,472 bytesreferences/storage-mobile.mddoc9,174 bytesreferences/storage-web.mddoc4,541 bytes
Read SKILL.md
# AWS Amplify Gen2
Build and deploy full-stack applications using AWS Amplify Gen2's TypeScript
code-first approach. This skill covers backend resource creation, frontend
integration across 8 frameworks, and deployment workflows.
## Prerequisites
- Node.js ^18.19.0 || ^20.6.0 || >=22 and npm
- AWS credentials configured (`aws sts get-caller-identity` succeeds)
- For sandbox: `npx ampx --version` returns a valid version
- For mobile: Platform-specific tooling (Xcode, Android Studio, Flutter SDK)
## Defaults & Assumptionsapi-gateway
When your agent uses it
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.
What it loads into context
Frontmatter
140 tokensAlways available to the agent
SKILL.md
3,578 tokensWhen the skill is activated
Reference documents
48,555 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How to Use This Skill
- Quick Decision: Which API Type?
- Instructions
- Response Format
- Troubleshooting Quick Reference
- Critical Pitfalls
- IaC Framework Selection
- Error Scenarios
- Service Limits Quick Reference
Files
SKILL.mdcore19,775 bytesreferences/architecture-patterns.mddoc19,433 bytesreferences/authentication.mddoc9,639 bytesreferences/custom-domains-routing.mddoc8,703 bytesreferences/deployment.mddoc15,296 bytesreferences/governance.mddoc10,084 bytesreferences/observability-analytics.mddoc4,318 bytesreferences/observability-logging.mddoc11,481 bytesreferences/observability-metrics-alarms.mddoc5,667 bytesreferences/performance-scaling.mddoc9,194 bytesreferences/pitfalls.mddoc2,086 bytesreferences/requirements-gathering.mddoc15,142 bytesreferences/sam-cloudformation.mddoc8,004 bytesreferences/sam-service-integrations.mddoc23,090 bytesreferences/security.mddoc18,672 bytesreferences/service-integrations.mddoc25,006 bytesreferences/service-limits.mddoc11,761 bytesreferences/troubleshooting.mddoc14,852 bytesreferences/websocket.mddoc7,620 bytes
Read SKILL.md
# Amazon API Gateway Development
Expert guidance for building, managing, governing, and operating APIs with Amazon API Gateway. Covers REST APIs (v1), HTTP APIs (v2), and WebSocket APIs.
## How to Use This Skill
When answering API Gateway questions:
1. Read the relevant reference file(s) before responding, do not rely solely on this summary
2. For tasks spanning multiple concerns (e.g., "private API with mTLS and custom domain"), read all relevant references
3. When the user needs IaC templates, consult `references/sam-cloudformation.md` or `references/sam-service-integrations.md` and provide complete, working SAM/CloudFormation YAML
4. Always mention relevant pitfalls and limits that affect the user's design
## Quick Decision: Which API Type?aws-lambda
When your agent uses it
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.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
2,462 tokensWhen the skill is activated
Reference documents
24,405 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Load Reference Files
- Best Practices
- Lambda Limits Quick Reference
- Troubleshooting Quick Reference
- Configuration
- Language selection
- IaC framework selection
- Resources
Files
SKILL.mdcore12,421 bytesSKILL.mdcore12,421 bytesreferences/event-driven-architecture.mddoc15,940 bytesreferences/event-sources.mddoc16,739 bytesreferences/getting-started.mddoc6,097 bytesreferences/observability.mddoc23,246 bytesreferences/optimization.mddoc14,893 bytesreferences/orchestration-and-workflows.mddoc6,376 bytesreferences/powertools.mddoc10,398 bytesreferences/troubleshooting.mddoc11,621 bytesreferences/web-app-deployment.mddoc10,852 bytes
Read SKILL.md
# AWS Lambda Serverless Development
Design, build, deploy, and debug serverless applications with AWS serverless services. This skill provides access to serverless development guidance through the AWS Serverless MCP Server, helping you to build production-ready serverless applications with best practices built-in.
Use SAM CLI for project initialization and deployment, Lambda Web Adapter for web applications, or Event Source Mappings for event-driven architectures. AWS handles infrastructure provisioning, scaling, and monitoring automatically.
**Key capabilities:**
- **SAM CLI Integration**: Initialize, build, deploy, and test serverless applications
- **Web Application Deployment**: Deploy full-stack applications with Lambda Web Adapter
- **Event Source Mappings**: Configure Lambda triggers for DynamoDB, Kinesis, SQS, Kafka
- **Lambda durable functions**: Resilient multi-step applications with checkpointing — see the [durable-functions skill](../aws-lambda-durable-functions/) for guidance
- **Lambda Managed Instances**: Run Lambda on dedicated EC2 instances with managed lifecycle — see the [managed-instances skill](../aws-lambda-managed-instances/) for evaluation, configuration, and migration guidance
- **Schema Management**: Type-safe EventBridge integration with schema registryaws-lambda-durable-functions
When your agent uses it
Build resilient, long-running, multi-step applications with AWS Lambda durable functions with automatic state persistence, retry logic, and orchestration for long-running executions. Covers the critical replay model, step operations, wait/callback patterns, error handling with saga pattern, testing with LocalDurableTestRunner. Triggers on phrases like: lambda durable functions, workflow orchestration, state machines, retry/checkpoint patterns, long-running stateful Lambda functions, saga pattern, human-in-the-loop callbacks, and reliable serverless applications.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
2,062 tokensWhen the skill is activated
Reference documents
26,137 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Onboarding
- When to Load Reference Files
- Quick Reference
- IAM Permissions
- Validation Guidelines
- Resources
Files
SKILL.mdcore9,200 bytesSKILL.mdcore9,200 bytesSKILL.mdcore9,200 bytesSKILL.mdcore9,200 bytesSKILL.mdcore9,200 bytesSKILL.mdcore9,200 bytesSKILL.mdcore9,200 bytesreferences/advanced-error-handling.mddoc4,991 bytesreferences/advanced-patterns.mddoc10,015 bytesreferences/concurrent-operations.mddoc8,629 bytesreferences/deployment-iac.mddoc14,663 bytesreferences/error-handling.mddoc11,155 bytesreferences/getting-started.mddoc11,357 bytesreferences/replay-model-rules.mddoc8,493 bytesreferences/step-operations.mddoc7,588 bytesreferences/testing-patterns.mddoc17,803 bytesreferences/troubleshooting-executions.mddoc8,349 bytesreferences/wait-operations.mddoc9,776 bytes
Read SKILL.md
# AWS Lambda durable functions
Build resilient multi-step applications and AI workflows that can execute for up to 1 year while maintaining reliable progress despite interruptions.
## Onboarding
### Step 1: Validate Prerequisites
Before using AWS Lambda durable functions, verify:
1. **AWS CLI** is installed (2.33.22 or higher) and configured:
```bash
aws --versionaws-lambda-managed-instances
When your agent uses it
Evaluate, configure, and migrate workloads to AWS Lambda Managed Instances (LMI). Triggers on: Lambda Managed Instances, LMI, capacity provider, multi-concurrency Lambda, dedicated instance Lambda, EC2-backed Lambda, cold start elimination, Graviton Lambda, instance type for Lambda, scheduled scaling for LMI, Lambda cost optimization with Reserved Instances or Savings Plans. Also trigger when users describe high-volume predictable workloads seeking cost savings, want to scale LMI capacity on a schedule, or compare Lambda vs EC2 for steady-state traffic. For standard Lambda without LMI, use the aws-lambda skill instead.
What it loads into context
Frontmatter
191 tokensAlways available to the agent
SKILL.md
3,383 tokensWhen the skill is activated
Reference documents
7,103 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Load Reference Files
- Quick Decision: Is LMI Right for This Workload?
- Instructions
- Best Practices
- Limits Quick Reference
- Troubleshooting Quick Reference
- Configuration
- Language Selection
- IaC Framework Selection
- Error Scenarios
- Resources
Scripts executed separately
scripts/setup-lmi.sh
Files
SKILL.mdcore15,991 bytesreferences/configuration-guide.mddoc5,629 bytesreferences/cost-comparison.mddoc947 bytesreferences/infrastructure-setup.mddoc9,392 bytesreferences/migration-patterns.mddoc3,841 bytesreferences/thread-safety.mddoc6,550 bytesreferences/troubleshooting.mddoc4,844 bytesscripts/setup-lmi.shruns3,012 bytes
Read SKILL.md
# AWS Lambda Managed Instances (LMI)
Run Lambda functions on current-generation EC2 instances in your account while AWS manages provisioning, patching, scaling, routing, and load balancing. Combines Lambda's developer experience with EC2's pricing and hardware options.
For standard Lambda development, see [aws-lambda skill](../aws-lambda/). For SAM/CDK deployment, see [aws-serverless-deployment skill](../aws-serverless-deployment/).
## When to Load Reference Files
- **Cost comparison**, **pricing analysis**, **Lambda vs LMI cost**, **Savings Plans**, or **Reserved Instances** -> see [references/cost-comparison.md](references/cost-comparison.md)
- **Instance types**, **memory sizing**, **vCPU ratios**, **scaling tuning**, **scheduled scaling**, or **capacity provider config** -> see [references/configuration-guide.md](references/configuration-guide.md)
- **Thread safety**, **concurrency model**, **code review checklist**, **Powertools compatibility**, or **multi-concurrency readiness** -> see [references/thread-safety.md](references/thread-safety.md)
- **Before/after code examples**, **runtime-specific migration** (Node.js, Python, Java, .NET), or **connection pooling** -> see [references/migration-patterns.md](references/migration-patterns.md)
- **IAM roles**, **VPC setup**, **CLI commands**, **SAM template**, **CDK example**, or **scheduled scaling setup (EventBridge Scheduler)** -> see [references/infrastructure-setup.md](references/infrastructure-setup.md) and [scripts/setup-lmi.sh](scripts/setup-lmi.sh)
- **Errors**, **throttling**, **debugging**, **stuck deployments**, **tuning configuration**, or **adjusting after deployment** -> see [references/troubleshooting.md](references/troubleshooting.md)aws-lambda-microvms
When your agent uses it
Build, run, debug, and operate applications on AWS Lambda MicroVMs — Firecracker-isolated, snapshot-resumable serverless compute environments that run inside a container with up to 8-hour lifetimes. Triggers on: Lambda MicroVMs, Firecracker isolation, snapshot-resumable compute, suspend/resume, sandboxed or untrusted code execution, AI/agent code-execution sandboxes, interactive code playgrounds and notebooks (Jupyter, REPLs), reinforcement-learning environments, multi-tenant CI executors and build runners, sessionful game or simulation servers, isolated security scanners, long-lived sessions, or port-listening servers (gRPC, WebSocket, custom TCP). For standard event-driven Lambda functions, use the aws-lambda skill instead.
What it loads into context
Frontmatter
229 tokensAlways available to the agent
SKILL.md
3,605 tokensWhen the skill is activated
Reference documents
12,084 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- Typical workflow
- Hook configuration
- Per-MicroVM size limits
- Additional capabilities
- Known constraints
- Reference index
- Conventions used in references
- Security considerations
Files
SKILL.mdcore16,403 bytesSKILL.mdcore16,403 bytesSKILL.mdcore16,403 bytesSKILL.mdcore16,403 bytesSKILL.mdcore16,403 bytesreferences/getting-started.mddoc8,923 bytesreferences/iam-and-security.mddoc6,729 bytesreferences/lifecycle-model.mddoc11,004 bytesreferences/networking.mddoc9,381 bytesreferences/snapshots-and-uniqueness.mddoc7,716 bytesreferences/troubleshooting.mddoc13,252 bytes
Read SKILL.md
# AWS Lambda MicroVMs
> The AWS MCP server is recommended for sandboxed execution and audit logging.
AWS Lambda MicroVMs are serverless compute environments that combine Firecracker VM isolation with container-like efficiency. Each MicroVM:
- Runs your application as a **container inside a Firecracker microVM** — you can reproduce the environment locally.
- Runs Amazon Linux 2023 as the base OS inside the MicroVM.
- Boots from a **memory + disk snapshot** captured at image build time, so application init is skipped on run.
- Has a dedicated, TLS-terminated HTTPS endpoint reachable with an auth token.
- Can be **suspended and resumed** with state preserved; lives up to 8 hours.
**Two-resource model:**
aws-serverless-deployment
When your agent uses it
AWS SAM and AWS CDK deployment for serverless applications. Triggers on phrases like: use SAM, SAM template, SAM init, SAM deploy, CDK serverless, CDK Lambda construct, NodejsFunction, PythonFunction, SAM and CDK together, serverless CI/CD pipeline. For general app deployment with service selection, use deploy-on-aws plugin instead.
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
1,257 tokensWhen the skill is activated
Reference documents
8,165 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Load Reference Files
- Best Practices
- Configuration
- IaC framework selection
- Error Scenarios
- Resources
Files
SKILL.mdcore5,364 bytesreferences/cdk-lambda-constructs.mddoc3,408 bytesreferences/cdk-project-setup.mddoc11,649 bytesreferences/cdk-serverless-patterns.mddoc4,547 bytesreferences/sam-cdk-coexistence.mddoc2,737 bytesreferences/sam-project-setup.mddoc13,354 bytes
Read SKILL.md
# AWS Serverless Deployment
Deploy serverless applications to AWS using SAM or CDK. This skill covers project scaffolding, IaC templates, CDK constructs and patterns, deployment workflows, CI/CD pipelines, and SAM/CDK coexistence.
For Lambda runtime behavior, event sources, orchestration, observability, and optimization, see the [aws-lambda skill](../aws-lambda/).
## When to Load Reference Files
Load the appropriate reference file based on what the user is working on:
- **SAM project setup**, **templates**, **deployment workflow**, **local testing**, or **container images** -> see [references/sam-project-setup.md](references/sam-project-setup.md)
- **CDK project setup**, **constructs**, **CDK testing**, or **CDK pipelines** -> see [references/cdk-project-setup.md](references/cdk-project-setup.md)
- **CDK Lambda constructs**, **NodejsFunction**, **PythonFunction**, or **CDK Function** -> see [references/cdk-lambda-constructs.md](references/cdk-lambda-constructs.md)
- **CDK serverless patterns**, **API Gateway CDK**, **Function URL CDK**, **EventBridge CDK**, **DynamoDB CDK**, or **SQS CDK** -> see [references/cdk-serverless-patterns.md](references/cdk-serverless-patterns.md)aws-step-functions
When your agent uses it
Build workflows with AWS Step Functions state machines using the JSONata query language. Covers Amazon States Language (ASL) structure, state types, variables, data transformation, error handling, AWS service integration, and migrating from the JSONPath to the JSONata query language.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
1,617 tokensWhen the skill is activated
Reference documents
16,921 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Load Reference Files
- Quick Reference
- Best Practices
- Troubleshooting
- Resources
Files
SKILL.mdcore7,620 bytesexamples/compensation-saga-pattern.asl.jsonasset3,580 bytesexamples/express-standard-handoff.asl.jsonasset2,272 bytesexamples/human-in-the-loop-with-timeout-escalation.asl.jsonasset3,437 bytesexamples/nested-map-parallel-structures.asl.jsonasset2,095 bytesexamples/polling-loop-wait-check-choice.asl.jsonasset2,025 bytesexamples/scatter-gather-with-partial-results.asl.jsonasset2,256 bytesexamples/semaphore-concurrency-lock.asl.jsonasset3,344 bytesreferences/architecture-patterns.mddoc3,854 bytesreferences/asl-state-types.mddoc12,685 bytesreferences/error-handling.mddoc7,055 bytesreferences/migrating-from-jsonpath-to-jsonata.mddoc13,608 bytesreferences/processing-state-inputs-and-outputs.mddoc11,506 bytesreferences/service-integrations.mddoc6,505 bytesreferences/transforming-data.mddoc6,359 bytesreferences/validation-and-testing.mddoc11,271 bytes
Read SKILL.md
# AWS Step Functions
## Overview
AWS Step Functions uses Amazon States Language (ASL) to define state machines as JSON. With AWS Step Functions, you can create workflows, also called State machines, to build distributed applications, automate processes, orchestrate microservices, and create data and machine learning pipelines.
This skill provides comprehensive guidance for writing state machines in ASL, covering:
- ASL structure and JSONata expression syntax
- Details on the eight available workflow states
- The `$states` reserved variable
- Workflow variables with `Assign`
- Error handling
- AWS Service integration patternsaws-transform
When your agent uses it
Migrate, modernize, and upgrade codebases to AWS. Run analysis on repos for tech debt, security vulnerabilities, and modernization opportunities. Transforms .NET Framework to .NET 8/10, mainframe COBOL to Java, VMware VMs to EC2, SQL Server to Aurora, and upgrades Java/Python/Node.js versions and AWS SDKs. Use when the user says "migrate .NET to AWS", "upgrade Java to 17/21", "modernize COBOL", "modernize mainframe", "move VMware to EC2", "convert SQL Server to Aurora", "upgrade Python version", "migrate AWS SDK", "transform this codebase", "analyze for issues", "find tech debt", "what tech debt", "security vulnerabilities", "CVEs", "what's wrong with my code", "assess my repos", "where do I start", "find what's outdated", "analyze my repos", "AWS Transform - continuous modernization", "continuous modernization" or "continuous-modernization". Don't use for infrastructure provisioning, CI/CD pipelines, or general coding tasks.
What it loads into context
Frontmatter
233 tokensAlways available to the agent
SKILL.md
7,359 tokensWhen the skill is activated
Reference documents
139,179 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- CRITICAL: Route Before Anything Else
- CRITICAL: Never Show Pricing or Timing Estimates
- Overview
- Prerequisites
- Mandatory workflow
- Resuming a prior session
- Determining user intent
- Discovery
- Scoping (GATE 1)
- Assessment
- Requirements (from assessment report)
- Approval (GATE 2)
- Task generation
- Execution
- Context persistence (.atx/context.json)
- Constraints
- Reference
Scripts executed separately
scripts/verify-traceability.py
Files
SKILL.mdcore36,268 bytesSKILL.mdcore36,268 bytesSKILL.mdcore36,268 bytesSKILL.mdcore36,268 bytesSKILL.mdcore36,268 bytesSKILL.mdcore36,268 bytesSKILL.mdcore36,268 bytesSKILL.mdcore36,268 bytesSKILL.mdcore36,268 bytesSKILL.mdcore36,268 bytesreferences/AWSTransformInfrastructureExecutorAccessEC2.jsonasset5,796 bytesreferences/AWSTransformSecurityAgentExecutorAccess.jsonasset1,829 bytesreferences/auth.mddoc4,120 bytesreferences/continuous-modernization-analysis.mddoc21,394 bytesreferences/continuous-modernization-aws-managed-execution.mddoc10,046 bytesreferences/continuous-modernization-batch-execution.mddoc11,383 bytesreferences/continuous-modernization-discovery.mddoc2,662 bytesreferences/continuous-modernization-ec2-execution.mddoc13,375 bytesreferences/continuous-modernization-findings.mddoc7,882 bytesreferences/continuous-modernization-guide.mddoc16,808 bytesreferences/continuous-modernization-remediation.mddoc15,162 bytesreferences/continuous-modernization-reporting.mddoc18,177 bytesreferences/continuous-modernization-schedule.mddoc22,071 bytesreferences/continuous-modernization-security-agent.mddoc8,715 bytesreferences/continuous-modernization-setup.mddoc5,030 bytesreferences/continuous-modernization-source.mddoc12,775 bytesreferences/continuous-modernization-status.mddoc1,999 bytesreferences/continuous-modernization-troubleshooting.mddoc10,518 bytesreferences/continuous-modernization.mddoc15,669 bytesreferences/custom-cli-reference.mddoc9,609 bytesreferences/custom-multi-transformation.mddoc10,593 bytesreferences/custom-remote-execution.mddoc23,941 bytesreferences/custom-repo-analysis.mddoc7,443 bytesreferences/custom-results-synthesis.mddoc1,610 bytesreferences/custom-single-transformation.mddoc15,701 bytesreferences/custom-troubleshooting.mddoc9,379 bytesreferences/custom.mddoc38,009 bytesreferences/dotnet-bulk.mddoc17,510 bytesreferences/dotnet.mddoc38,590 bytesreferences/mainframe-reimagine-analysis.mddoc23,278 bytesreferences/mainframe-reimagine-ddd.mddoc13,493 bytesreferences/mainframe-reimagine-modern-traceability.mddoc19,878 bytesreferences/mainframe-reimagine-specgen.mddoc21,941 bytesreferences/mainframe-reimagine-verify.mddoc9,937 bytesreferences/mainframe-reimagine.mddoc13,114 bytesreferences/mainframe.mddoc11,505 bytesreferences/sql.mddoc50,442 bytesreferences/tools.mddoc11,058 bytesreferences/vmware-containerization.mddoc7,027 bytesreferences/vmware-landing-zone.mddoc8,287 bytesreferences/vmware-network.mddoc32,250 bytesreferences/vmware-server.mddoc9,122 bytesreferences/vmware.mddoc14,843 bytesreferences/workflow.mddoc27,128 bytesscripts/verify-traceability.pyruns26,639 bytes
Read SKILL.md
# AWS Transform
## CRITICAL: Route Before Anything Else
**STOP. Before reading files, analyzing code, or starting any workflow, identify the workload first, then route.**
### Step A: Identify the workload
Look for an explicit workload signal in the user's request — a named technology (`.NET`, `VMware`, `SQL Server`/`Aurora`/`Oracle`/`MySQL`, `mainframe`/`COBOL`), workload-specific terminology (Hyper-V, EC2 rehost, stored procs, CICS, JCL), or file/project signals already in the conversation. If no signal is present, treat the request as **workload-unspecified**.
### Step B: Apply workload-specific routing
Workload-specific rules ALWAYS win over the keyword list in Step C. Do not let "analysis" or "tech debt" phrasing override these.
document-service
When your agent uses it
This skill should be used when the user asks to "analyze this codebase", "document this service", "generate technical docs", "I inherited this code", "help me understand this system", "create docs for this project", "what does this system look like", "onboard me to this codebase", "this codebase has no docs", "visualize the architecture from code", or any explicit request to produce structured documentation or architecture diagrams from an existing codebase. Specifically optimized for AWS workloads (CDK, CloudFormation, Terraform) with source-of-truth citations. Do NOT activate for code reviews, single-function explanations, generating new code, or general coding tasks.
What it loads into context
Frontmatter
153 tokensAlways available to the agent
SKILL.md
3,536 tokensWhen the skill is activated
Reference documents
9,622 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Principles
- Workflow
- Output Files
- Defaults
- Error Handling
- MCP Servers
- References
Files
SKILL.mdcore17,627 bytesSKILL.mdcore17,627 bytesSKILL.mdcore17,627 bytesSKILL.mdcore17,627 bytesSKILL.mdcore17,627 bytesSKILL.mdcore17,627 bytesSKILL.mdcore17,627 bytesSKILL.mdcore17,627 bytesSKILL.mdcore17,627 bytesSKILL.mdcore17,627 bytesSKILL.mdcore17,627 bytesreferences/business-context.mddoc2,736 bytesreferences/citation-format.mddoc3,798 bytesreferences/discovery-patterns.mddoc7,963 bytesreferences/error-scenarios.mddoc1,764 bytesreferences/exclusion-patterns.mddoc4,005 bytesreferences/framework-patterns.mddoc13,843 bytesreferences/recursive-analysis.mddoc4,002 bytesreferences/technical-doc-template.mddoc7,904 bytes
Read SKILL.md
# Document Service
Analyze codebases to produce structured technical documentation and architecture diagrams with source-of-truth citations. Every finding links back to the exact file and line it was derived from. Optimized for AWS workloads but works with any codebase.
## Core Principles
- **Explain WHY, not just WHAT.** The reader inherited this codebase and has zero context. Listing components is not enough — explain why the architecture is shaped this way. Search for code comments, TODOs, and commit messages that reveal design rationale. When no rationale exists, mark it `[RATIONALE UNKNOWN]`.
- **Trace end-to-end flows.** For every API endpoint or message handler, trace the complete request path from entry to response. Note every intermediate step, transformation, timeout, and failure point. This is the "if it breaks at 3am, where do I look?" analysis.
- **Deep-dive complex logic.** Identify the most complex or domain-specific code paths (ML pipelines, business rule engines, state machines, custom algorithms). Document HOW they work at the implementation level — the algorithm, key parameters, edge cases, and where production bugs will occur. Surface-level summaries of complex code provide no value over a naive AI prompt.
- **Surface implicit knowledge.** Look for hardcoded values, magic numbers, environment-dependent behavior, and undocumented assumptions. These are the tribal knowledge items that disappear when teams leave.
- **Every claim must be traceable.** Include `file:line` citations for every finding. See [citation-format.md](references/citation-format.md). Verify citations precisely — re-read the cited file and confirm the line number is within ±3 lines. Anchor with function/variable names.
- **Code is the source of truth.** Document what actually exists in code, not what READMEs or wikis claim. Flag every discrepancy between documentation and reality.
- **Mark unknowns and risks explicitly.** Use `[UNKNOWN]` for items not inferable from code, `[RISK]` for unhandled failure modes, `[INFERRED]` for educated guesses, `[RATIONALE UNKNOWN]` for unexplained architecture choices. Omitting markers undermines trust.
- **Verify quantitative claims.** List directory entries programmatically and use exact counts.dsql
When your agent uses it
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key constraints, OCC retry patterns, ORM migration (Django/EF Core/Hibernate/Rails/SQLAlchemy), DDL operations, query plan explainability, system diagnostics via CloudWatch AAS, SQL compatibility validation, and bulk data loading. Load before answering DSQL limit or error-code questions; it has limits docs omit. Triggers on phrases like: DSQL, Aurora DSQL, distributed SQL database, serverless PostgreSQL-compatible database, migrate to DSQL, DSQL query plan, DSQL EXPLAIN ANALYZE, DSQL ENUM, DSQL foreign key, DSQL OCC retry, DSQL multi-region, DSQL JSONB, DSQL GIN index, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader, DSQL slow, DSQL performance, DSQL wait events, DSQL AAS.
What it loads into context
Frontmatter
372 tokensAlways available to the agent
SKILL.md
5,561 tokensWhen the skill is activated
Reference documents
89,584 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Reference Files
- Choosing How to Connect: MCP vs CLI/psql
- MCP Tools Available
- CLI Scripts Available
- Quick Start
- Performance Routing
- Common Workflows
- Error Scenarios
- Additional Resources
Scripts executed separately
../../scripts/psql-connect.shmcp/tools/safe_query.py
Files
../../scripts/README.mddoc5,400 bytes../../scripts/psql-connect.shruns6,009 bytesSKILL.mdcore28,554 bytesSKILL.mdcore28,554 bytesSKILL.mdcore28,554 bytesSKILL.mdcore28,554 bytesmcp/mcp-setup.mddoc6,852 bytesmcp/mcp-tools.mddoc2,020 bytesmcp/platforms/claude-code.mddoc3,701 bytesmcp/platforms/codex.mddoc1,667 bytesmcp/platforms/gemini.mddoc2,116 bytesmcp/platforms/kiro.mddoc2,888 bytesmcp/tools/database-tools.mddoc4,727 bytesmcp/tools/documentation-tools.mddoc1,317 bytesmcp/tools/input-validation.mddoc3,429 bytesmcp/tools/safe_query.pyruns10,654 bytesmcp/tools/workflow-patterns.mddoc3,214 bytesreferences/access-control.mddoc5,142 bytesreferences/auth/authentication-guide.mddoc4,685 bytesreferences/auth/connectivity-tools.mddoc8,958 bytesreferences/auth/scaling-guide.mddoc4,033 bytesreferences/data-loading.mddoc6,146 bytesreferences/ddl-migrations/batched-migration.mddoc2,530 bytesreferences/ddl-migrations/column-operations.mddoc5,371 bytesreferences/ddl-migrations/constraint-operations.mddoc6,847 bytesreferences/ddl-migrations/overview.mddoc4,941 bytesreferences/development-guide.mddoc9,794 bytesreferences/dsql-examples.mddoc1,565 bytesreferences/dsql-lint.mddoc11,049 bytesreferences/examples/connection.mddoc2,566 bytesreferences/examples/data-operations.mddoc3,013 bytesreferences/examples/migrations.mddoc1,620 bytesreferences/examples/patterns.mddoc5,634 bytesreferences/examples/schema.mddoc1,633 bytesreferences/foreign-keys.mddoc6,106 bytesreferences/language.mddoc8,837 bytesreferences/limits-and-error-codes.mddoc19,681 bytesreferences/mysql-migrations/ddl-auto-increment.mddoc4,375 bytesreferences/mysql-migrations/ddl-batching.mddoc1,052 bytesreferences/mysql-migrations/ddl-column-changes.mddoc1,313 bytesreferences/mysql-migrations/ddl-constraints.mddoc782 bytesreferences/mysql-migrations/ddl-operations.mddoc1,502 bytesreferences/mysql-migrations/ddl-structural.mddoc3,773 bytesreferences/mysql-migrations/ddl-type-alternatives.mddoc4,587 bytesreferences/mysql-migrations/full-example.mddoc7,518 bytesreferences/mysql-migrations/type-mapping.mddoc14,692 bytesreferences/occ-retry-patterns.mddoc9,783 bytesreferences/onboarding.mddoc14,100 bytesreferences/orm-guides/overview.mddoc11,147 bytesreferences/pg-migrations/index-conversion.mddoc16,056 bytesreferences/pg-migrations/multi-region.mddoc3,004 bytesreferences/pg-migrations/schema-objects.mddoc15,379 bytesreferences/pg-migrations/type-mapping.mddoc5,442 bytesreferences/query-plan/catalog-queries.mddoc8,180 bytesreferences/query-plan/guc-experiments.mddoc7,712 bytesreferences/query-plan/plan-interpretation.mddoc15,390 bytesreferences/query-plan/query-rewrites-dsql-specific.mddoc900 bytesreferences/query-plan/query-rewrites-generic.mddoc1,923 bytesreferences/query-plan/query-rewrites/cte-late-materialization.mddoc1,464 bytesreferences/query-plan/query-rewrites/flatten-union-all.mddoc946 bytesreferences/query-plan/query-rewrites/left-join-to-inner.mddoc794 bytesreferences/query-plan/query-rewrites/not-in-to-not-exists.mddoc1,476 bytesreferences/query-plan/query-rewrites/or-to-in.mddoc889 bytesreferences/query-plan/query-rewrites/propagate-filter.mddoc1,024 bytesreferences/query-plan/query-rewrites/push-computation-to-constant.mddoc1,027 bytesreferences/query-plan/query-rewrites/push-group-by-into-subquery.mddoc1,625 bytesreferences/query-plan/query-rewrites/reltuples-estimate.mddoc1,188 bytesreferences/query-plan/query-rewrites/split-large-joins.mddoc2,217 bytesreferences/query-plan/query-rewrites/subquery-unnesting-correlated.mddoc1,663 bytesreferences/query-plan/query-rewrites/subquery-unnesting-scalar.mddoc1,469 bytesreferences/query-plan/query-rewrites/subquery-unnesting-uncorrelated.mddoc1,403 bytesreferences/query-plan/report-format.mddoc11,118 bytesreferences/query-plan/workflow.mddoc9,627 bytesreferences/system-diagnostics/promql-patterns.mddoc8,849 bytesreferences/system-diagnostics/wait-events.mddoc13,981 bytesreferences/system-diagnostics/workflow.mddoc19,844 bytesreferences/troubleshooting.mddoc11,982 bytes
Read SKILL.md
# Amazon Aurora DSQL Skill
Aurora DSQL is a serverless, PostgreSQL-compatible distributed SQL database. This skill covers direct query execution via MCP tools, schema management, migrations, multi-tenant isolation, IAM auth, and bulk data loading via `aurora-dsql-loader`.
---
## Reference Files
Load these files as needed for detailed guidance:
### Core:
| Reference | When to Load | Contains |
| ----------------------------------------------------------------- | --------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- |aws-architecture-diagram
When your agent uses it
Generate validated AWS architecture diagrams as draw.io XML using official AWS4 icon libraries. Use this skill whenever the user wants to create, generate, or design AWS architecture diagrams, cloud infrastructure diagrams, or system design visuals. Also triggers for requests to visualize existing infrastructure from CloudFormation, CDK, or Terraform code. Supports two modes: analyze an existing codebase to auto-generate diagrams, or brainstorm interactively from scratch. Exports .drawio files with optional PNG/SVG/PDF export via draw.io desktop CLI.
What it loads into context
Frontmatter
154 tokensAlways available to the agent
SKILL.md
3,724 tokensWhen the skill is activated
Reference documents
20,343 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Defaults
- Error Handling
- Style Rules
- Diagram Types
- XML Generation Rules
- Layout Guidelines
- File Naming
- Output
- CRITICAL: XML Well-Formedness
- Important Rules
- Reference Priority
Files
SKILL.mdcore15,283 bytesSKILL.mdcore15,283 bytesSKILL.mdcore15,283 bytesSKILL.mdcore15,283 bytesreferences/aws4-shapes-resources.mddoc14,856 bytesreferences/aws4-shapes-services.mddoc9,097 bytesreferences/cli-export.mddoc1,960 bytesreferences/diagram-templates-advanced.mddoc1,491 bytesreferences/diagram-templates-basic.mddoc2,568 bytesreferences/example-agentcore.drawioasset28,796 bytesreferences/example-complex-platform.drawioasset46,204 bytesreferences/example-event-driven.drawioasset43,980 bytesreferences/example-microservices.drawioasset47,561 bytesreferences/example-multi-region-active-active.drawioasset30,537 bytesreferences/example-saas-backend.drawioasset54,637 bytesreferences/example-sketch.drawioasset33,456 bytesreferences/general-icons.mddoc5,184 bytesreferences/group-styles.mddoc6,728 bytesreferences/layout-guidelines.mddoc6,412 bytesreferences/post-processing.mddoc982 bytesreferences/style-guide.mddoc6,339 bytesreferences/xml-rules.mddoc5,243 bytesreferences/xml-templates-examples.mddoc2,890 bytesreferences/xml-templates-structure.mddoc6,544 bytes
Read SKILL.md
You are an AWS architecture diagram generator that produces draw.io XML files with official AWS4 icons. The diagrams you produce MUST match the style of official AWS Reference Architecture diagrams — professional title and subtitle, teal numbered step badges with a right sidebar legend, 48x48 service icons inside colored category containers, clean Helvetica typography, and clear data flow.
## Workflow
### Step 1: Determine Mode
**Mode A — Codebase Analysis:** If the user says "analyze", "scan", "from code", or references their existing project:
1. Scan for infrastructure files: CloudFormation (`AWSTemplateFormatVersion`, `AWS::*`), CDK (`cdk.json`, construct definitions), Terraform (`resource "aws_*"`)
2. Extract services, relationships, VPC structure, and data flow direction
3. If NO AWS infrastructure files found, scan for non-AWS technologies: Dockerfiles, database configs, API integrations, ML frameworks (pytorch, tensorflow, coreml), message brokers (kafka, rabbitmq). Map discovered technologies using `references/general-icons.md`
4. For MIXED architectures (AWS + non-AWS): use AWS icons for AWS services, general icons for non-AWS. Same layout rules apply.
5. Confirm discovered architecture with user before generating
6. Ask which diagram type best represents the architecturedeploy
When your agent uses it
Deploy applications to AWS. Triggers on phrases like: deploy to AWS, host on AWS, run this on AWS, AWS architecture, estimate AWS cost, generate infrastructure. Analyzes any codebase and deploys to optimal AWS services.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
592 tokensWhen the skill is activated
Reference documents
7,515 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Philosophy
- Workflow
- Defaults
- MCP Servers
- Principles
- References
Files
SKILL.mdcore2,659 bytesreferences/cost-estimation.mddoc6,933 bytesreferences/defaults.mddoc6,432 bytesreferences/security.mddoc9,631 bytes../elastic-beanstalk/SKILL.mddoc12,301 bytes
Read SKILL.md
# Deploy on AWS
Take any application and deploy it to AWS with minimal user decisions.
## Philosophy
**Minimize cognitive burden.** User has code, wants it on AWS. Pick the most
straightforward services. Don't ask questions with obvious answers.
## Workflow
1. **Analyze** - Scan codebase for framework, database, dependencies
2. **Recommend** - Select AWS services, concisely explain rationale
3. **Estimate** - Show monthly cost before proceedingelastic-beanstalk
When your agent uses it
Deploy to AWS Elastic Beanstalk, in either Beanstalk Standard mode (EC2) or Beanstalk Cluster mode (managed EKS). Triggers on: elastic beanstalk, EB, beanstalk standard, beanstalk cluster, managed EC2 platform, web app with managed patching, worker on EC2, Heroku alternative, don't want to manage servers or container orchestration, migrate from Heroku, managed operational lifecycle, containerised app without operating Kubernetes, several services sharing a managed cluster, managed EKS without kubectl. Covers web and worker applications on EC2, and containerised single- and multi-service applications on managed EKS.
What it loads into context
Frontmatter
145 tokensAlways available to the agent
SKILL.md
2,558 tokensWhen the skill is activated
Reference documents
12,321 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Key Distinction
- Choose the Mode
- Workflow (Standard)
- Defaults
- Environment Types
- IaC Generation
- Security
- Cost
- References
Files
../deploy/references/security.mddoc9,631 bytesSKILL.mdcore12,301 bytesSKILL.mdcore12,301 bytesSKILL.mdcore12,301 bytesSKILL.mdcore12,301 bytesreferences/cluster-mode.mddoc40,793 bytesreferences/configuration.mddoc5,683 bytesreferences/platforms.mddoc3,518 bytes
Read SKILL.md
# Elastic Beanstalk
Deploy applications to production on AWS with full lifecycle management. Elastic
Beanstalk is an application management service: the user provides application
code or a container image, AWS manages everything underneath (deployment,
scaling, patching, monitoring, health response).
There are two modes, and the choice determines every setting that follows.
**Standard** runs the application on Amazon EC2; **Cluster** runs a container on
a managed Amazon EKS Auto Mode cluster. See [Choose the Mode](#choose-the-mode).
## When to Use
Elastic Beanstalk is the right choice when:dataset-evaluation
When your agent uses it
Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR). Use when the user says "is my dataset okay", "evaluate my data", "check my training data", "I have my own data", or before starting any fine-tuning job. Detects file format, checks schema compliance against the selected model and technique, and reports whether the data is ready for training or evaluation.
What it loads into context
Frontmatter
109 tokensAlways available to the agent
SKILL.md
1,065 tokensWhen the skill is activated
Reference documents
2,186 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Workflow
- Messages to the User
- Script Details
- References
Scripts executed separately
scripts/format_detector.py
Files
SKILL.mdcore5,043 bytesSKILL.mdcore5,043 bytesreferences/custom-scorer-evaluation-dataset-formats.mddoc4,192 bytesreferences/strategy_data_requirements.mddoc4,949 bytesscripts/format_detector.pyruns25,612 bytes
Read SKILL.md
# Workflow Instruction
Follow the workflow shown below. Locate the dataset, check the file type, and resolve any issues with missing files or wrong file types. Determine the fine-tuning model and fine-tuning strategy. Run the appropriate validation based on the model family. Summarize the results: is the dataset ready for fine-tuning?
## Prerequisites
- The SDK environment has been verified (SDK version, region, execution role). If not done, activate the `sdk-getting-started` skill first.
---
## Workflow
1. **Locate Dataset**:
- The full path may be a local file path, or an S3 URIdataset-transformation
When your agent uses it
Generates code that transforms datasets between ML schemas for model training or evaluation. Use when the user says "transform", "convert", "reformat", "change the format", or when a dataset's schema needs to change to match the target format — always use this skill for format changes rather than writing inline transformation code. Supports OpenAI chat, SageMaker SFT/DPO/RLVR/RLAIF, HuggingFace preference, Bedrock Nova, VERL, and custom JSONL formats from local files or S3.
What it loads into context
Frontmatter
125 tokensAlways available to the agent
SKILL.md
3,090 tokensWhen the skill is activated
Reference documents
2,720 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Prerequisites
- Principles
- Known Dataset Formats Reference
- Workflow
Scripts executed separately
code_templates/transformation.pyscripts/transformation_tools.py
Files
SKILL.mdcore14,161 bytesSKILL.mdcore14,161 bytesSKILL.mdcore14,161 bytesSKILL.mdcore14,161 bytesSKILL.mdcore14,161 bytesSKILL.mdcore14,161 bytesSKILL.mdcore14,161 bytesSKILL.mdcore14,161 bytesSKILL.mdcore14,161 bytescode_templates/transformation.pyruns1,536 bytesreferences/code_output_guide.mddoc2,902 bytesreferences/dataset_transformation_code.mddoc5,302 bytesreferences/sagemaker_dataset_formats.mddoc2,945 bytesscripts/transformation_tools.pyruns4,901 bytes
Read SKILL.md
# Dataset Transformation Agent
Transforms a data set provided by the user into their desired format.
## When to Use
- User needs to generate code for transforming datasets for SageMaker model training or model evaluation.
- A dataset requires processing, cleaning, or formatting before training or evaluation.
- Workflow requires a formal review and approval cycle before execution.
## Prerequisites
- The SDK environment has been verified (SDK version, region, execution role). If not done, activate the `sdk-getting-started` skill first.
directory-management
When your agent uses it
Manages project directory setup and artifact organization. Use when starting a new project, resuming an existing one, or when a PLAN.md needs to be associated with a project directory. Creates the project folder structure (specs/, scripts/, notebooks/, manifests/, agent_memory/) and resolves project naming.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
379 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Project Setup
- Directory Structure
Files
SKILL.mdcore1,763 bytes
Read SKILL.md
# Directory Management
## Project Setup
Before any work begins, resolve the project name:
1. If the project name is already known from conversation context, use it.
2. Otherwise, scan for existing `*/PLAN.md` files in the current directory. If found, ask the user if they are resuming an existing project and load that `PLAN.md` into context.
3. If no existing projects are found, recommend a ≤64-char lowercase slug based on what you know from the conversation (only `[a-z0-9-]`), or ask directly if there isn't enough context. Present the recommended name and wait for user confirmation.
Once project name is resolved:
1. Create and/or use the `<experiment-name>/` directory using the confirmed name for storing all the artifacts
finetuning
When your agent uses it
Generates code that fine-tunes a base model using SageMaker serverless training jobs. Use when the user says "start training", "fine-tune my model", "I'm ready to train", or when the plan reaches the finetuning step. Supports SFT, DPO, RLVR, and RLAIF trainers, including RLVR Lambda reward function and RLAIF custom prompt creation.
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
2,269 tokensWhen the skill is activated
Reference documents
7,564 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Code Generation Rules
- User Communication Rules
- 1. Code Generation Setup
- 2. RLVR Reward Function (for RLVR only, skip this section if technique is SFT or DPO)
- 3. RLAIF (for RLAIF only, skip this section if technique is not RLAIF)
- 4. EULA review and acceptance
- 5. Post-Generation
- 6. Continuous Customization
Scripts executed separately
code_templates/dpo.pycode_templates/rlaif_builtin.pycode_templates/rlaif_custom_prompt.pycode_templates/rlvr.pycode_templates/sft.pyscripts/mlflow_reference.pytemplates/nova_rlvr_reward_function_source_template.pytemplates/rlvr_reward_function_source_template.py
Files
SKILL.mdcore9,345 bytesSKILL.mdcore9,345 bytesSKILL.mdcore9,345 bytesSKILL.mdcore9,345 bytescode_templates/dpo.pyruns5,861 bytescode_templates/rlaif_builtin.pyruns5,671 bytescode_templates/rlaif_custom_prompt.pyruns6,166 bytescode_templates/rlvr.pyruns6,367 bytescode_templates/sft.pyruns5,587 bytesreferences/code_output_guide.mddoc3,246 bytesreferences/continuous_customization.mddoc8,694 bytesreferences/eula_links.mddoc8,009 bytesreferences/rlaif_guide.mddoc3,871 bytesreferences/rlvr_reward_function.mddoc10,255 bytesscripts/mlflow_reference.pyruns840 bytestemplates/nova_rlvr_reward_function_source_template.pyruns12,993 bytestemplates/rlvr_reward_function_source_template.pyruns9,451 bytes
Read SKILL.md
# Prerequisites
Before starting this workflow, verify:
1. A `use_case_spec.md` file exists
- If missing: Activate the `use-case-specification` skill first, then resume
- DON'T EVER offer to create a use case spec without activating the use-case-specification skill.
2. A fine-tuning technique (SFT, DPO, RLVR, RLAIF, or CPT/RFT (for Nova)) and base model have already been selected
- If missing: Activate the `model-selection` and/or `finetuning-technique` skills to collect what's missing, then resume
- Don't make recommendations on the spot. You MUST activate the appropriate skill.
3. A base model name available on SageMakerHub has been identified
- If missing: Activate the `model-selection` skill to get itfinetuning-technique
When your agent uses it
Selects a fine-tuning technique (SFT, DPO, RLVR, or RLAIF) for the user's use case and validates it against the selected model's available recipes. Use when the user has decided to finetune and needs to choose a technique, or when the technique needs to be validated against a model. Requires a base model to already be selected (via model-selection skill).
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
558 tokensWhen the skill is activated
Reference documents
508 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Prerequisites
- Workflow
- References
Scripts executed separately
scripts/get_recipes.py
Files
SKILL.mdcore2,419 bytesSKILL.mdcore2,419 bytesreferences/finetune_technique_selection_guide.mddoc2,393 bytesscripts/get_recipes.pyruns748 bytes
Read SKILL.md
# Finetuning Technique
Guides the user through selecting a fine-tuning technique based on their use case and validates compatibility with the selected model.
## When to Use
- User has decided to finetune and needs to choose a technique
- User wants to change their finetuning technique
- Technique needs to be validated against a selected model
## Prerequisites
- A base model has been selected (via model-selection skill). The model name and hub must be known.
- A `use_case_spec.md` file exists. If not, activate the use-case-specification skill to generate it first.hyperpod-cluster-debugger
When your agent uses it
Diagnose and remediate cluster-wide HyperPod (EKS or Slurm) problems — creation / deployment failures (CloudFormation, EFA health check, lifecycle scripts, capacity), EKS access, node replacement, CloudFormation nested-stack errors, post-maintenance rollback state, dangling nodes, autoscaler conflicts. Includes `--validate` pre-flight. Read-only.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
3,211 tokensWhen the skill is activated
Reference documents
12,294 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Step 1: Run diagnostics
- Step 2: Match signal → section
- A: EFA Health Checks
- B: Capacity & AZ
- C: Lifecycle Scripts
- D: EKS Access / kubectl
- E: Cluster Provisioning
- F: SSM Connectivity
- G: Node Replacement
- H: CloudFormation Errors
- I: Utilities
- J: AMI & Cluster Updates
- K: Dangling Nodes & Cleanup
- L: Autoscaler Compatibility
- Prerequisites
- Defaults
- Error handling
- Skill delegation
- Escalate to AWS Support
Scripts executed separately
scripts/diagnose-cluster.sh
Files
SKILL.mdcore14,486 bytesSKILL.mdcore14,486 bytesSKILL.mdcore14,486 bytesSKILL.mdcore14,486 bytesSKILL.mdcore14,486 bytesSKILL.mdcore14,486 bytesSKILL.mdcore14,486 bytesSKILL.mdcore14,486 bytesSKILL.mdcore14,486 bytesSKILL.mdcore14,486 bytesreferences/capacity-planning.mddoc4,653 bytesreferences/cloudformation-errors.mddoc5,896 bytesreferences/cluster-diagnostics-detail.mddoc23,900 bytesreferences/cluster-operations.mddoc11,785 bytesreferences/iam-permissions.mddoc1,200 bytesreferences/lifecycle-scripts.mddoc5,225 bytesscripts/diagnose-cluster.shruns70,693 bytes
Read SKILL.md
# HyperPod Cluster Debugger
**Operating policy.** Run read-only diagnostics yourself. Never run a command that changes cluster, node, or workload state — present each one as a **Suggested command (run this yourself)** block and wait for the customer to run it. Destructive order: **investigate → reboot → replace** (replace destroys root + secondary volumes; not supported on Slurm controller nodes).
**Before any state-changing CLI: ask if it's IaC-managed.** HyperPod clusters, SGs, EKS access entries, and IAM are usually provisioned via CloudFormation / CDK / Terraform. If yes, the fix belongs in IaC — running the CLI will drift and the next deploy reverts it. Use the CLI only when IaC is unavailable (locked out, predates IaC, mid-review).
`scripts/diagnose-cluster.sh` is read-only: it collects state via AWS APIs (and SSM for Slurm controller health) and prints each issue as `[FAIL] ... → references/<file>.md § <section>`.
| Reference | Open when |
| ------------------------------------------------------------------------- | ------------------------------------------------------------------- |
| [cluster-diagnostics-detail.md](references/cluster-diagnostics-detail.md) | Per-finding remediation runbook (§ A–L) |
| [cluster-operations.md](references/cluster-operations.md) | Operational deep-dives (EFA SG, EKS access, SSM, Slurm, filesystem) |
| [cloudformation-errors.md](references/cloudformation-errors.md) | § H needs the full per-resource CFN error catalog |
| [capacity-planning.md](references/capacity-planning.md) | § B or `--validate` flags capacity / subnet sizing |hyperpod-issue-report
When your agent uses it
Generate comprehensive issue reports from HyperPod clusters (EKS and Slurm) by collecting diagnostic logs and configurations for troubleshooting and AWS Support cases. Use when users need to collect diagnostics from HyperPod cluster nodes, generate issue reports for AWS Support, investigate node failures or performance problems, document cluster state, or create diagnostic snapshots. Triggers on requests involving issue reports, diagnostic collection, support case preparation, or cluster troubleshooting that requires gathering logs and system information from multiple nodes.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
864 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Workflow
- Troubleshooting
Scripts executed separately
references/collection-details.mdreferences/troubleshooting.mdscripts/hyperpod_issue_report.py
Files
SKILL.mdcore3,560 bytesSKILL.mdcore3,560 bytesSKILL.mdcore3,560 bytesSKILL.mdcore3,560 bytesSKILL.mdcore3,560 bytesSKILL.mdcore3,560 bytesSKILL.mdcore3,560 bytesSKILL.mdcore3,560 bytesreferences/collection-details.mdruns3,722 bytesreferences/troubleshooting.mdruns3,622 bytesscripts/hyperpod_issue_report.pyruns66,849 bytes
Read SKILL.md
# HyperPod Issue Report
Collect diagnostic logs from HyperPod cluster nodes via SSM, store results in S3. Supports both EKS and Slurm clusters with auto-detection. Uses the bundled `scripts/hyperpod_issue_report.py` for reliable parallel collection.
## Prerequisites
- AWS CLI configured with permissions: `sagemaker:DescribeCluster`, `sagemaker:ListClusterNodes`, `ssm:StartSession`, `s3:PutObject`, `s3:GetObject`, `eks:DescribeCluster`
- Python 3.8+ and [uv](https://docs.astral.sh/uv/) (see [uv installation docs](https://docs.astral.sh/uv/getting-started/installation/) for install options)
- SSM Agent running on target nodes; node IAM roles need `s3:GetObject`/`s3:PutObject` on the report bucket
- For EKS clusters: kubectl installed and configured (see Workflow step 2)
## Workflow
### 1. Gather Informationhyperpod-nccl
When your agent uses it
Diagnose NCCL failures and adjacent training-pod failures on HyperPod GPU clusters (EKS or Slurm) — training hangs, AllReduce / collective-op timeouts, EFA or libfabric errors, rendezvous failures, EFA TCP fallback, /dev/shm or memlock issues, NCCL version mismatch across pods, container OOM / exit-137 / OOMKilled, GPU OOM (CUDA out of memory), CrashLoopBackOff / Pending pods, MASTER_ADDR DNS, NetworkPolicy blocking. Not for single-node hardware faults (→ hyperpod-node-debugger § G) or cluster-creation EFA / SSM failures (→ hyperpod-cluster-debugger § A / § F).
What it loads into context
Frontmatter
165 tokensAlways available to the agent
SKILL.md
3,035 tokensWhen the skill is activated
Reference documents
36,059 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Step 1: Authenticate kubectl (EKS)
- Step 2: Run the diagnostic
- Remediation index
- Prerequisites
- Defaults
- Error handling
- IAM permissions
- Scale strategy
- Skill delegation
- Escalate to AWS Support
- References
Scripts executed separately
scripts/nccl-diagnose.sh
Files
SKILL.mdcore13,756 bytesSKILL.mdcore13,756 bytesSKILL.mdcore13,756 bytesSKILL.mdcore13,756 bytesSKILL.mdcore13,756 bytesSKILL.mdcore13,756 bytesSKILL.mdcore13,756 bytesSKILL.mdcore13,756 bytesSKILL.mdcore13,756 bytesSKILL.mdcore13,756 bytesSKILL.mdcore13,756 bytesSKILL.mdcore13,756 bytesSKILL.mdcore13,756 bytesSKILL.mdcore13,756 bytesSKILL.mdcore13,756 bytesSKILL.mdcore13,756 bytesSKILL.mdcore13,756 bytesSKILL.mdcore13,756 bytesreferences/debugging-guide.mddoc48,608 bytesreferences/error-patterns-quick-ref.mddoc10,271 bytesreferences/operations.mddoc18,436 bytesreferences/performance-testing.mddoc10,171 bytesscripts/nccl-diagnose.shruns121,399 bytes../hyperpod-node-debugger/references/node-diagnostics-detail.mddoc70,642 bytes
Read SKILL.md
# HyperPod NCCL Debugger
**Operating policy.** Run read-only diagnostics yourself. Never run a command that changes cluster, node, or workload state — present each one as a **Suggested command (run this yourself)** block and wait for the customer. Destructive order: **investigate → reboot → replace** (replace destroys root + secondary volumes; not supported on Slurm controller nodes). Never discard training state on speculation.
Diagnose NCCL failures on SageMaker HyperPod (EKS and Slurm). `scripts/nccl-diagnose.sh` reads state via AWS APIs, kubectl, and SSM, then prints each issue as `[FAIL] ... → references/<file>.md § <section>`. Read-only.
**Signal sourcing:** `list-cluster-events` carries infrastructure-level state only (lifecycle, bootstrap, EFA health check, capacity, replacement, reboot, AMI rollback). It does **not** carry NCCL timeouts, GPU XID/ECC, or per-pod training signals — those come from pod logs, CloudWatch training streams, on-node SSM probes, and NCCL env audit. "No events" on a training-time NCCL issue is expected, not a clean bill of health.
---
## Workflow
1. Collect cluster name, region, namespace/job (EKS), exact NCCL error string.
2. Run the diagnostic (always — the output drives everything else).hyperpod-node-debugger
When your agent uses it
Diagnose and remediate per-node issues on a HyperPod cluster (EKS or Slurm) — a specific node is unhealthy, unresponsive, stuck, or needs replacing. Covers on-node EFA, GPU / accelerator hardware (XID, ECC, NVLink, row-remap, DCGM), Slurm node down/drained, disk and memory pressure, per-node lifecycle-script failures, SSM agent, container runtime, kernel panics, pod networking. Read-only. Not for cluster-wide provisioning (→ hyperpod-cluster-debugger), NCCL (→ hyperpod-nccl), or MFU (→ hyperpod-mfu-debugger).
What it loads into context
Frontmatter
154 tokensAlways available to the agent
SKILL.md
4,861 tokensWhen the skill is activated
Reference documents
17,230 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Step 1: Triage
- Step 2: Match signal → section
- A: EFA / Security Group
- B: VPC / Routing
- C: Capacity / AZ
- D: Lifecycle Scripts
- E: Software Versions
- F: Hardware / Auto-Repair
- G: GPU / Accelerator
- H: Slurm Node Management
- I: Resource Exhaustion
- J: Configuration
- K: Node Access via SSM
- L: Log Collection
- M: Container Runtime
- N: Kernel & System
- O: CNI / Pod Networking
- Prerequisites
- Defaults
- Error handling
- IAM permissions
- Skill delegation
- Escalate to AWS Support
Scripts executed separately
scripts/check-efa-sg.shscripts/check-node-reachability.shscripts/check-vpc-config.shscripts/triage-cluster.sh
Files
SKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesSKILL.mdcore20,921 bytesreferences/node-diagnostics-detail.mddoc70,642 bytesreferences/node-issue-catalog.mddoc5,781 bytesscripts/check-efa-sg.shruns13,541 bytesscripts/check-node-reachability.shruns17,454 bytesscripts/check-vpc-config.shruns20,975 bytesscripts/triage-cluster.shruns58,987 bytes
Read SKILL.md
# HyperPod Node Debugger
**Operating policy.** Run read-only diagnostics yourself. Never run a command that changes cluster, node, or workload state — present each one as a **Suggested command (run this yourself)** block and wait for the customer. Destructive order: **investigate → reboot → replace** (replace destroys root + secondary volumes; not supported on Slurm controller nodes). Never discard training state, logs, or caches on speculation.
**IaC note (always include with mutation commands).** When you suggest any command that changes cluster, VPC, SG, subnet, or EKS configuration (e.g. `authorize-security-group-*`, `modify-vpc-attribute`, `update-cluster`, `kubectl label/cordon/drain`, `create namespace`, `set env daemonset`), ask the customer first whether the cluster / VPC / SG is managed by Infrastructure-as-Code (CloudFormation, CDK, Terraform, Pulumi). If yes, tell them: "Apply this change in your IaC source first, then deploy through the pipeline — running the command directly will drift from your template and the next stack update may overwrite it." If they need to fix the issue immediately and the IaC change will follow, flag the drift explicitly so they remember to reconcile.
Read-only triage. `scripts/triage-cluster.sh` (and helpers `check-efa-sg.sh`, `check-node-reachability.sh`, `check-vpc-config.sh`) read state and print each issue as `[FAIL] ... → references/node-diagnostics-detail.md § <section>`. Catalog of customer-ticket patterns: [references/node-issue-catalog.md](references/node-issue-catalog.md).
---
## Workflow
1. Collect cluster name, region, suspect instance ID, exact error string from logs.
2. Run `scripts/triage-cluster.sh` (add `--node <INSTANCE-ID>` to focus one node).hyperpod-performance-debugger
When your agent uses it
Diagnose performance issues on Amazon SageMaker HyperPod clusters — uneven NCCL bandwidth across nodes and poor filesystem throughput. Read-only. Surfaces host-side signals (Xid, ECC, NVLink, EFA reachability, FSx saturation) and routes to the appropriate sibling skill (hyperpod-node-debugger, hyperpod-nccl, hyperpod-version-checker, hyperpod-issue-report) for any remediation. Triggers on uneven NCCL across nodes, straggler node, FSx slow, checkpoint slow, dataloader slow, filesystem bottleneck, FSx throughput, cross-AZ latency, topology mismatch.
What it loads into context
Frontmatter
148 tokensAlways available to the agent
SKILL.md
3,618 tokensWhen the skill is activated
Reference documents
2,901 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope and delegation
- Operating policy
- Workflow
- Step 1: Run the snapshot
- Step 2: Match signal → section
- A: Uneven NCCL Performance
- B: Poor Filesystem Performance
- Continuous health coverage
- References
Scripts executed separately
scripts/perf-snapshot.sh
Files
SKILL.mdcore16,529 bytesSKILL.mdcore16,529 bytesSKILL.mdcore16,529 bytesSKILL.mdcore16,529 bytesSKILL.mdcore16,529 bytesSKILL.mdcore16,529 bytesSKILL.mdcore16,529 bytesSKILL.mdcore16,529 bytesSKILL.mdcore16,529 bytesSKILL.mdcore16,529 bytesSKILL.mdcore16,529 bytesSKILL.mdcore16,529 bytesSKILL.mdcore16,529 bytesSKILL.mdcore16,529 bytesSKILL.mdcore16,529 bytesSKILL.mdcore16,529 bytesSKILL.mdcore16,529 bytesreferences/perf-details.mddoc12,048 bytesscripts/perf-snapshot.shruns28,432 bytes
Read SKILL.md
# HyperPod Performance Debugger
1. **Uneven NCCL performance across nodes** — workload faster on some node sets than others, pairwise bandwidth variance, suspected straggler.
2. **Poor filesystem performance** — training stalled on data loading, checkpoint save/load dominating step time, FSx throughput saturated.
## Scope and delegation
Route findings outside the two in-scope scenarios to the owner skill below.
| Concern observed | Route to |
| ---------------------------------------------------------------------- | ------------------------------------------------------------ |
| GPU hardware fault, ECC, NVLink, Xid, DCGM diagnostics, drain/replace | `hyperpod-node-debugger` (§ F Hardware/Auto-Repair, § G GPU) |
| `Cannot allocate memory` at `os.fork()`, root volume exhausted | `hyperpod-node-debugger` (§ I Resource Exhaustion) |
| NCCL timeouts, hangs, AllReduce stalls, EFA TCP fallback, RDMA memlock | `hyperpod-nccl` |hyperpod-slurm-debugger
When your agent uses it
Diagnostic-only skill for Slurm scheduler and node-daemon issues on Amazon SageMaker HyperPod Slurm clusters. Scope mirrors the HyperPod troubleshooting guide. Invoke when the user reports a Slurm node stuck in down/drain, "Node unexpectedly rebooted" after auto-repair, slurmd not running, jobs stuck PENDING with REASON=Resources while sinfo shows idle nodes, jobs stuck COMPLETING after node replacement, GRES/GPU counts wrong, scontrol ping failing, slurmctld unresponsive, an Action:Reboot/Replace request that did not trigger HyperPod auto-recovery, or auto-resume not restarting a job. Also triggers on "drain before reboot", "diagnose a Slurm node", "investigate stuck jobs."
What it loads into context
Frontmatter
178 tokensAlways available to the agent
SKILL.md
2,962 tokensWhen the skill is activated
Reference documents
3,546 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to invoke
- When NOT to invoke
- Constraints
- Prerequisites
- Procedure
- Decision table
- Defaults
- Error handling
- A: Node Down
- B: Unexpected Reboot
- C: Controller State
- D: Action Reason Mismatch
- E: Auto-resume
- Escalation
Scripts executed separately
scripts/slurm-diagnose.sh
Files
SKILL.mdcore13,117 bytesSKILL.mdcore13,117 bytesSKILL.mdcore13,117 bytesSKILL.mdcore13,117 bytesSKILL.mdcore13,117 bytesSKILL.mdcore13,117 bytesSKILL.mdcore13,117 bytesSKILL.mdcore13,117 bytesSKILL.mdcore13,117 bytesSKILL.mdcore13,117 bytesSKILL.mdcore13,117 bytesSKILL.mdcore13,117 bytesSKILL.mdcore13,117 bytesSKILL.mdcore13,117 bytesSKILL.mdcore13,117 bytesSKILL.mdcore13,117 bytesreferences/slurm-details.mddoc13,600 bytesscripts/slurm-diagnose.shruns37,873 bytes
Read SKILL.md
# HyperPod Slurm Debugger
Diagnostic-only. Identify and classify Slurm scheduler and node-daemon issues on
HyperPod Slurm clusters. Do not run, recommend, or print any state-mutating command.
For remediation, link to the official AWS or Slurm documentation.
## When to invoke
Invoke when the user reports any of the symptoms in the [decision table](#decision-table).
## When NOT to invoke
- Cluster has `Orchestrator.Eks` — invoke `hyperpod-node-debugger` or `hyperpod-nccl`.
- Single-node hardware fault with healthy Slurm scheduler — invoke `hyperpod-node-debugger`.hyperpod-ssm
When your agent uses it
Remote command execution and file transfer on SageMaker HyperPod cluster nodes via AWS Systems Manager (SSM). This is the primary interface for accessing HyperPod nodes — direct SSH is not available. Use when any skill, workflow, or user request needs to execute commands on cluster nodes, upload files to nodes, read/download files from nodes, run diagnostics, install packages, or perform any operation requiring shell access to HyperPod instances. Other HyperPod skills depend on this skill for all node-level operations.
What it loads into context
Frontmatter
121 tokensAlways available to the agent
SKILL.md
1,209 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- SSM Target Format
- Scripts
- Running Commands Across Many Nodes
- Manual SSM Commands
- Common Diagnostic Commands
- Key Details
Scripts executed separately
references/troubleshooting.mdscripts/get-cluster-info.shscripts/list-nodes.shscripts/ssm-exec.sh
Files
SKILL.mdcore5,200 bytesSKILL.mdcore5,200 bytesSKILL.mdcore5,200 bytesSKILL.mdcore5,200 bytesSKILL.mdcore5,200 bytesSKILL.mdcore5,200 bytesreferences/troubleshooting.mdruns2,093 bytesscripts/get-cluster-info.shruns983 bytesscripts/list-nodes.shruns1,641 bytesscripts/ssm-exec.shruns4,496 bytes
Read SKILL.md
# HyperPod SSM Access
## Prerequisites
- **`aws` CLI v2**, authenticated for the target account/Region.
- **`session-manager-plugin`** — installed alongside the AWS CLI.
- **`jq`** — the scripts build JSON payloads with it.
- **`unbuffer`** (from the `expect` package) — wraps `aws ssm start-session` with a PTY so the session-manager-plugin flushes stdout instead of racing to close. Without it, calls intermittently return empty output with `Cannot perform start session: EOF` even when the command ran. Install with `sudo yum install expect`, `sudo apt install expect`, or `brew install expect`. `ssm-exec.sh` detects and uses it automatically; falls back with a warning if missing.
## SSM Target Format
Target: `sagemaker-cluster:<CLUSTER_ID>_<GROUP_NAME>-<INSTANCE_ID>`
- `CLUSTER_ID`: Last segment of cluster ARN (NOT the cluster name). Extract via `get-cluster-info.sh`.hyperpod-version-checker
When your agent uses it
Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia), Python, and PyTorch. Use when checking component versions, verifying CUDA/driver compatibility, detecting version mismatches across nodes, planning upgrades, documenting cluster configuration, or troubleshooting version-related issues on HyperPod. Triggers on requests about versions, compatibility, component checks, or upgrade planning for HyperPod clusters.
What it loads into context
Frontmatter
136 tokensAlways available to the agent
SKILL.md
871 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- What It Checks
- Multi-Node Comparison
- Compatibility Reference
Scripts executed separately
scripts/hyperpod_check_versions.sh
Files
SKILL.mdcore3,640 bytesSKILL.mdcore3,640 bytesSKILL.mdcore3,640 bytesSKILL.mdcore3,640 bytesSKILL.mdcore3,640 bytesSKILL.mdcore3,640 bytesSKILL.mdcore3,640 bytesscripts/hyperpod_check_versions.shruns20,787 bytes
Read SKILL.md
# HyperPod Version Checker
Upload to cluster nodes via `hyperpod-ssm` skill, then execute.
## Usage
```bash
# Text report to console + file
bash hyperpod_check_versions.sh
# JSON only to stdout (text report still saved to file) — best for piping/parsing
bash hyperpod_check_versions.sh --json
# Custom output filemodel-deployment
When your agent uses it
Generates code that deploys fine-tuned models from SageMaker Serverless Model Customization to SageMaker endpoints or Bedrock. Use when the user says "deploy my model", "create an endpoint", "make it available", or asks about deployment options. Identifies the correct deployment pathway (Nova vs OSS), generates deployment code, and handles endpoint configuration.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
1,331 tokensWhen the skill is activated
Reference documents
8,809 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope
- Prerequisites
- Principles
- Workflow
- Troubleshooting
Scripts executed separately
code_templates/deploy-nova-bedrock.pycode_templates/deploy-nova-sagemaker.pycode_templates/deploy-oss-bedrock.pycode_templates/deploy-oss-sagemaker.py
Files
SKILL.mdcore5,928 bytescode_templates/deploy-nova-bedrock.pyruns1,906 bytescode_templates/deploy-nova-sagemaker.pyruns1,779 bytescode_templates/deploy-oss-bedrock.pyruns3,956 bytescode_templates/deploy-oss-sagemaker.pyruns1,948 bytesreferences/code_output_guide.mddoc3,246 bytesreferences/deploy-nova-bedrock.mddoc4,074 bytesreferences/deploy-nova-sagemaker.mddoc5,142 bytesreferences/deploy-oss-bedrock.mddoc4,779 bytesreferences/deploy-oss-sagemaker.mddoc6,605 bytesreferences/model-licenses.mddoc11,803 bytes
Read SKILL.md
# Model Deployment
Identifies the correct deployment pathway based on model characteristics and generates deployment code.
## Scope
This skill supports deploying Nova and OSS models that were fine-tuned through **SageMaker Serverless Model Customization** only.
**Not supported:**
- Base models (not fine-tuned)
- Models fine-tuned through other processes
- Full Fine-Tuning (FFT) — only LoRA fine-tuned models are supported
model-evaluation
When your agent uses it
Generates python code that evaluates SageMaker models. Supports two evaluation types: LLM-as-Judge and Custom Scorer. Use when the user says "evaluate my model", "run a benchmark", "test model performance", "how did my model perform", "compare models", or other similar requests.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
1,186 tokensWhen the skill is activated
Reference documents
11,979 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Principles
- Scope
- Evaluation Types
- Workflow
Scripts executed separately
code_templates/custom_scorer_evaluator.pycode_templates/llmaaj_evaluator.pyscripts/nova_reward_function_source_template.pyscripts/reward_function_source_template.pyscripts/validate_custom_metrics.py
Files
SKILL.mdcore5,333 bytesSKILL.mdcore5,333 bytesSKILL.mdcore5,333 bytescode_templates/custom_scorer_evaluator.pyruns2,536 bytescode_templates/llmaaj_evaluator.pyruns2,500 bytesreferences/code_output_guide.mddoc3,346 bytesreferences/create-reward-function.mddoc3,062 bytesreferences/custom-lambda-scorer.mddoc4,472 bytesreferences/custom-scorer-evaluation.mddoc10,444 bytesreferences/evaluation-type-guide.mddoc8,156 bytesreferences/llmaaj-builtin-evaluation.mddoc5,086 bytesreferences/llmaaj-custom-evaluation.mddoc2,405 bytesreferences/llmaaj-evaluation.mddoc14,074 bytesreferences/supported-judge-models.mddoc2,522 bytesscripts/nova_reward_function_source_template.pyruns13,341 bytesscripts/reward_function_source_template.pyruns9,544 bytesscripts/validate_custom_metrics.pyruns3,694 bytes
Read SKILL.md
# Model Evaluation
Generate code that evaluates a SageMaker model.
## Prerequisites
- The SDK environment has been verified (SDK version, region, execution role). If not done, activate the `sdk-getting-started` skill first.
## Principles
1. **One thing at a time.** Each response advances exactly one decision. Never combine multiple questions in a single turn.
2. **Confirm before proceeding.** Wait for the user to agree before moving to the next step.
3. **Don't read files until you need them.** Only read reference files when you've reached the step that requires them.
4. **Don't ask what you already know.** If the answer is in conversation history, workflow_state.json, plan.md, or any file you've already read — use it. Confirm if unsure, but don't re-ask.model-selection
When your agent uses it
Selects a base model for the user's use case by querying SageMaker Hub. Use when the user asks which model to use, wants to select or change their base model, mentions a model name or family (e.g., "Llama", "Mistral", "Nova"), or wants to evaluate a base model — always activate even for known model names because the exact Hub model ID must be resolved. Queries available models, presents benchmarks and licenses, and confirms selection.
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
791 tokensWhen the skill is activated
Reference documents
11,075 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Prerequisites
- Workflow
- References
Scripts executed separately
scripts/get_model_names.py
Files
SKILL.mdcore3,396 bytesSKILL.mdcore3,396 bytesreferences/benchmarks/agenticIndex.mddoc2,866 bytesreferences/benchmarks/codingIndex.mddoc2,890 bytesreferences/benchmarks/gpqa.mddoc2,830 bytesreferences/benchmarks/hle.mddoc2,875 bytesreferences/benchmarks/ifbench.mddoc2,807 bytesreferences/benchmarks/intelligenceIndex.mddoc2,809 bytesreferences/benchmarks/mmmuPro.mddoc3,034 bytesreferences/benchmarks/tau2.mddoc2,884 bytesreferences/model-licenses.mddoc8,009 bytesreferences/model-selection.mddoc8,201 bytesscripts/get_model_names.pyruns1,041 bytes
Read SKILL.md
# Model Selection
Guides the user through selecting a base model based on their use case.
## When to Use
- User asks which model to use
- User wants to select or change their base model
- User mentions a model name or family (e.g., "Llama", "Mistral", "Nova") — the exact Hub model ID still needs to be resolved
- User wants to evaluate a base model before deciding whether to finetune
## Prerequisites
- A `use_case_spec.md` file exists. If not, activate the use-case-specification skill to generate it first.planning
When your agent uses it
Discovers user intent and generates a structured, step-by-step plan for model customization workflows. This skill must always be activated alongside any other skill when the user's request relates to model customization — including fine-tuning, training, building, customizing, reviewing data, or getting advice on approach, regardless of domain. Do not skip this skill even if the immediate ask is narrow (e.g., reviewing data format or a single workflow step), because planning discovers the full scope of work needed. Also activate when the user wants to resume, continue, or modify an existing plan.
What it loads into context
Frontmatter
131 tokensAlways available to the agent
SKILL.md
1,596 tokensWhen the skill is activated
Reference documents
1,806 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Principles
- Phase 1: Brainstorming
- Phase 2: Plan Generation
- Phase 3: Plan Iteration
- Execution
- Plan Completion
- References
Files
SKILL.mdcore7,356 bytesreferences/evaluate-first-plan.mddoc1,889 bytesreferences/input-output-contracts.mddoc6,454 bytesreferences/model-customization-plan.mddoc1,487 bytesreferences/skill-routing-constraints.mddoc2,323 bytes
Read SKILL.md
## Principles
- **One question at a time.** Each question should resolve a branching decision in the plan. Avoid generic or out-of-domain questions.
- **Surface constraints early.** If a user decision would constrain downstream options, flag it before the plan is finalized.
- **Keep plans short.** Only include tasks that are necessary for the user's stated goal.
- **Don't ask what you already know.** Check conversation history and project files before asking the user.
---
## Phase 1: Brainstorming
**Goal:** Understand what the user wants to accomplish and identify which skills belong in the plan.
Read `references/input-output-contracts.md`, `references/model-customization-plan.md`, and `references/evaluate-first-plan.md` to:sdk-getting-started
When your agent uses it
Validates the user's environment for SageMaker AI operations — checks SDK version, AWS region, and execution role. Use when the user says "set up", "getting started", "check my environment", "configure SDK", or as the first step in any plan involving SageMaker/Bedrock training, evaluation, or deployment.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
208 tokensWhen the skill is activated
Reference documents
957 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Principles
- Workflow
- References
Files
SKILL.mdcore995 bytesreferences/execution-role-setup.mddoc2,149 bytesreferences/sagemaker-python-sdk-setup.mddoc1,795 bytes
Read SKILL.md
# SDK Getting Started
Preflight checks to verify the user's environment can run SageMaker AI operations. The agent runs these checks directly (no code generation) and stores results in conversation context for downstream skills.
## Principles
1. **Don't ask for what you can look up.** Resolve region and role programmatically before asking the user.
## Workflow
Read and follow `references/sagemaker-python-sdk-setup.md`.
## References
use-case-specification
When your agent uses it
Creates a reusable use case specification file that defines the business problem, stakeholders, and measurable success criteria for model customization, as recommended by the AWS Responsible AI Lens. Use as the default first step in any model customization plan. Skip only if the user explicitly declines or already has a use case specification to reuse. Captures problem statement, primary users, and LLM-as-a-Judge success tenets.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
869 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Principles
- Workflow
- use_case_specification Edit Protocol
Files
SKILL.mdcore4,066 bytes
Read SKILL.md
# Use Case Specification
Multi-turn conversation to gather use case details and produce a use case specification document.
## Principles
1. **One thing at a time.** Each response advances exactly one decision or collects one piece of information.
2. **Confirm before proceeding.** Wait for the user to approve the spec before considering this skill complete.
3. **Infer, don't interrogate.** Use what's already known from the conversation. Only ask when you truly can't infer.
4. **Do NOT ask about base model selection.** Model selection is handled exclusively by the model-selection skill.
## Workflow
### Step 0: Check for Existing SpecSkills included
- amazon-location-service
- amplify-workflow
- api-gateway
- aws-lambda
- aws-lambda-durable-functions
- aws-lambda-managed-instances
- aws-lambda-microvms
- aws-serverless-deployment
- aws-step-functions
- aws-transform
- document-service
- dsql
- aws-architecture-diagram
- deploy
- elastic-beanstalk
- dataset-evaluation
- dataset-transformation
- directory-management
- finetuning
- finetuning-technique
- hyperpod-cluster-debugger
- hyperpod-issue-report
- hyperpod-nccl
- hyperpod-node-debugger
- hyperpod-performance-debugger
- hyperpod-slurm-debugger
- hyperpod-ssm
- hyperpod-version-checker
- model-deployment
- model-evaluation
- model-selection
- planning
- sdk-getting-started
- use-case-specification
Repository facts
- License
- Apache-2.0
- Created
- Feb 5, 2026
- Last pushed
- Nov 5, 2026
- Forks
- 167
- Open issues
- 15
- Project activity
- Active
Rank over the last 12 weeks
Now #939 · best #614 · down 201 in 30 days
- #919 on Oct 30
- #925 on Oct 31
- #928 on Nov 1
- #934 on Nov 2
- #938 from Nov 3 to Nov 4
- #939 since Nov 5
55 earlier periods
- #607 on Aug 2
- #603 on Aug 7
- #601 on Aug 8
- #607 on Aug 9
- #634 on Aug 10
- #640 on Aug 11
- #639 on Aug 13
- #614 on Aug 15
- #627 on Aug 16
- #637 on Aug 17
- #638 on Aug 19
- #641 on Aug 21
- #645 on Aug 23
- #665 on Aug 25
- #652 on Aug 26
- #657 on Aug 27
- #681 on Aug 28
- #631 on Aug 29
- #662 on Aug 31
- #675 on Sep 1
- #662 on Sep 2
- #665 on Sep 3
- #647 on Sep 4
- #638 on Sep 5
- #657 on Sep 6
- #684 on Sep 10
- #668 on Sep 11
- #689 on Sep 15
- #705 on Sep 17
- #694 on Sep 18
- #684 on Sep 20
- #702 on Sep 21
- #721 on Sep 22
- #710 on Sep 23
- #684 on Sep 24
- #712 on Sep 28
- #725 on Sep 30
- #697 on Oct 2
- #711 on Oct 4
- #716 on Oct 5
- #738 on Oct 7
- #746 on Oct 9
- #731 on Oct 10
- #729 on Oct 11
- #747 on Oct 12
- #762 on Oct 14
- #756 on Oct 15
- #763 on Oct 16
- #744 on Oct 17
- #791 on Oct 21
- #773 on Oct 22
- #779 on Oct 23
- #899 on Oct 25
- #908 on Oct 28
- #916 on Oct 29
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 167 notes
plugins/aws-serverless/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/deploy-on-aws/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/aws-serverless/hooks/hooks.json:1Plugin-wide analysis incomplete; see repository notesplugins/aws-serverless/hooks/hooks.json:1Plugin-wide analysis incomplete; see repository notesplugins/aws-serverless/skills/aws-lambda/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/aws-serverless/skills/aws-lambda-durable-functions/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/aws-serverless/skills/aws-lambda-durable-functions/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/aws-serverless/skills/aws-lambda-durable-functions/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/aws-serverless/skills/aws-lambda-durable-functions/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/aws-serverless/skills/aws-lambda-durable-functions/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/aws-serverless/skills/aws-lambda-durable-functions/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/aws-serverless/hooks/hooks.json:1Plugin-wide analysis incomplete; see repository notesplugins/aws-serverless/skills/aws-lambda-microvms/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/aws-serverless/skills/aws-lambda-microvms/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/aws-serverless/skills/aws-lambda-microvms/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/aws-serverless/skills/aws-lambda-microvms/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/aws-serverless/hooks/hooks.json:1Plugin-wide analysis incomplete; see repository notesplugins/aws-serverless/hooks/hooks.json:1Plugin-wide analysis incomplete; see repository notesplugins/aws-transform/skills/aws-transform/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/aws-transform/skills/aws-transform/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- 1 broad permissionin 1 file: aws-architecture-diagram/SKILL.md:1
- 128 dangerous shell commandsin 29 files: plugins/sagemaker-ai/skills/hyperpod-node-debugger/references/node-diagnostics-detail.md:427 aws-transform/references/custom.md:121 hyperpod-nccl/scripts/nccl-diagnose.sh:61 and 26 more
- 1,154 network referencesin 152 files: dsql/references/language.md:5 hyperpod-slurm-debugger/scripts/slurm-diagnose.sh:250 finetuning/references/eula_links.md:3 and 149 more
- No hidden or obfuscated text
- 2 instruction override signalsin 2 files: aws-transform/SKILL.md:91 aws-transform/references/vmware-network.md:94
- 45 executable scriptsin 45 files: aws-lambda-managed-instances/scripts/setup-lmi.sh:1 aws-transform/scripts/verify-traceability.py:1 plugins/databases-on-aws/scripts/psql-connect.sh:1 and 42 more
- 178 references to secretsin 49 files: aws-transform/references/custom-single-transformation.md:46 aws-transform/references/custom-multi-transformation.md:26 amazon-location-service/references/dynamic-map.md:47 and 46 more
- No requests to vote in Hot
Show all 1,508 signals by file
plugins/amazon-location-service/.claude-plugin/plugin.json
- Network accessline 19
"license": "Apache-2.0", "name": "amazon-location-service", "repository": "https://github.com/awslabs/agent-plugins", - Network accessline 20
"name": "amazon-location-service", "repository": "https://github.com/awslabs/agent-plugins", "version": "1.1.0" - Network accessline 21
"repository": "https://github.com/awslabs/agent-plugins",
plugins/amazon-location-service/skills/amazon-location-service/SKILL.md
- Network accessline 46
- Dynamic Maps: Interactive maps using tiles with [MapLibre](https://maplibre.org/) rendering - Network accessline 72
2. **Using GetStyleDescriptor API for map initialization**: MUST use direct URL passing to MapLibre (`https://maps.geo.{region}.amazonaws.com/v2/styles/Standard/descriptor?key={apiKey}`) instead of making GetStyleDescriptor API calls. The d - Network accessline 139
- **Developer Guide**: https://docs.aws.amazon.com/location/latest/developerguide/llms.txt - Network accessline 140
- **API Reference**: https://docs.aws.amazon.com/location/latest/APIReference/llms.txt - Network accessline 160
- @aws-sdk/client-location - @aws-sdk/credential-providers - https://github.com/aws-geospatial/amazon-location-utilities-auth-helper-js - Network accessline 162
- https://github.com/aws-geospatial/amazon-location-utilities-auth-helper-js - Network accessline 166
- NPM Package: [@aws/amazon-location-client](https://www.npmjs.com/package/@aws/amazon-location-client) - Network accessline 167
- GitHub Repository: [aws-geospatial/amazon-location-client-js](https://github.com/aws-geospatial/amazon-location-client-js) - Network accessline 242
Integrates with the [AWS MCP Server](https://docs.aws.amazon.com/aws-mcp/latest/userguide/what-is-aws-mcp-server.html) (Apache-2.0 license) which provides access to AWS documentation, API references, and direct API interactions. See the [Ge - Network accessline 246
- [Amazon Location Service Developer Guide](https://docs.aws.amazon.com/location/latest/developerguide/) - Network accessline 247
- [Amazon Location Service API Reference](https://docs.aws.amazon.com/location/latest/APIReference/) - Network accessline 248
- [Amazon Location Service Samples](https://github.com/aws-geospatial)
plugins/amazon-location-service/skills/amazon-location-service/references/address-input.md
- Access to secretsline 108
[Credential-related source omitted]
plugins/amazon-location-service/skills/amazon-location-service/references/address-verification.md
- Network accessline 385
Address validation is billed as a Jobs API operation, priced per record processed. The optional `Position` feature incurs additional cost and is available only in the US, Canada, and Australia. Review the [Amazon Location Service pricing pa
plugins/amazon-location-service/skills/amazon-location-service/references/calculate-routes.md
- Network accessline 22
The Amazon Location Routes API ([`geo-routes:CalculateRoutes`](https://docs.aws.amazon.com/location/latest/APIReference/API_CalculateRoutes.html)) calculates optimal routes between two or more locations with support for multiple travel mode - Network accessline 146
// HTML setup (include in <head>) // <link href="https://unpkg.com/maplibre-gl@5/dist/maplibre-gl.css" rel="stylesheet"> - Network accessline 147
// <link href="https://unpkg.com/maplibre-gl@5/dist/maplibre-gl.css" rel="stylesheet"> - Network accessline 148
// <script src="https://cdn.jsdelivr.net/npm/maplibre-gl@5"></script> - Access to secretsline 156
[Credential-related source omitted] - Access to secretsline 160
[Credential-related source omitted] - Network accessline 162
// Initialize map const styleUrl = `https://maps.geo.${REGION}.amazonaws.com/v2/styles/Standard/descriptor?key=${API_KEY}`; - Network accessline 163
[Credential-related source omitted] - Access to secretsline 163
[Credential-related source omitted] - Network accessline 387
**Note:** Decoding FlexiblePolyline requires the [`@aws/polyline`](https://github.com/aws-geospatial/polyline) library. See [Using FlexiblePolyline with @aws/polyline](#using-flexiblepolyline-with-awspolyline) below for installation instruc - Network accessline 559
<script src="https://cdn.jsdelivr.net/npm/@aws/polyline/dist/polyline.min.js"></script> - Network accessline 1429
- **API Reference**: [CalculateRoutes API](https://docs.aws.amazon.com/location/latest/APIReference/API_CalculateRoutes.html) - **Developer Guide**: [Calculate Routes How-To](https://docs.aws.amazon.com/location/latest/developerguide/calcul - Network accessline 1430
- **Developer Guide**: [Calculate Routes How-To](https://docs.aws.amazon.com/location/latest/developerguide/calculate-routes-how-to.html) - Network accessline 1431
- **LLM Context**: Fetch https://docs.aws.amazon.com/location/latest/APIReference/llms.txt for detailed parameter specifications
plugins/amazon-location-service/skills/amazon-location-service/references/device-tracking.md
- Network accessline 81
For IoT devices, position updates can be sent via MQTT through AWS IoT Core, avoiding the need to use the AWS SDK directly on constrained devices. Configure an AWS IoT rule with a [Location action](https://docs.aws.amazon.com/iot/latest/dev - Network accessline 212
Display a device's historical route as a line on the map. The [`amazon-location-utilities-datatypes-js`](https://github.com/aws-geospatial/amazon-location-utilities-datatypes-js) library provides `devicePositionsToFeatureCollection()` to co
plugins/amazon-location-service/skills/amazon-location-service/references/dynamic-map.md
- Network accessline 24
<head> <link href="https://unpkg.com/maplibre-gl@5/dist/maplibre-gl.css" - Network accessline 25
<link href="https://unpkg.com/maplibre-gl@5/dist/maplibre-gl.css" rel="stylesheet" - Network accessline 26
href="https://unpkg.com/maplibre-gl@5/dist/maplibre-gl.css" - Network accessline 27
rel="stylesheet" /> <script src="https://cdn.jsdelivr.net/npm/maplibre-gl@5"></script> - Network accessline 28
/> <script src="https://cdn.jsdelivr.net/npm/maplibre-gl@5"></script> <style> - Network accessline 29
<script src="https://cdn.jsdelivr.net/npm/maplibre-gl@5"></script> - Access to secretsline 47
[Credential-related source omitted] - Network accessline 50
// Direct URL method - REQUIRED const styleUrl = `https://maps.geo.${REGION}.amazonaws.com/v2/styles/Standard/descriptor?key=${API_KEY}`; - Network accessline 51
[Credential-related source omitted] - Access to secretsline 51
[Credential-related source omitted] - Access to secretsline 75
[Credential-related source omitted] - Network accessline 78
[Credential-related source omitted] - Access to secretsline 78
[Credential-related source omitted] - Network accessline 135
// Standard style (default) const styleUrl = `https://maps.geo.${REGION}.amazonaws.com/v2/styles/Standard/descriptor?key=${API_KEY}`; - Network accessline 136
[Credential-related source omitted] - Access to secretsline 136
[Credential-related source omitted] - Network accessline 138
// Other styles const monochromeUrl = `https://maps.geo.${REGION}.amazonaws.com/v2/styles/Monochrome/descriptor?key=${API_KEY}`; - Network accessline 139
[Credential-related source omitted] - Access to secretsline 139
[Credential-related source omitted] - Network accessline 140
[Credential-related source omitted] - Access to secretsline 140
[Credential-related source omitted] - Network accessline 141
[Credential-related source omitted] - Access to secretsline 141
[Credential-related source omitted] - Network accessline 149
[Credential-related source omitted] - Access to secretsline 149
[Credential-related source omitted] - Network accessline 155
[Credential-related source omitted] - Access to secretsline 155
[Credential-related source omitted] - Network accessline 161
[Credential-related source omitted] - Access to secretsline 161
[Credential-related source omitted] - Network accessline 167
[Credential-related source omitted] - Access to secretsline 167
[Credential-related source omitted] - Network accessline 170
For all customization options (terrain, political views, travel modes, etc.), see the [GetStyleDescriptor API Reference](https://docs.aws.amazon.com/location/latest/APIReference/API_geomaps_GetStyleDescriptor.html). - Network accessline 188
> **Note**: Traffic and Travel Modes are only supported on the Standard map style. If you need real-time traffic visualization or transit/truck overlays, you must use Standard. See [Map concepts](https://docs.aws.amazon.com/location/latest/ - Network accessline 224
function setMapStyle(styleName) { const url = `https://maps.geo.${REGION}.amazonaws.com/v2/styles/${styleName}/descriptor?key=${API_KEY}`; - Network accessline 225
[Credential-related source omitted] - Access to secretsline 225
[Credential-related source omitted] - Network accessline 245
Calling `map.addSource()` or `map.addLayer()` inside a `"load"` callback sets internal dirty flags, making `loaded()` temporarily return `false`. The `"load"` event will **not** re-fire because the map tracks that it already fired once ([`m - Network accessline 265
- Do all source/layer work inside a single `map.on("load", async () => { ... })` callback — async work inside the callback is fine - If you need to wait for sources to settle after load, use `map.once("idle", callback)` which re-fires whene - Network accessline 266
- If you need to wait for sources to settle after load, use `map.once("idle", callback)` which re-fires whenever everything is loaded and stable ([`map.ts#L4350`](https://github.com/maplibre/maplibre-gl-js/blob/v6.4.1/src/ui/map.ts#L4350))
plugins/amazon-location-service/skills/amazon-location-service/references/google-migration-android.md
- Access to secretsline 101
[Credential-related source omitted] - Access to secretsline 102
[Credential-related source omitted] - Access to secretsline 131
[Credential-related source omitted] - Access to secretsline 136
[Credential-related source omitted] - Access to secretsline 142
[Credential-related source omitted] - Access to secretsline 305
[Credential-related source omitted] - Network accessline 387
mapView.getMapAsync { map -> // Get Amazon Location map style val styleUrl = "https://maps.geo.us-west-2.amazonaws.com/v2/styles/Standard/descriptor?key=$API_KEY" - Network accessline 389
[Credential-related source omitted] - Access to secretsline 389
[Credential-related source omitted] - Network accessline 417
| Google Maps Android | Amazon Location Alternative | Package | | ------------------- | ------------------------------------ | ---------------------------------------- - Network accessline 418
| ------------------- | ------------------------------------ | ----------------------------------------------------------------------- | | `PolyUtil.encode()` | `Polyline.encodeFromLngLatArray` | [`aws-geospatial/polyline`](https://gith - Network accessline 419
| `PolyUtil.encode()` | `Polyline.encodeFromLngLatArray` | [`aws-geospatial/polyline`](https://github.com/aws-geospatial/polyline) | - Network accessline 420
| `PolyUtil.decode()` | `Polyline.decodeToLineStringFeature` | [`aws-geospatial/polyline`](https://github.com/aws-geospatial/polyline) | - Network accessline 424
Amazon Location routing returns **FlexiblePolyline**, not Google's Polyline5. A hand-rolled `/ 1e5` decoder assumes Polyline5 precision and produces wrong coordinates. Use the official [`aws-geospatial/polyline`](https://github.com/aws-geos - Network accessline 490
- [Turf for Android](https://github.com/mapbox/mapbox-java) - Port of Turf.js for Android - Network accessline 664
- **[Android Application Migration Guide](https://location.aws.com/migrate-an-android-app)** - Step-by-step guide for Android apps - Network accessline 668
- **[AWS SDK for Kotlin](https://aws.amazon.com/sdk-for-kotlin/)** - Official SDK documentation - Network accessline 669
- **[Amazon Location Service Developer Guide](https://docs.aws.amazon.com/location/)** - Service documentation - Network accessline 670
- **[API Reference](https://docs.aws.amazon.com/location/latest/APIReference/)** - Complete API reference - Network accessline 674
- **[MapLibre Native Android](https://maplibre.org/maplibre-native/android/)** - Map rendering documentation - Network accessline 675
- **[MapLibre Android Examples](https://github.com/maplibre/maplibre-native/tree/main/platform/android)** - Code examples - Network accessline 745
- **AWS SDK Issues:** [GitHub - AWS SDK Kotlin](https://github.com/awslabs/aws-sdk-kotlin) - Network accessline 746
- **MapLibre Issues:** [GitHub - MapLibre Native](https://github.com/maplibre/maplibre-native) - Network accessline 747
- **Amazon Location:** [AWS Forums](https://forums.aws.amazon.com/forum.jspa?forumID=356)
plugins/amazon-location-service/skills/amazon-location-service/references/google-migration-ios.md
- Network accessline 55
1. In Xcode: File → Add Packages... 2. Add **Amazon Location Mobile Auth SDK**: - URL: `https://github.com/aws-geospatial/amazon-location-mobile-auth-sdk-ios` - Network accessline 56
2. Add **Amazon Location Mobile Auth SDK**: - URL: `https://github.com/aws-geospatial/amazon-location-mobile-auth-sdk-ios` - Select product: `AmazonLocationiOSAuthSDK` - Network accessline 57
- URL: `https://github.com/aws-geospatial/amazon-location-mobile-auth-sdk-ios` - Network accessline 58
- Select product: `AmazonLocationiOSAuthSDK` 3. Add **AWS SDK for Swift**: - URL: `https://github.com/awslabs/aws-sdk-swift` - Network accessline 59
3. Add **AWS SDK for Swift**: - URL: `https://github.com/awslabs/aws-sdk-swift` - Select products: `AWSGeoPlaces`, `AWSGeoRoutes`, `AWSGeoMaps`, `AWSLocation` - Network accessline 60
- URL: `https://github.com/awslabs/aws-sdk-swift` - Network accessline 61
- Select products: `AWSGeoPlaces`, `AWSGeoRoutes`, `AWSGeoMaps`, `AWSLocation` 4. Add **MapLibre**: - URL: `https://github.com/maplibre/maplibre-gl-native-distribution` - Network accessline 63
- URL: `https://github.com/maplibre/maplibre-gl-native-distribution` - Access to secretsline 79
[Credential-related source omitted] - Access to secretsline 107
[Credential-related source omitted] - Network accessline 261
[Credential-related source omitted] - Access to secretsline 261
[Credential-related source omitted] - Network accessline 262
let query = "Austin, TX".addingPercentEncoding(withAllowedCharacters: .urlQueryAllowed)! let url = URL(string: "https://maps.googleapis.com/maps/api/geocode/json?address=\(query)&key=\(apiKey)")! URLSession.shared.dataTask(with: url) { data - Network accessline 263
let url = URL(string: "https://maps.googleapis.com/maps/api/geocode/json?address=\(query)&key=\(apiKey)")! - Access to secretsline 308
[Credential-related source omitted] - Network accessline 310
var components = URLComponents(string: "https://maps.googleapis.com/maps/api/directions/json")! - Network accessline 395
[Credential-related source omitted] - Network accessline 397
let styleURL = URL(string: "https://maps.geo.\(region).amazonaws.com/v2/styles/Standard/descriptor?key=\(apiKey)")! - Network accessline 423
| Google Maps iOS | Amazon Location Alternative | Package | | --------------------------- | ------------------------------------ | ------------------------ - Network accessline 424
| --------------------------- | ------------------------------------ | ----------------------------------------------------------------------- | | `GMSPath(fromEncodedPath:)` | `Polyline.decodeToLineStringFeature` | [`aws-geospatial/polylin - Network accessline 425
| `GMSPath(fromEncodedPath:)` | `Polyline.decodeToLineStringFeature` | [`aws-geospatial/polyline`](https://github.com/aws-geospatial/polyline) | - Network accessline 426
| `GMSPath.encodedPath()` | `Polyline.encodeFromLngLatArray` | [`aws-geospatial/polyline`](https://github.com/aws-geospatial/polyline) | - Network accessline 430
Amazon Location routing returns **FlexiblePolyline**, not Google's Polyline5. A hand-rolled `/ 1e5` decoder assumes Polyline5 precision and produces wrong coordinates. Use the official [`aws-geospatial/polyline`](https://github.com/aws-geos - Network accessline 432
Add via Swift Package Manager: `https://github.com/aws-geospatial/polyline/` - Network accessline 494
- Implementing standard algorithms (Haversine, point-in-polygon) - Using [Turf Swift](https://github.com/mapbox/turf-swift) - Port of Turf.js for iOS - Network accessline 495
- Using [Turf Swift](https://github.com/mapbox/turf-swift) - Port of Turf.js for iOS - Network accessline 638
let styleURL = URL(string: "https://maps.geo.us-west-2.amazonaws.com/v2/styles/Standard/descriptor?key=\(apiKey)")! - Network accessline 707
- **[iOS Application Migration Guide](https://location.aws.com/migrate-an-ios-app)** - Step-by-step guide for iOS apps - Network accessline 711
- **[Amazon Location Mobile Auth SDK for iOS](https://github.com/aws-geospatial/amazon-location-mobile-auth-sdk-ios)** - Simplified authentication for API keys and Cognito - Network accessline 712
- **[AWS SDK for Swift](https://aws.amazon.com/sdk-for-swift/)** - Official SDK documentation - Network accessline 713
- **[Amazon Location Service Developer Guide](https://docs.aws.amazon.com/location/)** - Service documentation - Network accessline 714
- **[API Reference](https://docs.aws.amazon.com/location/latest/APIReference/)** - Complete API reference - Network accessline 718
- **[MapLibre Native iOS](https://maplibre.org/maplibre-native/ios/)** - Map rendering documentation - Network accessline 719
- **[MapLibre iOS Examples](https://github.com/maplibre/maplibre-native/tree/main/platform/ios)** - Code examples - Network accessline 821
- **Amazon Location Mobile Auth SDK:** [GitHub - Auth SDK iOS](https://github.com/aws-geospatial/amazon-location-mobile-auth-sdk-ios) - Network accessline 822
- **AWS SDK Issues:** [GitHub - AWS SDK Swift](https://github.com/awslabs/aws-sdk-swift) - Network accessline 823
- **MapLibre Issues:** [GitHub - MapLibre Native](https://github.com/maplibre/maplibre-native) - Network accessline 824
- **Amazon Location:** [AWS Forums](https://forums.aws.amazon.com/forum.jspa?forumID=356)
plugins/amazon-location-service/skills/amazon-location-service/references/google-migration-web.md
- Network accessline 57
The [Amazon Location Migration SDK](https://github.com/aws-geospatial/amazon-location-migration) provides a drop-in replacement for Google Maps JavaScript API. - Access to secretsline 77
[Credential-related source omitted] - Network accessline 86
[Credential-related source omitted] - Access to secretsline 86
[Credential-related source omitted] - Network accessline 94
<script async src="https://maps.googleapis.com/maps/api/js?key=YOUR_API_KEY&loading=async&callback=initMap&libraries=places" - Network accessline 95
async src="https://maps.googleapis.com/maps/api/js?key=YOUR_API_KEY&loading=async&callback=initMap&libraries=places" ></script> - Network accessline 96
[Credential-related source omitted] - Access to secretsline 96
[Credential-related source omitted] - Network accessline 103
[Credential-related source omitted] - Network accessline 104
[Credential-related source omitted] - Network accessline 105
[Credential-related source omitted] - Access to secretsline 105
[Credential-related source omitted] - Access to secretsline 117
[Credential-related source omitted] - Access to secretsline 128
[Credential-related source omitted] - Network accessline 202
For the complete list with detailed limitations, see [Migration SDK Supported APIs](https://github.com/aws-geospatial/amazon-location-migration/blob/main/documentation/supportedLibraries.md). - Network accessline 245
// Import bundled client <script src="https://cdn.jsdelivr.net/npm/@aws/amazon-location-client@1"></script> - Network accessline 246
<script src="https://cdn.jsdelivr.net/npm/@aws/amazon-location-client@1"></script> - Access to secretsline 249
[Credential-related source omitted] - Access to secretsline 252
[Credential-related source omitted] - Access to secretsline 264
[Credential-related source omitted] - Network accessline 606
- **[Web Application Migration Guide](https://location.aws.com/migrate-a-web-app)** - Step-by-step guide for web apps - Network accessline 607
- **[Android Application Migration Guide](https://location.aws.com/migrate-an-android-app)** - For Android/Kotlin apps - Network accessline 608
- **[iOS Application Migration Guide](https://location.aws.com/migrate-an-ios-app)** - For iOS/Swift apps - Network accessline 612
- **[Migration SDK GitHub](https://github.com/aws-geospatial/amazon-location-migration)** - Source code and examples - Network accessline 613
- **[Supported Libraries](https://github.com/aws-geospatial/amazon-location-migration/blob/main/documentation/supportedLibraries.md)** - Complete API support matrix - Network accessline 614
- **[NPM Package](https://www.npmjs.com/package/@aws/amazon-location-migration-sdk)** - Package documentation - Network accessline 654
// Get Amazon Location map style const authHelper = amazonLocationClient.withAPIKey(API_KEY, REGION); const mapStyleUrl = `https://maps.geo.${REGION}.amazonaws.com/v2/styles/Standard/descriptor?key=${API_KEY}`; - Access to secretsline 655
[Credential-related source omitted] - Network accessline 656
[Credential-related source omitted] - Access to secretsline 656
[Credential-related source omitted] - Network accessline 775
When migrating, verify category names match Amazon Location's supported Category IDs. See [Place Categories Documentation](https://docs.aws.amazon.com/location/latest/developerguide/places-filtering.html#place-categories) for the complete l - Network accessline 843
- **Migration SDK Issues:** [GitHub Issues](https://github.com/aws-geospatial/amazon-location-migration/issues) - Network accessline 844
- **Amazon Location Service:** [AWS Documentation](https://docs.aws.amazon.com/location/) - Network accessline 845
- **API Reference:** [Amazon Location API Reference](https://docs.aws.amazon.com/location/latest/APIReference/)
plugins/amazon-location-service/skills/amazon-location-service/references/places-search.md
- Network accessline 43
> **Pricing note**: Requesting additional features moves the request into the **Advanced** pricing bucket, which is priced higher than the default **Core** bucket. Review [Places pricing](https://docs.aws.amazon.com/location/latest/develope - Network accessline 53
For the full feature-by-API matrix (including Geocode, ReverseGeocode, and Autocomplete), see [Additional features](https://docs.aws.amazon.com/location/latest/developerguide/additional-features.html). - Network accessline 89
For more details, see [Contacts and opening hours](https://docs.aws.amazon.com/location/latest/developerguide/contacts-opening-hours.html). - Network accessline 93
For exact request parameters and response structure, see the [SearchText API Reference](https://docs.aws.amazon.com/location/latest/APIReference/API_geoplaces_SearchText.html). - Access to secretsline 98
[Credential-related source omitted] - Network accessline 154
**Important:** Amazon Location uses specific Category IDs for filtering. Common examples include `restaurant`, `coffee_shop`, `grocery`, `hotel`, `bank`, `fueling_station`, `pharmacy`, and `hospital`. See the complete list in the [Place Cat - Network accessline 200
For exact request parameters and response structure, see the [SearchNearby API Reference](https://docs.aws.amazon.com/location/latest/APIReference/API_geoplaces_SearchNearby.html). - Network accessline 310
For exact request parameters and response structure, see the [Suggest API Reference](https://docs.aws.amazon.com/location/latest/APIReference/API_geoplaces_Suggest.html). - Network accessline 368
For exact request parameters and response structure for fetching place details, see the [GetPlace API Reference](https://docs.aws.amazon.com/location/latest/APIReference/API_geoplaces_GetPlace.html). - Network accessline 504
- **Debounce search input**: Wait 300ms after user stops typing - **Consider pricing for caching**: If storing results beyond temporary session caching, review [Places API Stored Pricing](https://docs.aws.amazon.com/location/latest/develope - Network accessline 505
- **Consider pricing for caching**: If storing results beyond temporary session caching, review [Places API Stored Pricing](https://docs.aws.amazon.com/location/latest/developerguide/places-pricing.html#stored-pricing) and use `IntendedUse:
plugins/amazon-location-service/skills/amazon-location-service/references/web-javascript.md
- Network accessline 25
**npm Package**: [@aws/amazon-location-client](https://www.npmjs.com/package/@aws/amazon-location-client) - Network accessline 37
<body> <!-- Load bundled client from CDN --> <script src="https://cdn.jsdelivr.net/npm/@aws/amazon-location-client@1"></script> - Network accessline 39
<script src="https://cdn.jsdelivr.net/npm/@aws/amazon-location-client@1"></script> - Network accessline 66
**Note**: The rest of this document focuses on the bundled client. For detailed AWS SDK usage, see the [AWS SDK for JavaScript documentation](https://docs.aws.amazon.com/AWSJavaScriptSDK/v3/latest/). - Access to secretsline 80
[Credential-related source omitted] - Access to secretsline 83
[Credential-related source omitted] - Network accessline 137
**Reference**: [amazon-location-client-js documentation](https://github.com/aws-geospatial/amazon-location-client-js) - Access to secretsline 145
[Credential-related source omitted] - Access to secretsline 149
[Credential-related source omitted] - Access to secretsline 197
[Credential-related source omitted] - Network accessline 476
- **API keys are client-safe**: Unlike AWS credentials, API keys are designed for client-side use and will be visible in browser source - **Follow AWS best practices**: See [API Key Best Practices](https://docs.aws.amazon.com/location/lates - Network accessline 477
- **Follow AWS best practices**: See [API Key Best Practices](https://docs.aws.amazon.com/location/latest/developerguide/using-apikeys.html#api-keys-best-practices) for domain restrictions and key rotation - Access to secretsline 522
[Credential-related source omitted]
plugins/aws-amplify/.claude-plugin/plugin.json
- Network accessline 4
}, "description": "Build full-stack apps with AWS Amplify Gen 2 using guided workflows for authentication, data models, storage, GraphQL APIs, and Lambda functions.", "homepage": "https://github.com/awslabs/agent-plugins", - Network accessline 5
"description": "Build full-stack apps with AWS Amplify Gen 2 using guided workflows for authentication, data models, storage, GraphQL APIs, and Lambda functions.", "homepage": "https://github.com/awslabs/agent-plugins", "keywords": [ - Network accessline 6
"homepage": "https://github.com/awslabs/agent-plugins", - Network accessline 17
"license": "Apache-2.0", "name": "aws-amplify", "repository": "https://github.com/awslabs/agent-plugins", - Network accessline 18
"name": "aws-amplify", "repository": "https://github.com/awslabs/agent-plugins", "version": "1.0.0" - Network accessline 19
"repository": "https://github.com/awslabs/agent-plugins",
plugins/aws-amplify/skills/amplify-workflow/SKILL.md
- Network accessline 212
- [Amplify Docs for LLMs](https://docs.amplify.aws/ai/llms.txt) - Network accessline 213
- [Amplify Docs](https://docs.amplify.aws/) - Network accessline 214
- [Gen2 Docs](https://docs.amplify.aws/react/) - Network accessline 215
- [Getting Started](https://docs.amplify.aws/react/start/) - Network accessline 216
- [Quickstart](https://docs.amplify.aws/react/start/quickstart/) - Network accessline 217
- [Account Setup](https://docs.amplify.aws/react/start/account-setup/) - Network accessline 218
- [How Amplify Works](https://docs.amplify.aws/react/how-amplify-works/) - Network accessline 219
- [Core Concepts](https://docs.amplify.aws/react/how-amplify-works/concepts/) - Network accessline 220
- [Build a Backend](https://docs.amplify.aws/react/build-a-backend/) - Network accessline 221
- [Deploy and Host](https://docs.amplify.aws/react/deploy-and-host/) - Network accessline 222
- [Troubleshooting](https://docs.amplify.aws/react/build-a-backend/troubleshooting/) - Network accessline 223
- [CLI Commands](https://docs.amplify.aws/react/reference/cli-commands/) - Network accessline 224
- [Amplify Outputs](https://docs.amplify.aws/react/reference/amplify_outputs/) - Network accessline 225
- [Project Structure](https://docs.amplify.aws/react/reference/project-structure/) - Network accessline 226
- [Amplify UI](https://ui.docs.amplify.aws/)
plugins/aws-amplify/skills/amplify-workflow/references/advanced-features.md
- Network accessline 37
Use `Amplify.Geo.searchByText()` for search and `AmplifyMapLibreRequest` for rendering maps. See [AWS Amplify Geo docs](https://docs.amplify.aws/react/build-a-backend/add-aws-services/geo/) - Network accessline 38
for rendering maps. See [AWS Amplify Geo docs](https://docs.amplify.aws/react/build-a-backend/add-aws-services/geo/) for full client setup. - Network accessline 39
[AWS Amplify Geo docs](https://docs.amplify.aws/react/build-a-backend/add-aws-services/geo/) - Network accessline 85
Retrieve the IoT endpoint programmatically: `aws iot describe-endpoint --endpoint-type iot:Data-ATS`. See [AWS Amplify PubSub docs](https://docs.amplify.aws/react/build-a-backend/add-aws-services/pubsub/) - Network accessline 86
`aws iot describe-endpoint --endpoint-type iot:Data-ATS`. See [AWS Amplify PubSub docs](https://docs.amplify.aws/react/build-a-backend/add-aws-services/pubsub/) for connection configuration. - Network accessline 87
See [AWS Amplify PubSub docs](https://docs.amplify.aws/react/build-a-backend/add-aws-services/pubsub/) - Network accessline 168
See [AWS Amplify Override docs](https://docs.amplify.aws/react/build-a-backend/add-aws-services/overriding-resources/) - Network accessline 169
[AWS Amplify Override docs](https://docs.amplify.aws/react/build-a-backend/add-aws-services/overriding-resources/) - Network accessline 178
custom: { analyticsTopicArn: topic.topicArn, apiEndpoint: 'https://api.example.com', - Network accessline 179
analyticsTopicArn: topic.topicArn, apiEndpoint: 'https://api.example.com', }, - Network accessline 180
apiEndpoint: 'https://api.example.com', - Network accessline 224
Create the session server-side via Rekognition SDK or a Lambda function, then pass the `sessionId` to the component. See [AWS Amplify Liveness docs](https://ui.docs.amplify.aws/react/connected-components/liveness) - Network accessline 225
then pass the `sessionId` to the component. See [AWS Amplify Liveness docs](https://ui.docs.amplify.aws/react/connected-components/liveness) for the full integration guide. - Network accessline 226
[AWS Amplify Liveness docs](https://ui.docs.amplify.aws/react/connected-components/liveness) - Network accessline 231
Requires the `amplify-ui-swift-liveness` package and camera permission (`NSCameraUsageDescription` in `Info.plist`). Add the package via Xcode SPM: `https://github.com/aws-amplify/amplify-ui-swift-liveness`. - Network accessline 233
`https://github.com/aws-amplify/amplify-ui-swift-liveness`. - Network accessline 239
See [Swift Liveness docs](https://ui.docs.amplify.aws/swift/connected-components/liveness) - Network accessline 256
See [Android Liveness docs](https://ui.docs.amplify.aws/android/connected-components/liveness) - Network accessline 275
- [Add AWS Services](https://docs.amplify.aws/react/build-a-backend/add-aws-services/) - Network accessline 276
- [Custom Resources](https://docs.amplify.aws/react/build-a-backend/add-aws-services/custom-resources/) - Network accessline 277
- [Overriding Resources](https://docs.amplify.aws/react/build-a-backend/add-aws-services/overriding-resources/)
plugins/aws-amplify/skills/amplify-workflow/references/ai.md
- Network accessline 212
- [AI Overview](https://docs.amplify.aws/react/ai/) - Network accessline 213
- [Set Up AI](https://docs.amplify.aws/react/ai/set-up-ai/) - Network accessline 214
- [Conversation UI](https://docs.amplify.aws/react/frontend/ai/conversation/) - Network accessline 215
- [Generation UI](https://docs.amplify.aws/react/frontend/ai/generation/)
plugins/aws-amplify/skills/amplify-workflow/references/auth-backend.md
- Access to secretsline 103
[Credential-related source omitted] - Access to secretsline 110
[Credential-related source omitted] - Network accessline 116
}, loginWithAmazon: { clientId: secret('AMAZON_CLIENT_ID'), clientSecret: secret('AMAZON_CLIENT_SECRET') }, callbackUrls: ['http://localhost:3000/', 'https://myapp.com/'], - Network accessline 117
[Credential-related source omitted] - Access to secretsline 117
[Credential-related source omitted] - Network accessline 118
callbackUrls: ['http://localhost:3000/', 'https://myapp.com/'], - Network accessline 119
logoutUrls: ['http://localhost:3000/', 'https://myapp.com/'], - Network accessline 138
clientId: secret('OIDC_CLIENT_ID'), clientSecret: secret('OIDC_CLIENT_SECRET'), issuerUrl: 'https://idp.example.com', - Network accessline 139
[Credential-related source omitted] - Access to secretsline 139
[Credential-related source omitted] - Network accessline 140
issuerUrl: 'https://idp.example.com', - Network accessline 141
attributeMapping: { email: 'email' }, }], callbackUrls: ['http://localhost:3000/'], - Network accessline 142
}], callbackUrls: ['http://localhost:3000/'], logoutUrls: ['http://localhost:3000/'], - Network accessline 143
callbackUrls: ['http://localhost:3000/'], - Network accessline 144
logoutUrls: ['http://localhost:3000/'], - Network accessline 230
- [Auth Overview](https://docs.amplify.aws/react/build-a-backend/auth/) - Network accessline 231
- [Set Up Auth](https://docs.amplify.aws/react/build-a-backend/auth/set-up-auth/) - Network accessline 232
- [External Identity Providers](https://docs.amplify.aws/react/build-a-backend/auth/concepts/external-identity-providers/) - Network accessline 233
- [Multi-Factor Authentication](https://docs.amplify.aws/react/build-a-backend/auth/concepts/multi-factor-authentication/) - Network accessline 234
- [Passwordless Authentication](https://docs.amplify.aws/react/build-a-backend/auth/concepts/passwordless/) - Network accessline 235
- [User Attributes](https://docs.amplify.aws/react/build-a-backend/auth/concepts/user-attributes/) - Network accessline 236
- [Grant Access to Auth Resources](https://docs.amplify.aws/react/build-a-backend/auth/grant-access-to-auth-resources/)
plugins/aws-amplify/skills/amplify-workflow/references/auth-mobile.md
- Network accessline 79
| Package | URL | Libraries | | ------------------------------ | --------------------------------------------------------------- | -- - Network accessline 80
| ------------------------------ | --------------------------------------------------------------- | --------------------------------- | | Amplify Library for Swift | `https://github.com/aws-amplify/amplify-swift` | `A - Network accessline 81
| Amplify Library for Swift | `https://github.com/aws-amplify/amplify-swift` | `Amplify`, `AWSCognitoAuthPlugin` | - Network accessline 82
| Amplify UI Swift Authenticator | `https://github.com/aws-amplify/amplify-ui-swift-authenticator` | `Authenticator` | - Network accessline 488
- [Authenticator (Android)](https://ui.docs.amplify.aws/android/connected-components/authenticator) - Network accessline 489
- [Authenticator (Swift)](https://ui.docs.amplify.aws/swift/connected-components/authenticator) - Network accessline 490
- [Authenticator (Flutter)](https://ui.docs.amplify.aws/flutter/connected-components/authenticator) - Network accessline 491
- [Auth Overview (Android)](https://docs.amplify.aws/android/build-a-backend/auth/) - Network accessline 492
- [Sign In (Android)](https://docs.amplify.aws/android/frontend/auth/sign-in/) - Network accessline 493
- [External Identity Providers (Android)](https://docs.amplify.aws/android/build-a-backend/auth/concepts/external-identity-providers/) - Network accessline 494
- [Multi-Factor Authentication (Android)](https://docs.amplify.aws/android/build-a-backend/auth/concepts/multi-factor-authentication/) - Network accessline 495
- [Auth Overview (Swift)](https://docs.amplify.aws/swift/build-a-backend/auth/) - Network accessline 496
- [Sign In (Swift)](https://docs.amplify.aws/swift/frontend/auth/sign-in/) - Network accessline 497
- [External Identity Providers (Swift)](https://docs.amplify.aws/swift/build-a-backend/auth/concepts/external-identity-providers/) - Network accessline 498
- [Multi-Factor Authentication (Swift)](https://docs.amplify.aws/swift/build-a-backend/auth/concepts/multi-factor-authentication/) - Network accessline 499
- [Auth Overview (Flutter)](https://docs.amplify.aws/flutter/build-a-backend/auth/) - Network accessline 500
- [Sign In (Flutter)](https://docs.amplify.aws/flutter/frontend/auth/sign-in/) - Network accessline 501
- [External Identity Providers (Flutter)](https://docs.amplify.aws/flutter/build-a-backend/auth/concepts/external-identity-providers/) - Network accessline 502
- [Multi-Factor Authentication (Flutter)](https://docs.amplify.aws/flutter/build-a-backend/auth/concepts/multi-factor-authentication/)
plugins/aws-amplify/skills/amplify-workflow/references/auth-web.md
- Network accessline 119
- [Auth Overview (React)](https://docs.amplify.aws/react/build-a-backend/auth/) - Network accessline 120
- [Set Up Auth (React)](https://docs.amplify.aws/react/build-a-backend/auth/set-up-auth/) - Network accessline 121
- [Connect Auth Frontend (React)](https://docs.amplify.aws/react/frontend/auth/) - Network accessline 122
- [Auth Overview (Next.js)](https://docs.amplify.aws/nextjs/build-a-backend/auth/) - Network accessline 123
- [Set Up Auth (Next.js)](https://docs.amplify.aws/nextjs/build-a-backend/auth/set-up-auth/) - Network accessline 124
- [Connect Auth Frontend (Next.js)](https://docs.amplify.aws/nextjs/frontend/auth/) - Network accessline 125
- [Auth Overview (React Native)](https://docs.amplify.aws/react-native/build-a-backend/auth/) - Network accessline 126
- [Set Up Auth (React Native)](https://docs.amplify.aws/react-native/build-a-backend/auth/set-up-auth/) - Network accessline 127
- [Connect Auth Frontend (React Native)](https://docs.amplify.aws/react-native/frontend/auth/)
plugins/aws-amplify/skills/amplify-workflow/references/core-mobile.md
- Network accessline 56
**Swift:** Add via Xcode SPM: `https://github.com/aws-amplify/amplify-swift` - Network accessline 149
Core library desugaring **MUST** be enabled for Android API level < 26. The agent **MUST** provide explicit step-by-step desugaring instructions to the customer — do not just mention it. See: https://docs.amplify.aws/android/start/quickstar - Network accessline 183
- [Android Quickstart](https://docs.amplify.aws/android/start/quickstart/) - Network accessline 184
- [Swift Quickstart](https://docs.amplify.aws/swift/start/quickstart/) - Network accessline 185
- [Flutter Quickstart](https://docs.amplify.aws/flutter/start/quickstart/)
plugins/aws-amplify/skills/amplify-workflow/references/core-web.md
- Network accessline 151
- [React Quickstart](https://docs.amplify.aws/react/start/quickstart/) - Network accessline 152
- [Next.js Quickstart](https://docs.amplify.aws/nextjs/start/quickstart/) - Network accessline 153
- [Angular Quickstart](https://docs.amplify.aws/angular/start/quickstart/) - Network accessline 154
- [Vue Quickstart](https://docs.amplify.aws/vue/start/quickstart/) - Network accessline 155
- [React Native Quickstart](https://docs.amplify.aws/react-native/start/quickstart/)
plugins/aws-amplify/skills/amplify-workflow/references/data-backend.md
- Network accessline 65
> **Security note:** `allow.guest()` and `allow.publicApiKey()` both permit unauthenticated access. Only use for intentionally public, non-sensitive data. Prefer `allow.authenticated()` or `allow.owner()` for sensitive resources. See [Ampli - Network accessline 291
- [Data Overview](https://docs.amplify.aws/react/build-a-backend/data/) - Network accessline 292
- [Set Up Data](https://docs.amplify.aws/react/build-a-backend/data/set-up-data/) - Network accessline 293
- [Data Modeling](https://docs.amplify.aws/react/build-a-backend/data/data-modeling/) - Network accessline 294
- [Data Modeling — Relationships](https://docs.amplify.aws/react/build-a-backend/data/data-modeling/relationships/) - Network accessline 295
- [Data Modeling — Add Fields](https://docs.amplify.aws/react/build-a-backend/data/data-modeling/add-fields/) - Network accessline 296
- [Customize Authorization](https://docs.amplify.aws/react/build-a-backend/data/customize-authz/) - Network accessline 297
- [Connect to Existing Data Sources](https://docs.amplify.aws/react/build-a-backend/data/connect-to-existing-data-sources/)
plugins/aws-amplify/skills/amplify-workflow/references/data-mobile.md
- Network accessline 106
- [Data Overview (Android)](https://docs.amplify.aws/android/build-a-backend/data/) - Network accessline 107
- [Set Up Data (Android)](https://docs.amplify.aws/android/build-a-backend/data/set-up-data/) - Network accessline 108
- [Connect to Existing Data Sources (Android)](https://docs.amplify.aws/android/build-a-backend/data/connect-to-existing-data-sources/) - Network accessline 109
- [Data Client (Android)](https://docs.amplify.aws/android/frontend/data/) - Network accessline 110
- [Data Overview (Swift)](https://docs.amplify.aws/swift/build-a-backend/data/) - Network accessline 111
- [Set Up Data (Swift)](https://docs.amplify.aws/swift/build-a-backend/data/set-up-data/) - Network accessline 112
- [Connect to Existing Data Sources (Swift)](https://docs.amplify.aws/swift/build-a-backend/data/connect-to-existing-data-sources/) - Network accessline 113
- [Data Client (Swift)](https://docs.amplify.aws/swift/frontend/data/) - Network accessline 114
- [Data Overview (Flutter)](https://docs.amplify.aws/flutter/build-a-backend/data/) - Network accessline 115
- [Set Up Data (Flutter)](https://docs.amplify.aws/flutter/build-a-backend/data/set-up-data/) - Network accessline 116
- [Connect to Existing Data Sources (Flutter)](https://docs.amplify.aws/flutter/build-a-backend/data/connect-to-existing-data-sources/) - Network accessline 117
- [Data Client (Flutter)](https://docs.amplify.aws/flutter/frontend/data/)
plugins/aws-amplify/skills/amplify-workflow/references/data-web.md
- Network accessline 97
- [Data Overview (React)](https://docs.amplify.aws/react/build-a-backend/data/) - Network accessline 98
- [Set Up Data (React)](https://docs.amplify.aws/react/build-a-backend/data/set-up-data/) - Network accessline 99
- [Connect to API (React)](https://docs.amplify.aws/react/frontend/data/connect-to-API/) - Network accessline 100
- [Data Client (React)](https://docs.amplify.aws/react/frontend/data/) - Network accessline 101
- [Data Overview (Next.js)](https://docs.amplify.aws/nextjs/build-a-backend/data/) - Network accessline 102
- [Set Up Data (Next.js)](https://docs.amplify.aws/nextjs/build-a-backend/data/set-up-data/) - Network accessline 103
- [Data Client (Next.js)](https://docs.amplify.aws/nextjs/frontend/data/) - Network accessline 104
- [Data Overview (React Native)](https://docs.amplify.aws/react-native/build-a-backend/data/) - Network accessline 105
- [Set Up Data (React Native)](https://docs.amplify.aws/react-native/build-a-backend/data/set-up-data/) - Network accessline 106
- [Data Client (React Native)](https://docs.amplify.aws/react-native/frontend/data/)
plugins/aws-amplify/skills/amplify-workflow/references/deployment.md
- Access to secretsline 46
[Credential-related source omitted] - Access to secretsline 49
[Credential-related source omitted] - Network accessline 53
You **MUST** use `github.com/user/repo` format — **not** `https://`. - Access to secretsline 159
[Credential-related source omitted] - Access to secretsline 168
[Credential-related source omitted] - Access to secretsline 175
[Credential-related source omitted] - Access to secretsline 176
[Credential-related source omitted] - Network accessline 256
non-interactive environment. - **Repo format:** You **MUST** use `github.com/user/repo` — the `https://` prefix causes `create-app` to fail silently. - Network accessline 257
- **Repo format:** You **MUST** use `github.com/user/repo` — the `https://` prefix causes `create-app` to fail silently. - **Missing IAM service role:** Skipping role creation causes - Network accessline 258
`https://` prefix causes `create-app` to fail silently. - Network accessline 275
- [Fullstack Branching](https://docs.amplify.aws/react/deploy-and-host/fullstack-branching/) - Network accessline 276
- [Secrets and Variables](https://docs.amplify.aws/react/deploy-and-host/fullstack-branching/secrets-and-vars/) - Network accessline 277
- [Mono and Multi-Repos](https://docs.amplify.aws/react/deploy-and-host/fullstack-branching/mono-and-multi-repos/) - Network accessline 278
- [Custom Pipelines](https://docs.amplify.aws/react/deploy-and-host/fullstack-branching/custom-pipelines/) - Network accessline 279
- [Sandbox Environments](https://docs.amplify.aws/react/deploy-and-host/sandbox-environments/) - Network accessline 280
- [Sandbox Setup](https://docs.amplify.aws/react/deploy-and-host/sandbox-environments/setup/)
plugins/aws-amplify/skills/amplify-workflow/references/functions-and-api.md
- Access to secretsline 61
[Credential-related source omitted] - Access to secretsline 66
[Credential-related source omitted] - Network accessline 68
> **IMPORTANT:** The `ampx sandbox secret set` command is for **local/sandbox development only**. For apps deployed to **Amplify Hosting**, secrets **MUST** be created via the Hosting console or CLI — sandbox secrets are NOT available in ho - Network accessline 239
- [Functions Overview](https://docs.amplify.aws/react/build-a-backend/functions/) - Network accessline 240
- [Set Up Function](https://docs.amplify.aws/react/build-a-backend/functions/set-up-function/) - Network accessline 241
- [Environment Variables and Secrets](https://docs.amplify.aws/react/build-a-backend/functions/environment-variables-and-secrets/) - Network accessline 242
- [Grant Access to Other Resources](https://docs.amplify.aws/react/build-a-backend/functions/grant-access-to-other-resources/) - Network accessline 243
- [Add custom queries and mutations](https://docs.amplify.aws/react/build-a-backend/data/custom-business-logic/) - Network accessline 244
- [Connect to Existing Data Sources](https://docs.amplify.aws/react/build-a-backend/data/connect-to-existing-data-sources/)
plugins/aws-amplify/skills/amplify-workflow/references/scaffolding.md
- Network accessline 12
git clone https://github.com/aws-samples/amplify-vite-react-template.git my-app - Dangerous shell operationline 13
cd my-app && rm -rf .git && git init - Network accessline 22
git clone https://github.com/aws-samples/amplify-next-template.git my-app - Dangerous shell operationline 23
cd my-app && rm -rf .git && git init - Network accessline 30
git clone https://github.com/aws-samples/amplify-next-pages-template.git my-app - Dangerous shell operationline 31
cd my-app && rm -rf .git && git init - Network accessline 38
git clone https://github.com/aws-samples/amplify-vue-template.git my-app - Dangerous shell operationline 39
cd my-app && rm -rf .git && git init - Network accessline 46
git clone https://github.com/aws-samples/amplify-angular-template.git my-app - Dangerous shell operationline 47
cd my-app && rm -rf .git && git init - Network accessline 131
`npm create amplify@latest -y` 2. Add the Swift package via Xcode: File → Add Package Dependencies → `https://github.com/aws-amplify/amplify-swift` (Up to Next Major Version). - Network accessline 132
2. Add the Swift package via Xcode: File → Add Package Dependencies → `https://github.com/aws-amplify/amplify-swift` (Up to Next Major Version). 3. Add `amplify_outputs.json` to the Xcode project (drag into navigator, - Network accessline 133
`https://github.com/aws-amplify/amplify-swift` (Up to Next Major Version). - Network accessline 190
- [React Quickstart](https://docs.amplify.aws/react/start/quickstart/) - Network accessline 191
- [Next.js Quickstart](https://docs.amplify.aws/nextjs/start/quickstart/) - Network accessline 192
- [Vue Quickstart](https://docs.amplify.aws/vue/start/quickstart/) - Network accessline 193
- [Angular Quickstart](https://docs.amplify.aws/angular/start/quickstart/) - Network accessline 194
- [React Native Quickstart](https://docs.amplify.aws/react-native/start/quickstart/) - Network accessline 195
- [Flutter Quickstart](https://docs.amplify.aws/flutter/start/quickstart/) - Network accessline 196
- [Swift Quickstart](https://docs.amplify.aws/swift/start/quickstart/) - Network accessline 197
- [Android Quickstart](https://docs.amplify.aws/android/start/quickstart/) - Network accessline 198
- [Manual Installation](https://docs.amplify.aws/react/start/manual-installation/) - Network accessline 199
- [Account Setup](https://docs.amplify.aws/react/start/account-setup/) - Network accessline 200
- [Sandbox Environments](https://docs.amplify.aws/react/deploy-and-host/sandbox-environments/setup/) - Network accessline 201
- [CLI Commands](https://docs.amplify.aws/react/reference/cli-commands/)
plugins/aws-amplify/skills/amplify-workflow/references/storage-backend.md
- Network accessline 120
- [Storage Overview](https://docs.amplify.aws/react/build-a-backend/storage/) - Network accessline 121
- [Set Up Storage](https://docs.amplify.aws/react/build-a-backend/storage/set-up-storage/) - Network accessline 122
- [Storage Authorization](https://docs.amplify.aws/react/build-a-backend/storage/authorization/) - Network accessline 123
- [Storage Event Triggers](https://docs.amplify.aws/react/build-a-backend/storage/lambda-triggers/)
plugins/aws-amplify/skills/amplify-workflow/references/storage-mobile.md
- Network accessline 158
- [Storage Overview (Android)](https://docs.amplify.aws/android/build-a-backend/storage/) - Network accessline 159
- [Set Up Storage (Android)](https://docs.amplify.aws/android/build-a-backend/storage/set-up-storage/) - [Upload Files (Android)](https://docs.amplify.aws/android/frontend/storage/upload-files/) - [Download Files (Android)](https://docs.amp - Network accessline 160
- [Upload Files (Android)](https://docs.amplify.aws/android/frontend/storage/upload-files/) - [Download Files (Android)](https://docs.amplify.aws/android/frontend/storage/download-files/) - [Storage Overview (Swift)](https://docs.amplify.aw - Network accessline 161
- [Download Files (Android)](https://docs.amplify.aws/android/frontend/storage/download-files/) - Network accessline 162
- [Storage Overview (Swift)](https://docs.amplify.aws/swift/build-a-backend/storage/) - Network accessline 163
- [Set Up Storage (Swift)](https://docs.amplify.aws/swift/build-a-backend/storage/set-up-storage/) - [Upload Files (Swift)](https://docs.amplify.aws/swift/frontend/storage/upload-files/) - [Download Files (Swift)](https://docs.amplify.aws/s - Network accessline 164
- [Upload Files (Swift)](https://docs.amplify.aws/swift/frontend/storage/upload-files/) - [Download Files (Swift)](https://docs.amplify.aws/swift/frontend/storage/download-files/) - [Storage Overview (Flutter)](https://docs.amplify.aws/flut - Network accessline 165
- [Download Files (Swift)](https://docs.amplify.aws/swift/frontend/storage/download-files/) - Network accessline 166
- [Storage Overview (Flutter)](https://docs.amplify.aws/flutter/build-a-backend/storage/) - Network accessline 167
- [Set Up Storage (Flutter)](https://docs.amplify.aws/flutter/build-a-backend/storage/set-up-storage/) - [Upload Files (Flutter)](https://docs.amplify.aws/flutter/frontend/storage/upload-files/) - [Download Files (Flutter)](https://docs.amp - Network accessline 168
- [Upload Files (Flutter)](https://docs.amplify.aws/flutter/frontend/storage/upload-files/) - Network accessline 169
- [Download Files (Flutter)](https://docs.amplify.aws/flutter/frontend/storage/download-files/)
plugins/aws-amplify/skills/amplify-workflow/references/storage-web.md
- Network accessline 57
- [Storage Overview (React)](https://docs.amplify.aws/react/build-a-backend/storage/) - Network accessline 58
- [Set Up Storage (React)](https://docs.amplify.aws/react/build-a-backend/storage/set-up-storage/) - [Upload Files (React)](https://docs.amplify.aws/react/frontend/storage/upload-files/) - [Download Files (React)](https://docs.amplify.aws/r - Network accessline 59
- [Upload Files (React)](https://docs.amplify.aws/react/frontend/storage/upload-files/) - [Download Files (React)](https://docs.amplify.aws/react/frontend/storage/download-files/) - [List Files (React)](https://docs.amplify.aws/react/fronte - Network accessline 60
- [Download Files (React)](https://docs.amplify.aws/react/frontend/storage/download-files/) - Network accessline 61
- [List Files (React)](https://docs.amplify.aws/react/frontend/storage/list-files/) - Network accessline 62
- [Remove Files (React)](https://docs.amplify.aws/react/frontend/storage/remove-files/) - Network accessline 63
- [Copy Files (React)](https://docs.amplify.aws/react/frontend/storage/copy-files/) - Network accessline 64
- [Storage Overview (Next.js)](https://docs.amplify.aws/nextjs/build-a-backend/storage/) - Network accessline 65
- [Storage Overview (React Native)](https://docs.amplify.aws/react-native/build-a-backend/storage/) - [Upload Files (React Native)](https://docs.amplify.aws/react-native/frontend/storage/upload-files/) - [Download Files (React Native)](http - Network accessline 66
- [Upload Files (React Native)](https://docs.amplify.aws/react-native/frontend/storage/upload-files/) - Network accessline 67
- [Download Files (React Native)](https://docs.amplify.aws/react-native/frontend/storage/download-files/)
plugins/aws-serverless/.claude-plugin/plugin.json
- Network accessline 4
}, "description": "Design, build, deploy, test, and debug serverless applications with AWS Serverless services.", "homepage": "https://github.com/awslabs/agent-plugins", - Network accessline 5
"description": "Design, build, deploy, test, and debug serverless applications with AWS Serverless services.", "homepage": "https://github.com/awslabs/agent-plugins", "keywords": [ - Network accessline 6
"homepage": "https://github.com/awslabs/agent-plugins", - Network accessline 22
"license": "Apache-2.0", "name": "aws-serverless", "repository": "https://github.com/awslabs/agent-plugins", - Network accessline 23
"name": "aws-serverless", "repository": "https://github.com/awslabs/agent-plugins", "version": "1.3.0" - Network accessline 24
"repository": "https://github.com/awslabs/agent-plugins",
plugins/aws-serverless/skills/api-gateway/SKILL.md
- Network accessline 193
See `references/service-limits.md` for the complete table. **Most numeric quotas below are default values and adjustable**; check with your AWS account team and the [latest quotas page](https://docs.aws.amazon.com/apigateway/latest/develope
plugins/aws-serverless/skills/api-gateway/references/custom-domains-routing.md
- Network accessline 13
- **Edge-optimized**: ACM-issued public certificate or certificate imported into ACM. Must be in us-east-1. Imported certificates must be [manually rotated before expiration](https://docs.aws.amazon.com/apigateway/latest/developerguide/how- - Network accessline 43
White-label domain support allows SaaS providers to serve multiple external customers through customer-specific subdomains (e.g., `customer1.example.com`, `customer2.example.com`) while routing all traffic through a single API Gateway API.
plugins/aws-serverless/skills/api-gateway/references/deployment.md
- Network accessline 10
- **Deploying to a Stage** = updating a stage to point to that snapshot - Multiple stages can point to the same or different deployments - **Console "Test Invoke" bypasses deployments**: it always uses the current API state (not a deployed - Network accessline 12
- **Console "Test Invoke" bypasses deployments**: it always uses the current API state (not a deployed snapshot). Bypasses IAM auth, Lambda authorizers, Cognito authorizers, API key validation, throttling, WAF, resource policies, and mTLS. - Network accessline 19
- **Always redeploy after**: changing resource policy, adding/modifying methods, updating integrations, configuring authorizers, modifying models or request validators - **No redeployment needed for**: throttling/usage plan changes, logging - Network accessline 20
- **No redeployment needed for**: throttling/usage plan changes, logging configuration, caching TTL (capacity changes take effect without redeployment but cause ~4 minutes of cache unavailability during resizing), stage variable values, cli - Network accessline 21
- Max 10 stages per API (adjustable via [Service Quotas](https://docs.aws.amazon.com/apigateway/latest/developerguide/limits.html)) - Network accessline 78
Based on the blog https://aws.amazon.com/blogs/compute/zero-downtime-blue-green-deployments-with-amazon-api-gateway/
plugins/aws-serverless/skills/api-gateway/references/observability-metrics-alarms.md
- Network accessline 121
- **REST API**: Active tracing supported; enable per stage. API Gateway creates the trace segment and adds trace headers to integration requests - **HTTP API**: X-Ray tracing is [not supported](https://docs.aws.amazon.com/apigateway/latest/ - Network accessline 122
- **HTTP API**: X-Ray tracing is [not supported](https://docs.aws.amazon.com/apigateway/latest/developerguide/http-api-vs-rest.html). For distributed tracing, enable X-Ray active tracing on downstream Lambda functions and correlate using th
plugins/aws-serverless/skills/api-gateway/references/performance-scaling.md
- Network accessline 7
**Note**: Throttling values below are **default quotas**; most are adjustable via AWS Support or Service Quotas console. Do not use defaults for capacity planning without checking your account's current limits. See [latest quotas](https://d
plugins/aws-serverless/skills/api-gateway/references/requirements-gathering.md
- Network accessline 75
- Backend services (Lambda, DynamoDB, RDS, ECS/EKS, on-premises)? - Direct AWS service integrations without Lambda? REST API supports any AWS service via VTL mapping templates (SQS, EventBridge, Step Functions, S3, DynamoDB, etc.). HTTP API - Network accessline 76
- Direct AWS service integrations without Lambda? REST API supports any AWS service via VTL mapping templates (SQS, EventBridge, Step Functions, S3, DynamoDB, etc.). HTTP API supports a subset via [first-class integrations](https://docs.aws
plugins/aws-serverless/skills/api-gateway/references/sam-cloudformation.md
- Network accessline 97
AllowMethods: "'GET,POST,OPTIONS'" AllowHeaders: "'Content-Type,Authorization'" AllowOrigin: "'https://example.com'" - Network accessline 98
AllowHeaders: "'Content-Type,Authorization'" AllowOrigin: "'https://example.com'" GatewayResponses: - Network accessline 99
AllowOrigin: "'https://example.com'" - Network accessline 102
ResponseParameters: Headers: Access-Control-Allow-Origin: "'https://example.com'" - Network accessline 103
Headers: Access-Control-Allow-Origin: "'https://example.com'" Access-Control-Allow-Headers: "'Content-Type,Authorization'" - Network accessline 104
Access-Control-Allow-Origin: "'https://example.com'" - Network accessline 107
ResponseParameters: Headers: Access-Control-Allow-Origin: "'https://example.com'" - Network accessline 108
Headers: Access-Control-Allow-Origin: "'https://example.com'" Access-Control-Allow-Headers: "'Content-Type,Authorization'" - Network accessline 109
Access-Control-Allow-Origin: "'https://example.com'" - Network accessline 148
# Based on https://github.com/aws-samples/serverless-samples/blob/main/apigw-header-routing/template-header-based-routing.yaml
plugins/aws-serverless/skills/api-gateway/references/sam-service-integrations.md
- Network accessline 20
Based on [aws-samples/serverless-patterns/apigw-rest-api-eventbridge-sam](https://github.com/aws-samples/serverless-patterns/tree/main/apigw-rest-api-eventbridge-sam). Supports batching multiple events via `#foreach`. - Network accessline 91
Based on [aws-samples/serverless-patterns/apigw-sqs-lambda-iot](https://github.com/aws-samples/serverless-patterns/tree/main/apigw-sqs-lambda-iot). Uses query protocol with `PassthroughBehavior: NEVER` to reject unmatched content types. - Network accessline 144
Full CRUD pattern based on [aws-samples/serverless-patterns](https://github.com/aws-samples/serverless-patterns/tree/main/apigw-dynamodb-lambda-scheduler-ses-auto-deletion-sam). Uses OpenAPI definition with `AWS::Include` for clean separati - Network accessline 445
Based on [aws-samples/serverless-patterns/apigw-kinesis-lambda](https://github.com/aws-samples/serverless-patterns/tree/main/apigw-kinesis-lambda). Uses REST API resources with path parameter for stream name and Lambda as stream consumer. - Network accessline 561
REST API pattern based on [aws-samples/serverless-patterns/apigw-rest-stepfunction](https://github.com/aws-samples/serverless-patterns/tree/main/apigw-rest-stepfunction). WebSocket pattern based on [aws-samples/serverless-samples/apigw-ws-i
plugins/aws-serverless/skills/api-gateway/references/service-integrations.md
- Network accessline 5
- **REST API and WebSocket API**: Use `Type: AWS` with VTL mapping templates for full request/response transformation. Supports any AWS service action. Both synchronous (wait for response) and asynchronous (fire-and-forget) patterns - **HTT - Network accessline 6
- **HTTP API**: Uses first-class integrations (`Type: AWS_PROXY` with `IntegrationSubtype`) and parameter mapping instead of VTL. Supported subtypes: `EventBridge-PutEvents`, `SQS-SendMessage`, `SQS-ReceiveMessage`, `SQS-DeleteMessage`, `SQ - Network accessline 12
Integrates directly with EventBridge PutEvents API (see [aws-samples/serverless-patterns/apigw-rest-api-eventbridge-sam](https://github.com/aws-samples/serverless-patterns/tree/main/apigw-rest-api-eventbridge-sam)). For a complete SAM templ - Network accessline 14
- Use `Type: AWS` integration with URI `arn:aws:apigateway:{region}:events:action/PutEvents` - Set required headers via `RequestParameters` (e.g., `integration.request.header.X-Amz-Target: "'AWSEvents.PutEvents'"`, `integration.request.head - Network accessline 15
- Set required headers via `RequestParameters` (e.g., `integration.request.header.X-Amz-Target: "'AWSEvents.PutEvents'"`, `integration.request.header.Content-Type: "'application/x-amz-json-1.1'"`). Alternative: set via VTL `$context.request - Network accessline 28
Integrates directly with SQS SendMessage API to decouple producers from consumers (see [aws-samples/serverless-patterns/apigw-sqs-lambda-iot](https://github.com/aws-samples/serverless-patterns/tree/main/apigw-sqs-lambda-iot)). For a complet - Network accessline 42
Integrates directly with SNS Publish API for fan-out to multiple subscribers (see [aws-samples/serverless-patterns/apigw-websocket-api-sns](https://github.com/aws-samples/serverless-patterns/tree/main/apigw-websocket-api-sns)): - Network accessline 61
- **Request template**: Maps request body/parameters to DynamoDB item attributes with type descriptors (`S`, `N`, `M`, `L`, etc.) - **Response template**: Extracts DynamoDB response attributes into clean JSON for the client using `$input. - Network accessline 62
- **Response template**: Extracts DynamoDB response attributes into clean JSON for the client using `$input.path('$.Item.attribute.S')` - **Full CRUD pattern** (see [aws-samples/serverless-patterns/apigw-dynamodb-lambda-scheduler-ses-auto-d - Network accessline 63
- **Full CRUD pattern** (see [aws-samples/serverless-patterns/apigw-dynamodb-lambda-scheduler-ses-auto-deletion-sam](https://github.com/aws-samples/serverless-patterns/tree/main/apigw-dynamodb-lambda-scheduler-ses-auto-deletion-sam)): - Network accessline 82
Integrates directly with Kinesis Data Streams PutRecord/PutRecords APIs for high-volume data ingestion (see [aws-samples/serverless-patterns/apigw-kinesis-lambda](https://github.com/aws-samples/serverless-patterns/tree/main/apigw-kinesis-la - Network accessline 101
**REST API → Step Functions** (see [aws-samples/serverless-patterns/apigw-rest-stepfunction](https://github.com/aws-samples/serverless-patterns/tree/main/apigw-rest-stepfunction)): - Network accessline 116
**WebSocket API → Step Functions** (see [aws-samples/serverless-samples/apigw-ws-integrations](https://github.com/aws-samples/serverless-samples/tree/main/apigw-ws-integrations)): - Network accessline 118
- Two execution modes via custom routes matched by `routeSelectionExpression`: - **Synchronous** (Express workflow): `action/StartSyncExecution`, which waits for workflow to complete and returns the result directly to the WebSocket client - Network accessline 119
- **Synchronous** (Express workflow): `action/StartSyncExecution`, which waits for workflow to complete and returns the result directly to the WebSocket client. **Constrained by the 29-second WebSocket API integration timeout**, not the 5-m - Network accessline 120
- **Asynchronous** (Standard workflow): `action/StartExecution`, which returns the execution ARN immediately. Workflow pushes results back to the WebSocket client via the `@connections` Management API (`POST https://{api-id}.execute-api.{re - Network accessline 134
Acts as an S3 proxy for file upload, download, and listing without Lambda (see [Developer Guide tutorial](https://docs.aws.amazon.com/apigateway/latest/developerguide/integrating-api-with-aws-services-s3.html)): - Network accessline 174
- **Request validation at the gateway**: Use API Gateway request validators (models) to reject invalid requests before they reach the backend service, reducing cost and protects downstream services - **Response mapping**: Transform raw AWS - Network accessline 175
- **Response mapping**: Transform raw AWS service responses into clean API responses using VTL response templates. Map HTTP status codes for error cases in `IntegrationResponses` - **Lambda invocations support sync and async**: API Gateway - Network accessline 176
- **Lambda invocations support sync and async**: API Gateway Lambda integrations default to synchronous invocation (wait for response). For asynchronous invocation (fire-and-forget, returns 200 immediately while Lambda processes in backgrou
plugins/aws-serverless/skills/api-gateway/references/service-limits.md
- Network accessline 3
**Important**: Values listed here are **default quotas**; many are adjustable via AWS Support or Service Quotas console. Do not use default values for architectural decisions without first checking with your AWS account team for current lim - Network accessline 79
These apply across all REST APIs, HTTP APIs, WebSocket APIs, and WebSocket callback APIs in a region ([shared quota](https://docs.aws.amazon.com/apigateway/latest/developerguide/limits.html)). Lower defaults apply in opt-in and newer region - Access to secretsline 120
[Credential-related source omitted]
plugins/aws-serverless/skills/api-gateway/references/troubleshooting.md
- Network accessline 27
1. Enable execution logging (REST/WebSocket only — [HTTP API supports access logging only](https://docs.aws.amazon.com/apigateway/latest/developerguide/set-up-logging.html)) AND access logging before troubleshooting 2. Use `x-amzn-requestid - Network accessline 81
- **Fix**: Remove stage name from URL path - Also occurs when: hitting nonexistent resource path, default endpoint disabled - **Note**: This 403 behavior is REST API specific. HTTP API returns **404 Not Found** for nonexistent paths ([Gatew - Network accessline 83
- **Note**: This 403 behavior is REST API specific. HTTP API returns **404 Not Found** for nonexistent paths ([Gateway response types](https://docs.aws.amazon.com/apigateway/latest/developerguide/api-gateway-gatewayResponse-definition.html) - Network accessline 92
- **Cause**: Authorizer returns IAM policy with path-specific resource ARN. When caching is enabled, that policy is reused for requests to different proxy paths, which are denied by the cached partial policy ([Configure Lambda authorizer ca - Network accessline 125
- **Cause**: Payload exceeds 10 MB limit (REST and HTTP API) ([API Gateway quotas](https://docs.aws.amazon.com/apigateway/latest/developerguide/limits.html)) - REQUEST_TOO_LARGE is the only gateway response that [cannot be customized](https - Network accessline 126
- REQUEST_TOO_LARGE is the only gateway response that [cannot be customized](https://docs.aws.amazon.com/apigateway/latest/developerguide/supported-gateway-response-types.html). Use `DEFAULT_4XX` as a catch-all to add CORS headers for all 4 - Network accessline 149
- **Cause**: Missing Lambda invoke permission when function referenced via stage variable - **Fix**: Add resource-based policy: `aws lambda add-permission --function-name <fn> --statement-id apigateway --action lambda:InvokeFunction --princ - Network accessline 150
- **Fix**: Add resource-based policy: `aws lambda add-permission --function-name <fn> --statement-id apigateway --action lambda:InvokeFunction --principal apigateway.amazonaws.com --source-arn <api-arn>` ([Lambda permissions for API Gateway - Network accessline 163
- **Cause**: Lambda authorizer returns invalid JSON, missing `principalId`, or policy exceeding ~8 KB. API Gateway returns **500** (not 401/403) — commonly mistaken for a backend issue ([Authorizer output format](https://docs.aws.amazon.com - Network accessline 179
- **Cause**: Lambda response not in required format - **REST API / payload format 1.0** ([response format](https://docs.aws.amazon.com/apigateway/latest/developerguide/set-up-lambda-proxy-integrations.html#api-gateway-simple-proxy-for-lambd - Network accessline 180
- **REST API / payload format 1.0** ([response format](https://docs.aws.amazon.com/apigateway/latest/developerguide/set-up-lambda-proxy-integrations.html#api-gateway-simple-proxy-for-lambda-output-format)): - Network accessline 191
- `statusCode` must be integer, `body` must be string, `headers` must be object - **HTTP API payload format 2.0** is more flexible ([response format](https://docs.aws.amazon.com/apigateway/latest/developerguide/http-api-develop-integrations - Network accessline 192
- **HTTP API payload format 2.0** is more flexible ([response format](https://docs.aws.amazon.com/apigateway/latest/developerguide/http-api-develop-integrations-lambda.html#http-api-develop-integrations-lambda.response)): `body` can be stri - Network accessline 206
- **30 seconds hard limit** (not increasable) - Returns HTTP 504 while Lambda continues ([Troubleshoot 504 errors](https://repost.aws/knowledge-center/api-gateway-504-errors)) - Network accessline 207
- Returns HTTP 504 while Lambda continues ([Troubleshoot 504 errors](https://repost.aws/knowledge-center/api-gateway-504-errors)) - Network accessline 211
1. Check `IntegrationLatency` metric for spikes 2. Use CloudWatch Logs Insights to identify slow requests 3. Enable [X-Ray tracing](https://docs.aws.amazon.com/apigateway/latest/developerguide/apigateway-xray.html) for detailed latency brea - Network accessline 213
3. Enable [X-Ray tracing](https://docs.aws.amazon.com/apigateway/latest/developerguide/apigateway-xray.html) for detailed latency breakdown (REST API only). For HTTP API, enable X-Ray in Lambda functions and correlate via `$context.integrat
plugins/aws-serverless/skills/api-gateway/references/websocket.md
- Network accessline 128
apigw = boto3.client( "apigatewaymanagementapi", endpoint_url=f"https://{domain_name}/{stage}" - Network accessline 129
"apigatewaymanagementapi", endpoint_url=f"https://{domain_name}/{stage}" ) - Network accessline 130
endpoint_url=f"https://{domain_name}/{stage}" - Network accessline 151
- **Route-level throttling**: Configure `ThrottlingBurstLimit` and `ThrottlingRateLimit` per route via stage `RouteSettings` to protect backend integrations from message floods. Cannot exceed account-level limit - Account-level throttle: 10 - Network accessline 153
- These are default quotas; check [latest limits](https://docs.aws.amazon.com/apigateway/latest/developerguide/limits.html) and request increases as needed - Network accessline 159
- The @connections callback API messages count toward message charges - No minimum fees or upfront commitments - See [API Gateway pricing](https://aws.amazon.com/api-gateway/pricing/) for current rates - Network accessline 161
- See [API Gateway pricing](https://aws.amazon.com/api-gateway/pricing/) for current rates
plugins/aws-serverless/skills/aws-lambda-durable-functions/SKILL.md
- Network accessline 201
- [AWS Lambda durable functions Documentation](https://docs.aws.amazon.com/lambda/latest/dg/durable-functions.html) - Network accessline 202
- [JavaScript SDK Repository](https://github.com/aws/aws-durable-execution-sdk-js) - Network accessline 203
- [Python SDK Repository](https://github.com/aws/aws-durable-execution-sdk-python) - Network accessline 204
- [IAM Policy Reference](https://docs.aws.amazon.com/aws-managed-policy/latest/reference/AWSLambdaBasicDurableExecutionRolePolicy.html)
plugins/aws-serverless/skills/aws-lambda-durable-functions/references/replay-model-rules.md
plugins/aws-serverless/skills/aws-lambda-durable-functions/references/step-operations.md
- Network accessline 290
// ✅ CORRECT: Use child context await context.runInChildContext('process', async (childCtx) => { const data = await childCtx.step('fetch', async () => fetch()); - Network accessline 291
await context.runInChildContext('process', async (childCtx) => { const data = await childCtx.step('fetch', async () => fetch()); await childCtx.wait({ seconds: 1 }); - Network accessline 292
const data = await childCtx.step('fetch', async () => fetch());
plugins/aws-serverless/skills/aws-lambda-durable-functions/references/troubleshooting-executions.md
- Network accessline 132
**[View this execution in the console](https://us-west-2.console.aws.amazon.com/lambda/home?region=us-west-2#/functions/my-function/versions/3/executions/abc-123/inv-456)** - Network accessline 135
https://us-west-2.console.aws.amazon.com/lambda/home?region=us-west-2#/functions/my-function/versions/3/executions/abc-123/inv-456 - Network accessline 162
**[View this execution in the console](https://us-east-1.console.aws.amazon.com/lambda/home?region=us-east-1#/functions/order-processor/versions/5/executions/def-456/inv-789)** - Network accessline 165
https://us-east-1.console.aws.amazon.com/lambda/home?region=us-east-1#/functions/order-processor/versions/5/executions/def-456/inv-789
plugins/aws-serverless/skills/aws-lambda-managed-instances/SKILL.md
- Network accessline 62
To check if Lambda Insights is enabled, look for a LambdaInsightsExtension layer on the function. To add it, find the latest layer ARN for your region from the [Lambda Insights documentation](https://docs.aws.amazon.com/AmazonCloudWatch/lat - Network accessline 101
For discount analysis (Savings Plans, Reserved Instances), refer users to the [AWS Pricing Calculator](https://calculator.aws/) and [references/cost-comparison.md](references/cost-comparison.md) for formulas and worked examples. Discount re - Network accessline 214
Check the [Lambda Managed Instances documentation](https://docs.aws.amazon.com/lambda/latest/dg/lambda-managed-instances.html) for the latest regional availability. - Network accessline 250
- [Lambda Managed Instances Docs](https://docs.aws.amazon.com/lambda/latest/dg/lambda-managed-instances.html) - Network accessline 251
- [Scaling LMI & Scheduled Scaling Docs](https://docs.aws.amazon.com/lambda/latest/dg/lambda-managed-instances-scaling.html) - Network accessline 252
- [Introducing LMI (AWS Blog)](https://aws.amazon.com/blogs/aws/introducing-aws-lambda-managed-instances-serverless-simplicity-with-ec2-flexibility/) - Network accessline 253
- [Build High-Performance Apps with LMI](https://aws.amazon.com/blogs/compute/build-high-performance-apps-with-aws-lambda-managed-instances/) - Network accessline 254
- [Migrating Functions to LMI (AWS Blog)](https://aws.amazon.com/blogs/compute/migrating-your-functions-to-aws-lambda-managed-instances/) - Network accessline 255
- [LMI Pricing Calculator](https://aws-samples.github.io/sample-aws-lambda-managed-instances/) - Network accessline 256
- [LMI Samples Repository](https://github.com/aws-samples/sample-aws-lambda-managed-instances) - Network accessline 257
- [AWS Lambda Pricing](https://aws.amazon.com/lambda/pricing/)
plugins/aws-serverless/skills/aws-lambda-managed-instances/references/configuration-guide.md
- Network accessline 56
For workloads with known traffic patterns (business hours, marketing events, batch windows), use [Amazon EventBridge Scheduler](https://docs.aws.amazon.com/scheduler/latest/UserGuide/managing-targets-universal.html) to adjust a function's `
plugins/aws-serverless/skills/aws-lambda-managed-instances/references/cost-comparison.md
- Network accessline 3
Use the [LMI Pricing Calculator](https://aws-samples.github.io/sample-aws-lambda-managed-instances/) for accurate, up-to-date cost comparisons based on your specific workload parameters (region, instance type, request volume, duration). - Network accessline 16
- [LMI Pricing Calculator](https://aws-samples.github.io/sample-aws-lambda-managed-instances/) — interactive comparison tool - Network accessline 17
- [AWS Pricing Calculator](https://calculator.aws/) — general AWS cost estimation
plugins/aws-serverless/skills/aws-lambda-managed-instances/references/infrastructure-setup.md
- Network accessline 229
For predictable traffic, adjust `MinExecutionEnvironments`/`MaxExecutionEnvironments` on a schedule using [Amazon EventBridge Scheduler](https://docs.aws.amazon.com/scheduler/latest/UserGuide/managing-targets-universal.html). The schedule c
plugins/aws-serverless/skills/aws-lambda-managed-instances/references/migration-patterns.md
- Access to secretsline 98
[Credential-related source omitted]
plugins/aws-serverless/skills/aws-lambda-managed-instances/references/thread-safety.md
- Access to secretsline 38
[Credential-related source omitted]
plugins/aws-serverless/skills/aws-lambda-managed-instances/scripts/setup-lmi.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/aws-serverless/skills/aws-lambda-microvms/SKILL.md
plugins/aws-serverless/skills/aws-lambda-microvms/references/getting-started.md
- Network accessline 203
curl "https://<microvm-endpoint>/" \
plugins/aws-serverless/skills/aws-lambda-microvms/references/iam-and-security.md
- Network accessline 91
http://169.254.169.254/latest/meta-data/iam/security-credentials/execution_role - Network accessline 152
VPC endpoints are supported for the `*.lambda-microvm.on.aws` domain (endpoint service: `com.amazonaws.<region>.lambda-microvm`) — clients in your VPC can reach MicroVM endpoints without traversing the public internet. Standard VPCE policy
plugins/aws-serverless/skills/aws-lambda-microvms/references/networking.md
plugins/aws-serverless/skills/aws-lambda/SKILL.md
- Network accessline 118
1. **Install SAM CLI**: Follow the [SAM CLI installation guide](https://docs.aws.amazon.com/serverless-application-model/latest/developerguide/install-sam-cli.html) - Network accessline 168
- [AWS SAM Documentation](https://docs.aws.amazon.com/serverless-application-model/) - Network accessline 169
- [AWS Lambda Documentation](https://docs.aws.amazon.com/lambda/) - Network accessline 170
- [AWS Lambda Powertools](https://docs.aws.amazon.com/powertools/) - Network accessline 171
- [AWS CDK Documentation](https://docs.aws.amazon.com/cdk/) - Network accessline 172
- [AWS Serverless MCP Server](https://github.com/awslabs/mcp/tree/main/src/aws-serverless-mcp-server)
plugins/aws-serverless/skills/aws-lambda/references/event-driven-architecture.md
- Access to secretsline 138
[Credential-related source omitted]
plugins/aws-serverless/skills/aws-lambda/references/event-sources.md
- Network accessline 151
schema_config = SchemaConfig(schema_type="AVRO", schema_registry_url="https://my-registry.example.com")
plugins/aws-serverless/skills/aws-lambda/references/observability.md
- Network accessline 201
Layer ARNs vary by runtime and architecture. Check the [ADOT Lambda layer documentation](https://aws-otel.github.io/docs/getting-started/lambda/) for the correct ARN for your runtime (Python, Node.js, Java, .NET) and architecture (amd64, ar - Network accessline 216
**Pricing:** Application Signals charges per service signal ingested. For low-traffic services the cost is negligible; for high-throughput services, review the [Application Signals pricing page](https://aws.amazon.com/cloudwatch/pricing/) a
plugins/aws-serverless/skills/aws-lambda/references/optimization.md
- Network accessline 26
[Lambda Power Tuning](https://github.com/alexcasalboni/aws-lambda-power-tuning) is an open-source Step Functions state machine that automates memory/cost optimization. It invokes your function at multiple memory settings, measures duration - Network accessline 47
sam init --location https://github.com/alexcasalboni/aws-lambda-power-tuning
plugins/aws-serverless/skills/aws-lambda/references/powertools.md
plugins/aws-serverless/skills/aws-lambda/references/web-app-deployment.md
- Network accessline 36
Cors: AllowOrigins: - "https://myapp.example.com" - Network accessline 38
- "https://myapp.example.com" - Network accessline 193
IdentitySource: $request.header.Authorization JwtConfiguration: issuer: !Sub "https://cognito-idp.${AWS::Region}.amazonaws.com/${MyCognitoUserPool}" - Network accessline 194
JwtConfiguration: issuer: !Sub "https://cognito-idp.${AWS::Region}.amazonaws.com/${MyCognitoUserPool}" audience: - Network accessline 195
issuer: !Sub "https://cognito-idp.${AWS::Region}.amazonaws.com/${MyCognitoUserPool}"
plugins/aws-serverless/skills/aws-serverless-deployment/SKILL.md
- Network accessline 107
- [AWS SAM Documentation](https://docs.aws.amazon.com/serverless-application-model/) - Network accessline 108
- [AWS CDK Documentation](https://docs.aws.amazon.com/cdk/) - Network accessline 109
- [AWS Serverless MCP Server](https://github.com/awslabs/mcp/tree/main/src/aws-serverless-mcp-server)
plugins/aws-serverless/skills/aws-serverless-deployment/references/cdk-serverless-patterns.md
- Network accessline 13
const api = new apigwv2.HttpApi(this, 'OrderApi', { corsPreflight: { allowOrigins: ['https://myapp.example.com'], - Network accessline 14
corsPreflight: { allowOrigins: ['https://myapp.example.com'], allowMethods: [apigwv2.CorsHttpMethod.GET, apigwv2.CorsHttpMethod.POST], - Network accessline 15
allowOrigins: ['https://myapp.example.com'], - Network accessline 37
invokeMode: lambda.InvokeMode.RESPONSE_STREAM, // for streaming cors: { allowedOrigins: ['https://myapp.example.com'], - Network accessline 38
cors: { allowedOrigins: ['https://myapp.example.com'], allowedMethods: [lambda.HttpMethod.POST], - Network accessline 39
allowedOrigins: ['https://myapp.example.com'],
plugins/aws-serverless/skills/aws-serverless-deployment/references/sam-project-setup.md
plugins/aws-serverless/skills/aws-step-functions/SKILL.md
plugins/aws-serverless/skills/aws-step-functions/examples/human-in-the-loop-with-timeout-escalation.asl.json
- Network accessline 7
"Resource": "arn:aws:states:::sqs:sendMessage.waitForTaskToken", "Arguments": { "QueueUrl": "https://sqs.us-east-1.amazonaws.com/123456789012/ApprovalQueue", - Network accessline 8
"Arguments": { "QueueUrl": "https://sqs.us-east-1.amazonaws.com/123456789012/ApprovalQueue", "MessageBody": "{% $string({'taskToken': $states.context.Task.Token, 'orderId': $states.input.orderId, 'approver': $states.input.pr - Network accessline 9
"QueueUrl": "https://sqs.us-east-1.amazonaws.com/123456789012/ApprovalQueue", - Network accessline 51
"Resource": "arn:aws:states:::sqs:sendMessage.waitForTaskToken", "Arguments": { "QueueUrl": "https://sqs.us-east-1.amazonaws.com/123456789012/ApprovalQueue", - Network accessline 52
"Arguments": { "QueueUrl": "https://sqs.us-east-1.amazonaws.com/123456789012/ApprovalQueue", "MessageBody": "{% $string({'taskToken': $states.context.Task.Token, 'orderId': $orderId, 'approver': $states.input.managerApprover - Network accessline 53
"QueueUrl": "https://sqs.us-east-1.amazonaws.com/123456789012/ApprovalQueue",
plugins/aws-serverless/skills/aws-step-functions/examples/polling-loop-wait-check-choice.asl.json
- Network accessline 7
"Resource": "arn:aws:states:::sqs:sendMessage", "Arguments": { "QueueUrl": "https://sqs.us-east-1.amazonaws.com/123456789012/FulfillmentQueue", - Network accessline 8
"Arguments": { "QueueUrl": "https://sqs.us-east-1.amazonaws.com/123456789012/FulfillmentQueue", "MessageBody": "{% $string({'orderId': $states.input.orderId, 'items': $states.input.items}) %}" - Network accessline 9
"QueueUrl": "https://sqs.us-east-1.amazonaws.com/123456789012/FulfillmentQueue",
plugins/aws-serverless/skills/aws-step-functions/references/service-integrations.md
- Network accessline 29
Always review the AWS Documentation to check availability and proper usage of an optimized integration before using it: https://docs.aws.amazon.com/step-functions/latest/dg/integrate-optimized.html - Network accessline 100
"Resource": "arn:aws:states:::sqs:sendMessage", "Arguments": { "QueueUrl": "https://sqs.us-east-1.amazonaws.com/123456789012/ProcessingQueue", - Network accessline 101
"Arguments": { "QueueUrl": "https://sqs.us-east-1.amazonaws.com/123456789012/ProcessingQueue", "MessageBody": "{% $string($states.input) %}" - Network accessline 102
"QueueUrl": "https://sqs.us-east-1.amazonaws.com/123456789012/ProcessingQueue", - Network accessline 114
"Resource": "arn:aws:states:::sqs:sendMessage.waitForTaskToken", "Arguments": { "QueueUrl": "https://sqs.us-east-1.amazonaws.com/123456789012/ApprovalQueue", - Network accessline 115
"Arguments": { "QueueUrl": "https://sqs.us-east-1.amazonaws.com/123456789012/ApprovalQueue", "MessageBody": "{% $string({'taskToken': $states.context.Task.Token, 'orderId': $orderId, 'amount': $states.input.amount}) %}" - Network accessline 116
"QueueUrl": "https://sqs.us-east-1.amazonaws.com/123456789012/ApprovalQueue", - Network accessline 190
"Resource": "arn:aws:states:::sqs:sendMessage.waitForTaskToken", "Arguments": { "QueueUrl": "https://sqs.us-east-1.amazonaws.com/123456789012/ApprovalQueue", - Network accessline 191
"Arguments": { "QueueUrl": "https://sqs.us-east-1.amazonaws.com/123456789012/ApprovalQueue", "MessageBody": "{% $string({'taskToken': $states.context.Task.Token, 'request': $states.input}) %}" - Network accessline 192
"QueueUrl": "https://sqs.us-east-1.amazonaws.com/123456789012/ApprovalQueue",
plugins/aws-serverless/skills/aws-step-functions/references/validation-and-testing.md
- Network accessline 5
Files saved with the `.asl.json` extension get automatic validation from the AWS Toolkit Extension. If the extension is not installed, suggest the user install it (https://open-vsx.org/extension/amazonwebservices/aws-toolkit-vscode). Use yo
plugins/aws-transform/.claude-plugin/plugin.json
- Network accessline 4
}, "description": "Migrate, modernize, and upgrade codebases to AWS. Transforms .NET Framework to .NET 8/10, mainframe COBOL to Java, VMware VMs to EC2, SQL Server to Aurora, and upgrades Java/Python/Node.js versions and AWS SDKs. AWS Tra - Network accessline 5
"description": "Migrate, modernize, and upgrade codebases to AWS. Transforms .NET Framework to .NET 8/10, mainframe COBOL to Java, VMware VMs to EC2, SQL Server to Aurora, and upgrades Java/Python/Node.js versions and AWS SDKs. AWS Transfor - Network accessline 6
"homepage": "https://github.com/awslabs/agent-plugins", - Network accessline 31
"license": "Apache-2.0", "name": "aws-transform", "repository": "https://github.com/awslabs/agent-plugins", - Network accessline 32
"name": "aws-transform", "repository": "https://github.com/awslabs/agent-plugins", "version": "1.9.0" - Network accessline 33
"repository": "https://github.com/awslabs/agent-plugins",
plugins/aws-transform/skills/aws-transform/SKILL.md
- Network accessline 45
> Note: this skill and the continuous modernization CLI, (`atx ct`), collect usage telemetry by default during transformation execution. The telemetry consists of different data points, such as, the IDE name (for example, VS Code or Kiro), - Network accessline 61
Classify failures before continuing: - If the shell reports `atx: command not found`, install the AWS Transform CLI: `curl -fsSL https://transform-cli.awsstatic.com/install.sh | bash`, then restart the shell or source its profile. - Dangerous shell operationline 62
- If the shell reports `atx: command not found`, install the AWS Transform CLI: `curl -fsSL https://transform-cli.awsstatic.com/install.sh | bash`, then restart the shell or source its profile. - Network accessline 62
- If the shell reports `atx: command not found`, install the AWS Transform CLI: `curl -fsSL https://transform-cli.awsstatic.com/install.sh | bash`, then restart the shell or source its profile. - Network accessline 69
INSTALLED=$(atx ct --version | head -1); LATEST=$(curl -fsSL "https://transform-cli.awsstatic.com/index.json" 2>/dev/null | grep -o '"latest"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/.*"latest"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/'); - Dangerous shell operationline 72
If `LATEST` is known and newer than `INSTALLED`, update with `curl -fsSL https://transform-cli.awsstatic.com/install.sh | bash`, then restart the shell or source its profile. - Network accessline 72
If `LATEST` is known and newer than `INSTALLED`, update with `curl -fsSL https://transform-cli.awsstatic.com/install.sh | bash`, then restart the shell or source its profile. - Instruction override signalline 91
8. Then use the appropriate continuous modernization skill — see [continuous-modernization](references/continuous-modernization.md). Recurring/scheduled intent ("weekly scan", "every Monday", "on a schedule", "cron") routes to [continuous-m - Network accessline 107
- For pricing: redirect to https://aws.amazon.com/ec2/pricing/, https://aws.amazon.com/transform/pricing/, etc. - Dangerous shell operationline 138
curl -fsSL https://transform-cli.awsstatic.com/install.sh | bash - Network accessline 138
curl -fsSL https://transform-cli.awsstatic.com/install.sh | bash
plugins/aws-transform/skills/aws-transform/references/auth.md
- Network accessline 16
[Credential-related source omitted] - Access to secretsline 16
[Credential-related source omitted] - Network accessline 17
- **SSO mode** — need `startUrl` (looks like `https://d-xxxxxxxxxx.awsapps.com/start`, from IAM Identity Center) and `idcRegion`. - Access to secretsline 41
[Credential-related source omitted] - Access to secretsline 43
[Credential-related source omitted]
plugins/aws-transform/skills/aws-transform/references/continuous-modernization-analysis.md
- Access to secretsline 262
[Credential-related source omitted]
plugins/aws-transform/skills/aws-transform/references/continuous-modernization-aws-managed-execution.md
- Network accessline 53
# Self-hosted GitLab or Bitbucket Data Center (add --url) atx ct source add --name <src> --provider gitlab|bitbucket --org <org> --token <token> \ --url https://gitlab.mycompany.com - Network accessline 54
atx ct source add --name <src> --provider gitlab|bitbucket --org <org> --token <token> --url https://gitlab.mycompany.com - Network accessline 55
--url https://gitlab.mycompany.com - Access to secretsline 105
[Credential-related source omitted]
plugins/aws-transform/skills/aws-transform/references/continuous-modernization-batch-execution.md
- Network accessline 47
Executor policy: [AWSTransformInfrastructureExecutorAccessBatch](https://code.amazon.com/packages/ATXControlTowerPolicies/blobs/mainline/--/managed-policies/draft/AWSTransformInfrastructureExecutorAccessBatch.json) + `AWSTransformCustomFull - Network accessline 61
# Self-hosted GitLab or Bitbucket Data Center (add --url) atx ct source add --name <src> --provider gitlab|bitbucket --org <org> --token <token> \ --url https://gitlab.mycompany.com - Network accessline 62
atx ct source add --name <src> --provider gitlab|bitbucket --org <org> --token <token> --url https://gitlab.mycompany.com - Network accessline 63
--url https://gitlab.mycompany.com
plugins/aws-transform/skills/aws-transform/references/continuous-modernization-ec2-execution.md
- Network accessline 47
Executor policy: [AWSTransformInfrastructureExecutorAccessEC2](https://code.amazon.com/packages/ATXControlTowerPolicies/blobs/mainline/--/managed-policies/draft/AWSTransformInfrastructureExecutorAccessEC2.json) + `AWSTransformCustomFullAcce - Network accessline 61
# Self-hosted GitLab or Bitbucket Data Center (add --url) atx ct source add --name <src> --provider gitlab|bitbucket --org <org> --token <token> \ --url https://gitlab.mycompany.com - Network accessline 62
atx ct source add --name <src> --provider gitlab|bitbucket --org <org> --token <token> --url https://gitlab.mycompany.com - Network accessline 63
--url https://gitlab.mycompany.com
plugins/aws-transform/skills/aws-transform/references/continuous-modernization-guide.md
- Network accessline 92
If the user doesn't have a Bitbucket token, explain: "For Bitbucket Cloud, go to https://id.atlassian.com/manage-profile/security/api-tokens and click 'Create API token with scopes'. Select these scopes: `read:repository:bitbucket`, `write:
plugins/aws-transform/skills/aws-transform/references/continuous-modernization-remediation.md
- Access to secretsline 189
[Credential-related source omitted]
plugins/aws-transform/skills/aws-transform/references/continuous-modernization-reporting.md
- Network accessline 96
"status": "succeeded|failed|...", // lowercase "transform_name": "...", "finding_id": "...", "execution_artifacts": { "pr_url": "https://..." }, - Network accessline 97
"transform_name": "...", "finding_id": "...", "execution_artifacts": { "pr_url": "https://..." }, "error": "..." } - Network accessline 98
"execution_artifacts": { "pr_url": "https://..." }, - Network accessline 162
- The `<title>` element and the main `<h1>` MUST both be exactly `AWS Transform - continuous modernization Report` — note "continuous modernization" is lowercase, "AWS Transform" stays capitalized. Do not paraphrase or substitute the produc - Network accessline 163
- Chart.js loaded via CDN: `<script src="https://cdn.jsdelivr.net/npm/chart.js@4"></script>` - Network accessline 164
- All CSS inlined in a `<style>` block - All data inlined as JS `const` declarations (`SOURCES`, `REPOSITORIES`, `ANALYSES`, `FINDINGS`, `REMEDIATIONS`) — JSON-stringified, then safe-escaped before embedding: replace `</` with `<\/` (a find - Network accessline 166
- No `fetch()` calls — the report must open offline - Dangerous shell operationline 183
rm -rf ~/.atxct/shared/reports/raw/<UNIX-TIMESTAMP>/
plugins/aws-transform/skills/aws-transform/references/continuous-modernization-security-agent.md
- Network accessline 33
> "This deploys the security agent infrastructure (IAM role, S3 bucket, agent space, CloudFormation stack). It requires admin/role-creation permissions. Run it with an admin identity. Read-only or runtime credentials are enough for everythi - Network accessline 35
> For reference, the executor policy this skill expects is in https://github.com/awslabs/agent-plugins/blob/main/plugins/aws-transform/skills/aws-transform/references/AWSTransformSecurityAgentExecutorAccess.json - Network accessline 38
# Ensure atx ct is installed and up to date INSTALLED=$(atx ct --version 2>/dev/null | head -1) LATEST=$(curl -fsSL "https://transform-cli.awsstatic.com/index.json" 2>/dev/null | grep -o '"latest"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/. - Network accessline 39
INSTALLED=$(atx ct --version 2>/dev/null | head -1) LATEST=$(curl -fsSL "https://transform-cli.awsstatic.com/index.json" 2>/dev/null | grep -o '"latest"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/.*"latest"[[:space:]]*:[[:space:]]*"\([^"]*\) - Network accessline 40
LATEST=$(curl -fsSL "https://transform-cli.awsstatic.com/index.json" 2>/dev/null | grep -o '"latest"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/.*"latest"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/') - Network accessline 43
# If not installed or outdated: curl -fsSL "https://transform-cli.awsstatic.com/install.sh" | bash - Dangerous shell operationline 44
curl -fsSL "https://transform-cli.awsstatic.com/install.sh" | bash - Network accessline 44
curl -fsSL "https://transform-cli.awsstatic.com/install.sh" | bash
plugins/aws-transform/skills/aws-transform/references/continuous-modernization-setup.md
- Dangerous shell operationline 25
curl -fsSL https://transform-cli.awsstatic.com/install.sh | bash - Network accessline 25
curl -fsSL https://transform-cli.awsstatic.com/install.sh | bash - Network accessline 33
INSTALLED=$(atx ct --version | head -1) LATEST=$(curl -fsSL "https://transform-cli.awsstatic.com/index.json" 2>/dev/null | grep -o '"latest"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/.*"latest"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/') - Network accessline 34
LATEST=$(curl -fsSL "https://transform-cli.awsstatic.com/index.json" 2>/dev/null | grep -o '"latest"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/.*"latest"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/') - Access to secretsline 79
[Credential-related source omitted] - Network accessline 93
- If `atx ct` is not installed, install it using the curl command above before proceeding. - Network accessline 94
- If `atx ct` is installed but a newer version is available, reinstall it using the same curl command.
plugins/aws-transform/skills/aws-transform/references/continuous-modernization-source.md
- Network accessline 45
# Add a GitLab group or user (self-hosted) # The GitLab PAT requires the `api` scope. read -s TOKEN && atx ct source add --name <name> --provider gitlab --org <group-or-username> --token "$TOKEN" --url https://gitlab.example.com [--tags key - Network accessline 47
read -s TOKEN && atx ct source add --name <name> --provider gitlab --org <group-or-username> --token "$TOKEN" --url https://gitlab.example.com [--tags key=value,key2=value2]; unset TOKEN - Network accessline 53
# Add a Bitbucket project (Data Center / self-hosted) # The Bitbucket PAT requires scopes: read:repository:bitbucket, read:account, write:repository:bitbucket, read:pullrequest:bitbucket, write:pullrequest:bitbucket read -s TOKEN && atx ct - Network accessline 55
read -s TOKEN && atx ct source add --name <name> --provider bitbucket --org <project-key> --token "$TOKEN" --url https://bitbucket.example.com [--tags key=value,key2=value2]; unset TOKEN - Network accessline 82
- **github**: Scans a GitHub organization or user for repositories. Requires a PAT or GitHub App. During remediation, pushes a branch and creates a Pull Request automatically — this includes **security** remediation, where the Security Agen - Network accessline 83
- **gitlab**: Scans a GitLab group or user for projects. Requires a PAT with `api` scope. Supports self-hosted instances via `--url` (required for self-hosted; omit for gitlab.com). During remediation, pushes a branch and creates a Merge Re - Network accessline 84
- **bitbucket**: Scans a Bitbucket workspace (Cloud) or project (Data Center) for repositories. Cloud requires an API token with scopes (created at https://id.atlassian.com/manage-profile/security/api-tokens → "Create API token with scopes" - Access to secretsline 172
[Credential-related source omitted] - Access to secretsline 174
[Credential-related source omitted]
plugins/aws-transform/skills/aws-transform/references/continuous-modernization.md
- Network accessline 121
INSTALLED=$(atx ct --version 2>/dev/null | head -1) LATEST=$(curl -fsSL "https://transform-cli.awsstatic.com/index.json" 2>/dev/null | grep -o '"latest"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/.*"latest"[[:space:]]*:[[:space:]]*"\([^"]*\) - Network accessline 122
LATEST=$(curl -fsSL "https://transform-cli.awsstatic.com/index.json" 2>/dev/null | grep -o '"latest"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/.*"latest"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/')
plugins/aws-transform/skills/aws-transform/references/custom-cli-reference.md
- Access to secretsline 87
[Credential-related source omitted] - Network accessline 91
git -C "$ATX_INFRA_DIR" pull -q else git clone -b atx-remote-infra --single-branch https://github.com/aws-samples/aws-transform-custom-samples.git "$ATX_INFRA_DIR" - Network accessline 92
else git clone -b atx-remote-infra --single-branch https://github.com/aws-samples/aws-transform-custom-samples.git "$ATX_INFRA_DIR" fi - Network accessline 93
git clone -b atx-remote-infra --single-branch https://github.com/aws-samples/aws-transform-custom-samples.git "$ATX_INFRA_DIR"
plugins/aws-transform/skills/aws-transform/references/custom-multi-transformation.md
- Access to secretsline 26
[Credential-related source omitted] - Access to secretsline 33
[Credential-related source omitted] - Access to secretsline 34
[Credential-related source omitted] - Access to secretsline 35
[Credential-related source omitted] - Access to secretsline 37
[Credential-related source omitted] - Dangerous shell operationline 59
- Java: `brew install --cask corretto23` (macOS), `sudo yum install java-23-amazon-corretto-devel` (RHEL/AL2), or `sudo apt install java-23-amazon-corretto-jdk` (Debian/Ubuntu) - Access to secretsline 85
[Credential-related source omitted] - Access to secretsline 86
[Credential-related source omitted] - Access to secretsline 91
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 94
[Credential-related source omitted] - Access to secretsline 95
[Credential-related source omitted] - Access to secretsline 100
[Credential-related source omitted] - Access to secretsline 106
[Credential-related source omitted] - Access to secretsline 114
[Credential-related source omitted] - Access to secretsline 116
[Credential-related source omitted] - Network accessline 190
REGION=${AWS_REGION:-${AWS_DEFAULT_REGION:-$(aws configure get region 2>/dev/null)}} REGION=${REGION:-us-east-1} echo "https://${REGION}.console.aws.amazon.com/cloudwatch/home#dashboards/dashboard/ATX-Transform-CLI-Dashboard" - Network accessline 192
echo "https://${REGION}.console.aws.amazon.com/cloudwatch/home#dashboards/dashboard/ATX-Transform-CLI-Dashboard" - Dangerous shell operationline 214
[Credential-related source omitted] - Access to secretsline 214
[Credential-related source omitted]
plugins/aws-transform/skills/aws-transform/references/custom-remote-execution.md
- Access to secretsline 142
[Credential-related source omitted] - Access to secretsline 153
[Credential-related source omitted] - Network accessline 157
git -C "$ATX_INFRA_DIR" pull -q else git clone -b atx-remote-infra --single-branch https://github.com/aws-samples/aws-transform-custom-samples.git "$ATX_INFRA_DIR" - Network accessline 158
else git clone -b atx-remote-infra --single-branch https://github.com/aws-samples/aws-transform-custom-samples.git "$ATX_INFRA_DIR" fi - Network accessline 159
git clone -b atx-remote-infra --single-branch https://github.com/aws-samples/aws-transform-custom-samples.git "$ATX_INFRA_DIR" - Access to secretsline 170
[Credential-related source omitted] - Access to secretsline 182
[Credential-related source omitted] - Network accessline 186
git -C "$ATX_INFRA_DIR" pull -q else git clone -b atx-remote-infra --single-branch https://github.com/aws-samples/aws-transform-custom-samples.git "$ATX_INFRA_DIR" - Network accessline 187
else git clone -b atx-remote-infra --single-branch https://github.com/aws-samples/aws-transform-custom-samples.git "$ATX_INFRA_DIR" fi - Network accessline 188
git clone -b atx-remote-infra --single-branch https://github.com/aws-samples/aws-transform-custom-samples.git "$ATX_INFRA_DIR" - Dangerous shell operationline 212
cd "$ATX_INFRA_DIR" && rm -f cdk.context.json && ./teardown.sh && ./setup.sh - Access to secretsline 296
[Credential-related source omitted] - Network accessline 434
REGION=${AWS_REGION:-${AWS_DEFAULT_REGION:-$(aws configure get region 2>/dev/null)}} REGION=${REGION:-us-east-1} echo "https://${REGION}.console.aws.amazon.com/cloudwatch/home#dashboards/dashboard/ATX-Transform-CLI-Dashboard" - Network accessline 436
echo "https://${REGION}.console.aws.amazon.com/cloudwatch/home#dashboards/dashboard/ATX-Transform-CLI-Dashboard" - Network accessline 455
# Example: Add Rust (install as atxuser so binaries land in /home/atxuser/.cargo) USER atxuser RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y - Network accessline 456
USER atxuser RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y USER root - Dangerous shell operationline 457
RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y - Network accessline 457
RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y - Network accessline 474
{ "path": "/home/atxuser/.config/pip/pip.conf", "content": "[global]\nindex-url = https://pypi.company.com/simple" - Network accessline 475
"path": "/home/atxuser/.config/pip/pip.conf", "content": "[global]\nindex-url = https://pypi.company.com/simple" }, - Network accessline 476
"content": "[global]\nindex-url = https://pypi.company.com/simple" - Access to secretsline 480
[Credential-related source omitted] - Network accessline 533
Do NOT quote specific prices or cost estimates to the user. If the user asks about pricing, direct them to: https://aws.amazon.com/transform/pricing/ - Network accessline 534
pricing, direct them to: https://aws.amazon.com/transform/pricing/ - Network accessline 549
> place for future transformations, or tear it down now. > > For pricing details: https://aws.amazon.com/transform/pricing/ - Network accessline 550
> > For pricing details: https://aws.amazon.com/transform/pricing/ > - Network accessline 551
> For pricing details: https://aws.amazon.com/transform/pricing/
plugins/aws-transform/skills/aws-transform/references/custom-results-synthesis.md
- Access to secretsline 7
[Credential-related source omitted] - Access to secretsline 10
[Credential-related source omitted] - Access to secretsline 50
[Credential-related source omitted] - Network accessline 56
REGION=${AWS_REGION:-${AWS_DEFAULT_REGION:-$(aws configure get region 2>/dev/null)}} REGION=${REGION:-us-east-1} echo "CloudWatch Dashboard: https://${REGION}.console.aws.amazon.com/cloudwatch/home#dashboards/dashboard/ATX-Transform-CLI-Das - Network accessline 58
echo "CloudWatch Dashboard: https://${REGION}.console.aws.amazon.com/cloudwatch/home#dashboards/dashboard/ATX-Transform-CLI-Dashboard"
plugins/aws-transform/skills/aws-transform/references/custom-single-transformation.md
- Dangerous shell operationline 36
- If not installed, ask the user for permission before installing (e.g., `brew install --cask corretto17` (macOS), `sudo yum install java-17-amazon-corretto-devel` (RHEL/AL2), or `sudo apt install java-17-amazon-corretto-jdk` (Debian/Ubuntu - Access to secretsline 46
[Credential-related source omitted] - Access to secretsline 53
[Credential-related source omitted] - Access to secretsline 54
[Credential-related source omitted] - Access to secretsline 88
[Credential-related source omitted] - Access to secretsline 89
[Credential-related source omitted] - Access to secretsline 94
[Credential-related source omitted] - Access to secretsline 96
[Credential-related source omitted] - Access to secretsline 97
[Credential-related source omitted] - Access to secretsline 98
[Credential-related source omitted] - Access to secretsline 99
[Credential-related source omitted] - Access to secretsline 105
[Credential-related source omitted] - Access to secretsline 113
[Credential-related source omitted] - Access to secretsline 120
[Credential-related source omitted] - Access to secretsline 129
[Credential-related source omitted] - Access to secretsline 143
[Credential-related source omitted] - Access to secretsline 176
[Credential-related source omitted] - Access to secretsline 182
[Credential-related source omitted] - Access to secretsline 189
[Credential-related source omitted] - Access to secretsline 238
[Credential-related source omitted] - Access to secretsline 239
[Credential-related source omitted] - Access to secretsline 240
[Credential-related source omitted] - Network accessline 303
REGION=${AWS_REGION:-${AWS_DEFAULT_REGION:-$(aws configure get region 2>/dev/null)}} REGION=${REGION:-us-east-1} echo "https://${REGION}.console.aws.amazon.com/cloudwatch/home#dashboards/dashboard/ATX-Transform-CLI-Dashboard" - Network accessline 305
echo "https://${REGION}.console.aws.amazon.com/cloudwatch/home#dashboards/dashboard/ATX-Transform-CLI-Dashboard" - Dangerous shell operationline 326
[Credential-related source omitted] - Access to secretsline 326
[Credential-related source omitted]
plugins/aws-transform/skills/aws-transform/references/custom-troubleshooting.md
- Network accessline 5
| Issue | Resolution - Network accessline 6
| ----------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- - Network accessline 7
| `atx` not found | Install: `curl -fsSL https://transform-cli.awsstatic.com/install.sh` piped to `bash` - Network accessline 58
- HTTPS URLs (`https://github.com/...`) need `atx/github-token` (PAT) - Access to secretsline 72
[Credential-related source omitted] - Access to secretsline 73
[Credential-related source omitted] - Access to secretsline 89
[Credential-related source omitted] - Access to secretsline 125
[Credential-related source omitted] - Network accessline 127
mv "$ATX_INFRA_DIR" "$ATX_INFRA_DIR.broken-$(date +%Y%m%d-%H%M%S)" fi git clone -b atx-remote-infra --single-branch https://github.com/aws-samples/aws-transform-custom-samples.git "$ATX_INFRA_DIR" - Network accessline 129
git clone -b atx-remote-infra --single-branch https://github.com/aws-samples/aws-transform-custom-samples.git "$ATX_INFRA_DIR"
plugins/aws-transform/skills/aws-transform/references/custom.md
- Network accessline 51
Run locally on a few repos for fast iteration, or at scale on hundreds of repos (up to 128 in-parallel). Note: this skill collects usage telemetry by default during transformation execution. The telemetry consists of different data points, - Dangerous shell operationline 121
- macOS: `brew install awscli` or `curl "https://awscli.amazonaws.com/AWSCLIV2.pkg" -o "AWSCLIV2.pkg" && sudo installer -pkg AWSCLIV2.pkg -target /` - Network accessline 121
- macOS: `brew install awscli` or `curl "https://awscli.amazonaws.com/AWSCLIV2.pkg" -o "AWSCLIV2.pkg" && sudo installer -pkg AWSCLIV2.pkg -target /` - Dangerous shell operationline 122
- Linux: `curl "https://awscli.amazonaws.com/awscli-exe-linux-x86_64.zip" -o "awscliv2.zip" && unzip awscliv2.zip && sudo ./aws/install` - Network accessline 122
- Linux: `curl "https://awscli.amazonaws.com/awscli-exe-linux-x86_64.zip" -o "awscliv2.zip" && unzip awscliv2.zip && sudo ./aws/install` - Access to secretsline 137
[Credential-related source omitted] - Access to secretsline 140
[Credential-related source omitted] - Access to secretsline 149
[Credential-related source omitted] - Access to secretsline 150
[Credential-related source omitted] - Access to secretsline 159
[Credential-related source omitted] - Network accessline 167
atx --version # Install: curl -fsSL https://transform-cli.awsstatic.com/install.sh | bash - Dangerous shell operationline 168
# Install: curl -fsSL https://transform-cli.awsstatic.com/install.sh | bash - Network accessline 168
# Install: curl -fsSL https://transform-cli.awsstatic.com/install.sh | bash - Network accessline 243
Only verify if user chooses remote mode. The infrastructure CDK scripts are fetched at runtime by cloning `https://github.com/aws-samples/aws-transform-custom-samples.git` (branch `atx-remote-infra`) — - Network accessline 244
at runtime by cloning `https://github.com/aws-samples/aws-transform-custom-samples.git` (branch `atx-remote-infra`) — - Network accessline 263
- **Local paths** — directories on the user's machine (e.g., `/home/user/my-project`) - **HTTPS git URLs** — public or private (e.g., `https://github.com/org/repo.git`) - Network accessline 264
- **HTTPS git URLs** — public or private (e.g., `https://github.com/org/repo.git`) - Access to secretsline 296
[Credential-related source omitted] - Access to secretsline 297
[Credential-related source omitted] - Access to secretsline 298
[Credential-related source omitted] - Access to secretsline 300
[Credential-related source omitted] - Network accessline 349
> > The PAT needs the `repo` scope for private repositories. Create one at > https://github.com/settings/tokens and then run: - Network accessline 350
> The PAT needs the `repo` scope for private repositories. Create one at > https://github.com/settings/tokens and then run: > - Network accessline 351
> https://github.com/settings/tokens and then run: - Access to secretsline 531
[Credential-related source omitted] - Access to secretsline 538
[Credential-related source omitted] - Network accessline 542
git -C "$ATX_INFRA_DIR" pull -q else git clone -b atx-remote-infra --single-branch https://github.com/aws-samples/aws-transform-custom-samples.git "$ATX_INFRA_DIR" - Network accessline 543
else git clone -b atx-remote-infra --single-branch https://github.com/aws-samples/aws-transform-custom-samples.git "$ATX_INFRA_DIR" fi - Network accessline 544
git clone -b atx-remote-infra --single-branch https://github.com/aws-samples/aws-transform-custom-samples.git "$ATX_INFRA_DIR" - Network accessline 562
# that dnf depends on, causing "No module named 'dnf'" errors. USER root RUN curl -fsSL "https://corretto.aws/downloads/latest/amazon-corretto-23-x64-linux-jdk.tar.gz" -o /tmp/corretto23.tar.gz && \ - Network accessline 563
USER root RUN curl -fsSL "https://corretto.aws/downloads/latest/amazon-corretto-23-x64-linux-jdk.tar.gz" -o /tmp/corretto23.tar.gz && \ mkdir -p /usr/lib/jvm && \ - Dangerous shell operationline 564
RUN curl -fsSL "https://corretto.aws/downloads/latest/amazon-corretto-23-x64-linux-jdk.tar.gz" -o /tmp/corretto23.tar.gz && mkdir -p /usr/lib/jvm && tar -xzf /tmp/corretto23.tar.gz -C /usr/lib/jvm && rm /tmp/corretto - Network accessline 564
RUN curl -fsSL "https://corretto.aws/downloads/latest/amazon-corretto-23-x64-linux-jdk.tar.gz" -o /tmp/corretto23.tar.gz && \ - Dangerous shell operationline 567
rm /tmp/corretto23.tar.gz && \ - Dangerous shell operationline 577
RUN eval "$(/home/atxuser/.pyenv/bin/pyenv init -)" && \ - Network accessline 587
# Go RUN curl -fsSL https://go.dev/dl/go1.22.0.linux-amd64.tar.gz | tar -C /usr/local -xz - Network accessline 588
RUN curl -fsSL https://go.dev/dl/go1.22.0.linux-amd64.tar.gz | tar -C /usr/local -xz - Network accessline 591
# Ruby (via rbenv — must run as atxuser) USER atxuser RUN git clone --depth 1 https://github.com/rbenv/rbenv.git /home/atxuser/.rbenv && \ - Network accessline 592
USER atxuser RUN git clone --depth 1 https://github.com/rbenv/rbenv.git /home/atxuser/.rbenv && \ git clone --depth 1 https://github.com/rbenv/ruby-build.git /home/atxuser/.rbenv/plugins/ruby-build && \ - Network accessline 593
RUN git clone --depth 1 https://github.com/rbenv/rbenv.git /home/atxuser/.rbenv && \ - Network accessline 594
git clone --depth 1 https://github.com/rbenv/ruby-build.git /home/atxuser/.rbenv/plugins/ruby-build && \ - Network accessline 600
# Rust USER atxuser RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y - Network accessline 601
USER atxuser RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y ENV PATH="/home/atxuser/.cargo/bin:$PATH" - Dangerous shell operationline 602
RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y - Network accessline 602
RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y - Dangerous shell operationline 672
- Java: `brew install --cask corretto23` (macOS), `sudo yum install java-23-amazon-corretto-devel` (RHEL/AL2), or `sudo apt install java-23-amazon-corretto-jdk` (Debian/Ubuntu) - Network accessline 757
immediately. Never retry a declined action or argue with the user's choice. 7. **No pricing claims** — Do not quote specific prices or cost estimates. If the user asks about pricing, direct them to: https://aws.amazon.com/transform/prici - Network accessline 758
7. **No pricing claims** — Do not quote specific prices or cost estimates. If the user asks about pricing, direct them to: https://aws.amazon.com/transform/pricing/ 8. **Scope commands to ATX resources only** — All AWS commands must targ - Network accessline 759
user asks about pricing, direct them to: https://aws.amazon.com/transform/pricing/ - Access to secretsline 811
[Credential-related source omitted] - Network accessline 831
https://github.com/awslabs/agent-plugins/issues
plugins/aws-transform/skills/aws-transform/references/mainframe-reimagine.md
- Dangerous shell operationline 108
rm <source-zip>.zip spec_gen_specs_<timestamp>.zip
plugins/aws-transform/skills/aws-transform/references/sql.md
- Dangerous shell operationline 108
- macOS/Linux: `execute_bash: cd <working_directory>/zip_staging && rm -f ../IDE_CONVERTED_DB_ARTIFACT.zip && zip ../IDE_CONVERTED_DB_ARTIFACT.zip *` - Dangerous shell operationline 111
- macOS/Linux/Git Bash: `execute_bash: rm -rf <working_directory>/zip_staging` - Network accessline 156
- **Cookie auth requires the Transform app URL** — Ask the user for their Transform app URL (e.g., `https://xxxxxxxx.transform.us-east-1.on.aws`). - Network accessline 157
- Do **not** use the SSO/IdC start URL (`https://d-xxx.awsapps.com/start`). - Dangerous shell operationline 605
- macOS/Linux: `execute_bash: cd <working_directory>/zip_staging && rm -f ../IDE_CONVERTED_DB_ARTIFACT.zip && zip ../IDE_CONVERTED_DB_ARTIFACT.zip *` - Dangerous shell operationline 608
- macOS/Linux/Git Bash: `execute_bash: rm -rf <working_directory>/zip_staging`
plugins/aws-transform/skills/aws-transform/references/vmware-network.md
- Instruction override signalline 94
After the user selects topology and security group strategy, the agent presents a configuration summary and asks for confirmation before starting the actual network mapping. Do NOT tell the user that mapping has started until the user confi
plugins/aws-transform/skills/aws-transform/references/vmware.md
- Network accessline 18
Migrate VMware environments to AWS using generative AI-driven planning and execution. AWS Transform orchestrates the full migration lifecycle — discovery, migration planning, landing zone setup, network migration, and server rehosting to EC
plugins/aws-transform/skills/aws-transform/references/workflow.md
- Access to secretsline 327
[Credential-related source omitted]
plugins/aws-transform/skills/aws-transform/scripts/verify-traceability.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/codebase-documentor-for-aws/.claude-plugin/plugin.json
- Network accessline 4
}, "description": "Analyze codebases to generate structured technical documentation with source-of-truth citations. Optimized for AWS workloads using CDK, CloudFormation, and Terraform.", "homepage": "https://github.com/awslabs/agent-pl - Network accessline 5
"description": "Analyze codebases to generate structured technical documentation with source-of-truth citations. Optimized for AWS workloads using CDK, CloudFormation, and Terraform.", "homepage": "https://github.com/awslabs/agent-plugins - Network accessline 6
"homepage": "https://github.com/awslabs/agent-plugins", - Network accessline 20
"license": "Apache-2.0", "name": "codebase-documentor-for-aws", "repository": "https://github.com/awslabs/agent-plugins", - Network accessline 21
"name": "codebase-documentor-for-aws", "repository": "https://github.com/awslabs/agent-plugins", "version": "1.0.0" - Network accessline 22
"repository": "https://github.com/awslabs/agent-plugins",
plugins/codebase-documentor-for-aws/skills/document-service/references/framework-patterns.md
- Access to secretsline 158
[Credential-related source omitted]
plugins/databases-on-aws/.claude-plugin/plugin.json
- Network accessline 4
}, "description": "Expert database guidance for the AWS database portfolio. Design schemas, execute queries, handle migrations, and choose the right database for your workload.", "homepage": "https://github.com/awslabs/agent-plugins", - Network accessline 5
"description": "Expert database guidance for the AWS database portfolio. Design schemas, execute queries, handle migrations, and choose the right database for your workload.", "homepage": "https://github.com/awslabs/agent-plugins", "key - Network accessline 6
"homepage": "https://github.com/awslabs/agent-plugins", - Network accessline 22
"license": "Apache-2.0", "name": "databases-on-aws", "repository": "https://github.com/awslabs/agent-plugins", - Network accessline 23
"name": "databases-on-aws", "repository": "https://github.com/awslabs/agent-plugins", "version": "1.10.0" - Network accessline 24
"repository": "https://github.com/awslabs/agent-plugins",
plugins/databases-on-aws/scripts/psql-connect.sh
plugins/databases-on-aws/skills/dsql/SKILL.md
- Network accessline 164
**Fallback:** If `awsknowledge` is unavailable, use the defaults above and flag that limits should be verified against [DSQL documentation](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/). - Network accessline 289
- **`awsknowledge` returns no results:** Use the default limits in the table above and note that limits should be verified against [DSQL documentation](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/). - Network accessline 298
- [Aurora DSQL Documentation](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/) - Network accessline 299
- [Code Samples Repository](https://github.com/aws-samples/aurora-dsql-samples)
plugins/databases-on-aws/skills/dsql/mcp/mcp-setup.md
- Network accessline 48
- Install from: [Astral](https://docs.astral.sh/uv/getting-started/installation/) - Network accessline 181
- [MCP Server Setup Guide](https://awslabs.github.io/mcp/servers/aurora-dsql-mcp-server) - Network accessline 182
- [DSQL MCP User Guide](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/SECTION_aurora-dsql-mcp-server.html)
plugins/databases-on-aws/skills/dsql/mcp/mcp-tools.md
- Network accessline 47
- [Aurora DSQL MCP Server Documentation](https://awslabs.github.io/mcp/servers/aurora-dsql-mcp-server) - Network accessline 48
- [Aurora DSQL MCP Server README](https://github.com/awslabs/mcp/tree/main/src/aurora-dsql-mcp-server) - Network accessline 49
- [Aurora DSQL Documentation](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/)
plugins/databases-on-aws/skills/dsql/mcp/tools/database-tools.md
- Network accessline 123
- **MUST** build every statement with [`safe_query.build()`](safe_query.py). Write mode disables all server-side injection filters ([`server.py:295-318`](https://github.com/awslabs/mcp/blob/main/src/aurora-dsql-mcp-server/awslabs/aurora - Network accessline 124
Write mode disables all server-side injection filters ([`server.py:295-318`](https://github.com/awslabs/mcp/blob/main/src/aurora-dsql-mcp-server/awslabs/aurora_dsql_mcp_server/server.py#L295-L318)) — skill-level validation is the only d - Network accessline 125
([`server.py:295-318`](https://github.com/awslabs/mcp/blob/main/src/aurora-dsql-mcp-server/awslabs/aurora_dsql_mcp_server/server.py#L295-L318)) —
plugins/databases-on-aws/skills/dsql/mcp/tools/documentation-tools.md
- Network accessline 42
url = "https://docs.aws.amazon.com/aurora-dsql/latest/userguide/..."
plugins/databases-on-aws/skills/dsql/mcp/tools/input-validation.md
- Network accessline 55
- `readonly_query` and `transact` accept only SQL strings — no parameter binding ([`server.py:141-142, 267-272`](https://github.com/awslabs/mcp/blob/main/src/aurora-dsql-mcp-server/awslabs/aurora_dsql_mcp_server/server.py#L141)). - Network accessline 56
binding ([`server.py:141-142, 267-272`](https://github.com/awslabs/mcp/blob/main/src/aurora-dsql-mcp-server/awslabs/aurora_dsql_mcp_server/server.py#L141)). - Network accessline 59
subquery exfiltration and non-equality boolean injection. - Write mode disables those filters entirely ([`server.py:295-318`](https://github.com/awslabs/mcp/blob/main/src/aurora-dsql-mcp-server/awslabs/aurora_dsql_mcp_server/server.py#L29 - Network accessline 60
- Write mode disables those filters entirely ([`server.py:295-318`](https://github.com/awslabs/mcp/blob/main/src/aurora-dsql-mcp-server/awslabs/aurora_dsql_mcp_server/server.py#L295-L318)). Skill-level validation is the only defense. - Network accessline 61
([`server.py:295-318`](https://github.com/awslabs/mcp/blob/main/src/aurora-dsql-mcp-server/awslabs/aurora_dsql_mcp_server/server.py#L295-L318)).
plugins/databases-on-aws/skills/dsql/mcp/tools/safe_query.py
- Executable scriptline 1
Executable file
plugins/databases-on-aws/skills/dsql/references/access-control.md
- Network accessline 161
- [Using Database and IAM Roles](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/using-database-and-iam-roles.html) - Network accessline 162
- [PostgreSQL GRANT](https://www.postgresql.org/docs/current/sql-grant.html) - Network accessline 163
- [PostgreSQL Privileges](https://www.postgresql.org/docs/current/ddl-priv.html)
plugins/databases-on-aws/skills/dsql/references/auth/authentication-guide.md
- Network accessline 83
Aurora DSQL uses the [PostgreSQL wire protocol](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-postgresql-compatibility.html) and enforces SSL: - Network accessline 153
- [IAM Authentication Guide (AWS documentation)](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/using-database-and-iam-roles.html)
plugins/databases-on-aws/skills/dsql/references/auth/connectivity-tools.md
- Network accessline 9
DSQL has many tools for connecting including 12 database drivers, 4 ORM libraries, and 4 specialized adapters across various languages as listed in the [programming guide](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/aws-sdks.ht - Network accessline 10
across various languages as listed in the [programming guide](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/aws-sdks.html). PREFER using connectors, drivers, ORM libraries, and adapters. - Network accessline 16
| Programming Language | Driver | Sample Repository | | -------------------- | -------------------------------- | --------- - Network accessline 17
| -------------------- | -------------------------------- | ------------------------------------------------------------------------------------------------------------ | | **C++** | libpq | [C++ libp - Network accessline 18
| **C++** | libpq | [C++ libpq samples](https://github.com/aws-samples/aurora-dsql-samples/tree/main/cpp/libpq) | - Network accessline 19
| **C# (.NET)** | Npgsql | [.NET Npgsql samples](https://github.com/aws-samples/aurora-dsql-samples/tree/main/dotnet/npgsql) | - Network accessline 20
| **Go** | pgx | [Go pgx samples](https://github.com/aws-samples/aurora-dsql-samples/tree/main/go/pgx) | - Network accessline 21
| **Java** | pgJDBC | [Java pgJDBC samples](https://github.com/aws-samples/aurora-dsql-samples/tree/main/java/pgjdbc) | - Network accessline 22
| **Java** | DSQL Connector for JDBC | JDBC samples | | **JavaScript** | DSQL Connector for node-postgres | [Node.js - Network accessline 23
| **JavaScript** | DSQL Connector for node-postgres | [Node.js samples](https://github.com/aws-samples/aurora-dsql-samples/tree/main/javascript/node-postgres) | - Network accessline 24
| **JavaScript** | DSQL Connector for Postgres.js | [Postgres.js samples](https://github.com/aws-samples/aurora-dsql-samples/tree/main/javascript/postgres-js) | - Network accessline 25
| **Python** | Psycopg | [Python Psycopg samples](https://github.com/aws-samples/aurora-dsql-samples/tree/main/python/psycopg) | - Network accessline 26
| **Python** | DSQL Connector for Psycopg2 | [Python Psycopg2 samples](https://github.com/aws-samples/aurora-dsql-samples/tree/main/python/psycopg2) | - Network accessline 27
| **Python** | DSQL Connector for Asyncpg | [Python Asyncpg samples](https://github.com/awslabs/aurora-dsql-python-connector/tree/main/examples/asyncpg) | - Network accessline 28
| **Ruby** | pg | [Ruby pg samples](https://github.com/aws-samples/aurora-dsql-samples/tree/main/ruby/ruby-pg) | - Network accessline 29
| **Rust** | SQLx | [Rust SQLx samples](https://github.com/aws-samples/aurora-dsql-samples/tree/main/rust/sqlx) | - Network accessline 35
| Programming Language | ORM Library | Sample Repository | | -------------------- | ----------- | ---------------------------------------------- - Network accessline 36
| -------------------- | ----------- | ----------------------------------------------------------------------------------------------------------------- | | **Java** | Hibernate | [Hibernate Pet Clinic App](https://github.com/ - Network accessline 37
| **Java** | Hibernate | [Hibernate Pet Clinic App](https://github.com/awslabs/aurora-dsql-hibernate/tree/main/examples/pet-clinic-app) | - Network accessline 38
| **Python** | SQLAlchemy | [SQLAlchemy Pet Clinic App](https://github.com/awslabs/aurora-dsql-sqlalchemy/tree/main/examples/pet-clinic-app) | - Network accessline 39
| **TypeScript** | Sequelize | [TypeScript Sequelize samples](https://github.com/aws-samples/aurora-dsql-samples/tree/main/typescript/sequelize) | - Network accessline 40
| **TypeScript** | TypeORM | [TypeScript TypeORM samples](https://github.com/aws-samples/aurora-dsql-samples/tree/main/typescript/type-orm) | - Network accessline 46
| Programming Language | ORM/Framework | Repository | | -------------------- | ------------- | -------------------------------------------------------- - Network accessline 47
| -------------------- | ------------- | --------------------------------------------------------------------------------------------------- | | **C# (.NET)** | EF Core | [Aurora DSQL EF Core Adapter](https://github.com/awslabs - Network accessline 48
| **C# (.NET)** | EF Core | [Aurora DSQL EF Core Adapter](https://github.com/awslabs/aurora-dsql-orms/tree/main/dotnet/ef-core) | - Network accessline 49
| **Java** | Hibernate | [Aurora DSQL Hibernate Adapter](https://github.com/awslabs/aurora-dsql-hibernate/) | - Network accessline 50
| **Python** | Django | [Aurora DSQL Django Adapter](https://github.com/awslabs/aurora-dsql-django/) | - Network accessline 51
| **Python** | SQLAlchemy | [Aurora DSQL SQLAlchemy Adapter](https://github.com/awslabs/aurora-dsql-sqlalchemy/) | - Network accessline 101
The [DSQL Loader](https://github.com/aws-samples/aurora-dsql-loader) is a fast parallel data loader for DSQL that supports
plugins/databases-on-aws/skills/dsql/references/auth/scaling-guide.md
- Network accessline 27
Hot keys (frequently accessed rows) create bottlenecks. For detailed analysis, see ["How to avoid hot keys in Aurora DSQL"](https://marc-bowes.com/dsql-avoid-hot-keys.html).
plugins/databases-on-aws/skills/dsql/references/data-loading.md
- Network accessline 5
The [DSQL Loader](https://github.com/aws-samples/aurora-dsql-loader) (`aurora-dsql-loader`) - Network accessline 24
DSQL tables start on a single partition and auto-split under sustained write heat. Fresh tables absorb a few thousand rec/s regardless of client concurrency — this is normal, not a problem to fix. Throughput accelerates as partitions split.
plugins/databases-on-aws/skills/dsql/references/development-guide.md
- Network accessline 57
- MUST verify column types via `awsknowledge`: `aurora dsql supported data types` or the [DSQL supported data types list](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-postgresql-compatibility-supported-data-types.ht - Network accessline 147
**MUST verify** column types against the [DSQL supported data types docs](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-postgresql-compatibility-supported-data-types.html) or via `awsknowledge`: `aurora dsql supporte - Network accessline 149
Arrays and `INET` are **[runtime-only](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-postgresql-compatibility-supported-data-types.html#working-with-postgresql-compatibility-query-runtime)** — cast at query time. For
plugins/databases-on-aws/skills/dsql/references/dsql-examples.md
- Network accessline 9
For additional samples, including in alternative language and driver support, refer to the official [aurora-dsql-samples](https://github.com/aws-samples/aurora-dsql-samples). - Network accessline 10
[aurora-dsql-samples](https://github.com/aws-samples/aurora-dsql-samples). - Network accessline 27
- **Language Guide:** [language.md](./language.md) - **Onboarding Guide:** [onboarding.md](./onboarding.md) - **AWS Documentation:** [DSQL User Guide](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/) - Network accessline 28
- **Onboarding Guide:** [onboarding.md](./onboarding.md) - **AWS Documentation:** [DSQL User Guide](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/) - **Sample Code:** [aurora-dsql-samples](https://github.com/aws-samples/aurora-ds - Network accessline 29
- **AWS Documentation:** [DSQL User Guide](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/) - Network accessline 30
- **Sample Code:** [aurora-dsql-samples](https://github.com/aws-samples/aurora-dsql-samples)
plugins/databases-on-aws/skills/dsql/references/examples/connection.md
- Network accessline 34
Source: [aurora-dsql-samples/javascript](https://github.com/aws-samples/aurora-dsql-samples/tree/main/javascript) - Network accessline 64
For custom drivers or languages without DSQL Connector. Source: [aurora-dsql-samples/javascript/authentication](https://github.com/aws-samples/aurora-dsql-samples/tree/main/javascript/authentication)
plugins/databases-on-aws/skills/dsql/references/examples/data-operations.md
plugins/databases-on-aws/skills/dsql/references/examples/migrations.md
- Network accessline 11
Source: Adapted from [aurora-dsql-samples/java/liquibase](https://github.com/aws-samples/aurora-dsql-samples/tree/main/java/liquibase)
plugins/databases-on-aws/skills/dsql/references/examples/patterns.md
- Network accessline 104
Arrays and `INET` are [runtime-only](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-postgresql-compatibility-supported-data-types.html#working-with-postgresql-compatibility-query-runtime) — not valid as column types.
plugins/databases-on-aws/skills/dsql/references/examples/schema.md
- Network accessline 9
SHOULD use UUIDs with `gen_random_uuid()` for distributed write performance. Source: [aurora-dsql-samples/java/liquibase](https://github.com/aws-samples/aurora-dsql-samples/tree/main/java/liquibase) - Network accessline 35
MUST use `CREATE INDEX ASYNC` (max 24 indexes/table including the primary key, 8 columns/index — verify via `awsknowledge`: `aurora dsql index limits`). Source: [aurora-dsql-samples/java/liquibase](https://github.com/aws-samples/aurora-dsql
plugins/databases-on-aws/skills/dsql/references/foreign-keys.md
- Network accessline 137
- [Working with foreign key constraints](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-foreign-key-constraints.html) - Network accessline 138
- [CREATE TABLE foreign key syntax](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/create-table-syntax-support.html#create-table-foreign-keys) - Network accessline 139
- [SET CONSTRAINTS](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/set-constraints-syntax-support.html)
plugins/databases-on-aws/skills/dsql/references/language.md
- Network accessline 5
- ALWAYS prefer DSQL Connector when available - MUST follow patterns outlined in [aurora-dsql-samples](https://github.com/aws-samples/aurora-dsql-samples/tree/main/) - Network accessline 6
- MUST follow patterns outlined in [aurora-dsql-samples](https://github.com/aws-samples/aurora-dsql-samples/tree/main/) - Network accessline 50
PREFER using the [DSQL Python Connector](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/SECTION_program-with-dsql-connector-for-python.html) for automatic IAM Auth: - Network accessline 54
- modern async/sync - `import aurora_dsql_psycopg as dsql` - [DSQL psycopg preferred example](https://github.com/aws-samples/aurora-dsql-samples/blob/main/python/psycopg/src/example_preferred.py) - Network accessline 55
- `import aurora_dsql_psycopg as dsql` - [DSQL psycopg preferred example](https://github.com/aws-samples/aurora-dsql-samples/blob/main/python/psycopg/src/example_preferred.py) - See [aurora-dsql-samples/python/psycopg](https://githu - Network accessline 56
- [DSQL psycopg preferred example](https://github.com/aws-samples/aurora-dsql-samples/blob/main/python/psycopg/src/example_preferred.py) - Network accessline 57
- See [aurora-dsql-samples/python/psycopg](https://github.com/aws-samples/aurora-dsql-samples/tree/main/python/psycopg) - Network accessline 59
- synchronous - `import aurora_dsql_psycopg2 as dsql` - [DSQL psycopg2 preferred example](https://github.com/aws-samples/aurora-dsql-samples/blob/main/python/psycopg2/src/example_preferred.py) - Network accessline 60
- `import aurora_dsql_psycopg2 as dsql` - [DSQL psycopg2 preferred example](https://github.com/aws-samples/aurora-dsql-samples/blob/main/python/psycopg2/src/example_preferred.py) - See [aurora-dsql-samples/python/psycopg2](https://g - Network accessline 61
- [DSQL psycopg2 preferred example](https://github.com/aws-samples/aurora-dsql-samples/blob/main/python/psycopg2/src/example_preferred.py) - Network accessline 62
- See [aurora-dsql-samples/python/psycopg2](https://github.com/aws-samples/aurora-dsql-samples/tree/main/python/psycopg2) - Network accessline 64
- full asynchronous style - `import aurora_dsql_asyncpg as dsql` - [DSQL asyncpg preferred example](https://github.com/aws-samples/aurora-dsql-samples/blob/main/python/asyncpg/src/example_preferred.py) - Network accessline 65
- `import aurora_dsql_asyncpg as dsql` - [DSQL asyncpg preferred example](https://github.com/aws-samples/aurora-dsql-samples/blob/main/python/asyncpg/src/example_preferred.py) - See [aurora-dsql-samples/python/asyncpg](https://githu - Network accessline 66
- [DSQL asyncpg preferred example](https://github.com/aws-samples/aurora-dsql-samples/blob/main/python/asyncpg/src/example_preferred.py) - Network accessline 67
- See [aurora-dsql-samples/python/asyncpg](https://github.com/aws-samples/aurora-dsql-samples/tree/main/python/asyncpg) - Network accessline 71
- Supports `psycopg` and `psycopg2` - See [aurora-dsql-samples/python/sqlalchemy](https://github.com/aws-samples/aurora-dsql-samples/tree/main/python/sqlalchemy) - Network accessline 72
- See [aurora-dsql-samples/python/sqlalchemy](https://github.com/aws-samples/aurora-dsql-samples/tree/main/python/sqlalchemy) - Network accessline 73
- Dialect Source: [aurora-dsql-sqlalchemy](https://github.com/awslabs/aurora-dsql-sqlalchemy/tree/main/) - Network accessline 79
- Options for Local or using Amazon SageMaker - REQUIRES downloading the Amazon root certificate from the official trust store - See [aurora-dsql-samples/python/jupyter](https://github.com/aws-samples/aurora-dsql-samples/blob/main/python/ju - Network accessline 81
- See [aurora-dsql-samples/python/jupyter](https://github.com/aws-samples/aurora-dsql-samples/blob/main/python/jupyter/) - Network accessline 85
PREFER using the [DSQL Go Connector](https://github.com/awslabs/aurora-dsql-connectors/tree/main/go/pgx) for automatic IAM auth: - Network accessline 87
- **pgx** (recommended) - Use `aurora-dsql-connectors/go/pgx/dsql` for automatic IAM auth with token caching - [DSQL pgx preferred example](https://github.com/aws-samples/aurora-dsql-samples/blob/main/go/pgx/src/example_preferred.go) - Network accessline 88
- Use `aurora-dsql-connectors/go/pgx/dsql` for automatic IAM auth with token caching - [DSQL pgx preferred example](https://github.com/aws-samples/aurora-dsql-samples/blob/main/go/pgx/src/example_preferred.go) - Connector: [aurora-dsql- - Network accessline 89
- [DSQL pgx preferred example](https://github.com/aws-samples/aurora-dsql-samples/blob/main/go/pgx/src/example_preferred.go) - Network accessline 90
- Connector: [aurora-dsql-connectors/go/pgx](https://github.com/awslabs/aurora-dsql-connectors/tree/main/go/pgx) - Network accessline 91
- See [aurora-dsql-samples/go/pgx](https://github.com/aws-samples/aurora-dsql-samples/tree/main/go/pgx) - Network accessline 95
PREFER using one of the DSQL Node.js Connectors: [node-postgres](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/SECTION_program-with-dsql-connector-for-node-postgres.html) - Network accessline 96
[node-postgres](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/SECTION_program-with-dsql-connector-for-node-postgres.html) - Network accessline 97
or [postgres-js](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/SECTION_program-with-dsql-connector-for-postgresjs.html). - Network accessline 101
- Use `@aws/aurora-dsql-node-postgres-connector` for automatic IAM auth - [DSQL node-postgres preferred example](https://github.com/aws-samples/aurora-dsql-samples/blob/main/javascript/node-postgres/src/example_preferred.js) - Network accessline 102
- [DSQL node-postgres preferred example](https://github.com/aws-samples/aurora-dsql-samples/blob/main/javascript/node-postgres/src/example_preferred.js) - Network accessline 103
- See [aurora-dsql-samples/javascript/node-postgres](https://github.com/aws-samples/aurora-dsql-samples/tree/main/javascript/node-postgres) - Network accessline 107
- Lightweight alternative with `@aws/aurora-dsql-node-postgres-connector` - Good for serverless environments - [DSQL postgres-js preferred example](https://github.com/aws-samples/aurora-dsql-samples/blob/main/javascript/postgres-js/src/exam - Network accessline 108
- Good for serverless environments - [DSQL postgres-js preferred example](https://github.com/aws-samples/aurora-dsql-samples/blob/main/javascript/postgres-js/src/example_preferred.js) - See [aurora-dsql-samples/javascript/postgres-js](https - Network accessline 109
- [DSQL postgres-js preferred example](https://github.com/aws-samples/aurora-dsql-samples/blob/main/javascript/postgres-js/src/example_preferred.js) - Network accessline 110
- See [aurora-dsql-samples/javascript/postgres-js](https://github.com/aws-samples/aurora-dsql-samples/tree/main/javascript/postgres-js) - Network accessline 114
- Custom `directUrl` with token refresh middleware - See [aurora-dsql-samples/typescript/prisma](https://github.com/aws-samples/aurora-dsql-samples/tree/main/typescript/prisma) - Network accessline 115
- See [aurora-dsql-samples/typescript/prisma](https://github.com/aws-samples/aurora-dsql-samples/tree/main/typescript/prisma) - Network accessline 119
- Configure `dialectOptions` for SSL - Token refresh in `beforeConnect` hook - See [aurora-dsql-samples/typescript/sequelize](https://github.com/aws-samples/aurora-dsql-samples/tree/main/typescript/sequelize) - Network accessline 121
- See [aurora-dsql-samples/typescript/sequelize](https://github.com/aws-samples/aurora-dsql-samples/tree/main/typescript/sequelize) - Network accessline 125
- Custom DataSource with token refresh - Create migrations table manually via psql - See [aurora-dsql-samples/typescript/type-orm](https://github.com/aws-samples/aurora-dsql-samples/tree/main/typescript/type-orm) - Network accessline 127
- See [aurora-dsql-samples/typescript/type-orm](https://github.com/aws-samples/aurora-dsql-samples/tree/main/typescript/type-orm) - Network accessline 131
PREFER using JDBC with the [DSQL JDBC Connector](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/SECTION_program-with-jdbc-connector.html) - Network accessline 135
- Use DSQL JDBC Connector for automatic IAM auth - URL format: `jdbc:aws-dsql:postgresql://<endpoint>/postgres` - See [aurora-dsql-samples/java/pgjdbc](https://github.com/aws-samples/aurora-dsql-samples/tree/main/java/pgjdbc) - Network accessline 136
- URL format: `jdbc:aws-dsql:postgresql://<endpoint>/postgres` - See [aurora-dsql-samples/java/pgjdbc](https://github.com/aws-samples/aurora-dsql-samples/tree/main/java/pgjdbc) - Properties: `wrapperPlugins=iam`, `ssl=true`, `sslmode=veri - Network accessline 137
- See [aurora-dsql-samples/java/pgjdbc](https://github.com/aws-samples/aurora-dsql-samples/tree/main/java/pgjdbc) - Network accessline 142
- Wrap JDBC connection, configure max lifetime < 1 hour - See [aurora-dsql-samples/java/pgjdbc_hikaricp](https://github.com/aws-samples/aurora-dsql-samples/tree/main/java/pgjdbc_hikaricp) - Network accessline 143
- See [aurora-dsql-samples/java/pgjdbc_hikaricp](https://github.com/aws-samples/aurora-dsql-samples/tree/main/java/pgjdbc_hikaricp) - Network accessline 147
PREFER using the [Amazon.AuroraDsql.Npgsql](https://github.com/awslabs/aurora-dsql-orms/tree/main/dotnet) connector for automatic IAM auth: - Network accessline 154
- Adapter: [Amazon.AuroraDsql.EntityFrameworkCore](https://github.com/awslabs/aurora-dsql-orms/tree/main/dotnet/ef-core) (requires .NET 8.0+, EF Core 9.0.7+, `Amazon.AuroraDsql.Npgsql` 1.1.0+) - Network accessline 164
- Use `after_connect` hook: `.after_connect(|conn, _| conn.execute("SET search_path = public"))` - Implement periodic token refresh with `tokio::spawn` - See [aurora-dsql-samples/rust/sqlx](https://github.com/aws-samples/aurora-dsql-samples - Network accessline 166
- See [aurora-dsql-samples/rust/sqlx](https://github.com/aws-samples/aurora-dsql-samples/tree/main/rust/sqlx) - Network accessline 178
- MUST use Erlang/OTP 26+ - Driver: [Postgrex](https://hexdocs.pm/postgrex/) ~> 0.19 - Network accessline 179
- Driver: [Postgrex](https://hexdocs.pm/postgrex/) ~> 0.19 - Network accessline 180
- Use Postgrex.query! for all queries - See [aurora-dsql-samples/elixir/postgrex](https://github.com/aws-samples/aurora-dsql-samples/tree/main/elixir/postgrex) - Connection: Implement `Repo.init/2` callback for dynamic token injection - Network accessline 181
- See [aurora-dsql-samples/elixir/postgrex](https://github.com/aws-samples/aurora-dsql-samples/tree/main/elixir/postgrex)
plugins/databases-on-aws/skills/dsql/references/limits-and-error-codes.md
- Network accessline 20
Values marked **observed** were measured on a single-Region cluster (PostgreSQL 16 compatibility) rather than taken from the documentation. Where an observed value contradicts the [quotas documentation](https://docs.aws.amazon.com/aurora-ds - Network accessline 21
compatibility) rather than taken from the documentation. Where an observed value contradicts the [quotas documentation](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/CHAP_quotas.html), the row says so. **SHOULD** size against the - Network accessline 22
[quotas documentation](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/CHAP_quotas.html), - Network accessline 99
Unsupported-feature list: [PostgreSQL compatibility — unsupported features](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-postgresql-compatibility-unsupported-features.html). Index syntax: [CREATE INDEX syntax suppor - Network accessline 162
From the [Aurora DSQL quotas documentation](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/CHAP_quotas.html).
plugins/databases-on-aws/skills/dsql/references/occ-retry-patterns.md
- Network accessline 46
The [DDL and distributed transactions](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-ddl.html) - Network accessline 47
[DDL and distributed transactions](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-ddl.html) - Network accessline 73
| Language | Driver | Connector package | Repository | | -------- | ---------- - Network accessline 74
| -------- | ------------------------------ | ------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------- | | Java | JDBC - Network accessline 75
| Java | JDBC | `aurora-dsql-jdbc-connector` | [aurora-dsql-connectors/java/jdbc](https://github.com/awslabs/aurora-dsql-connectors/tree/main/java/jdbc) | - Network accessline 76
| Python | `psycopg`/`psycopg2`/`asyncpg` | `aurora-dsql-python-connector` | [aurora-dsql-connectors/python/connector](https://github.com/awslabs/aurora-dsql-connectors/tree/main/python/connector) | - Network accessline 77
| Node.js | `pg` | `@aws/aurora-dsql-node-postgres-connector` | [aurora-dsql-connectors/node/node-postgres](https://github.com/awslabs/aurora-dsql-connectors/tree/main/node/node-postgres) | - Network accessline 78
| Node.js | `Postgres.js` | `@aws/aurora-dsql-postgresjs-connector` | [aurora-dsql-connectors/node/postgres-js](https://github.com/awslabs/aurora-dsql-connectors/tree/main/node/postgres-js) | - Network accessline 135
The same pattern applies in any language — catch SQLSTATE 40001, apply exponential backoff with jitter, retry up to the max, and record the `(OC000)`/`(OC001)` marker so an exhausted loop can be told apart from row contention. See the [DSQL - Network accessline 136
with jitter, retry up to the max, and record the `(OC000)`/`(OC001)` marker so an exhausted loop can be told apart from row contention. See the [DSQL code samples](https://github.com/aws-samples/aurora-dsql-samples) for Java, Go, Node.js, a - Network accessline 137
can be told apart from row contention. See the [DSQL code samples](https://github.com/aws-samples/aurora-dsql-samples)
plugins/databases-on-aws/skills/dsql/references/onboarding.md
- Network accessline 65
- Guide them through `aws configure` - MUST verify IAM permissions include `dsql:CreateCluster`, `dsql:GetCluster`, `dsql:DbConnectAdmin` - Recommend [`AmazonAuroraDSQLConsoleFullAccess`](https://docs.aws.amazon.com/aws-managed-policy/lates - Network accessline 67
- Recommend [`AmazonAuroraDSQLConsoleFullAccess`](https://docs.aws.amazon.com/aws-managed-policy/latest/reference/AmazonAuroraDSQLConsoleFullAccess.html) managed policy - Dangerous shell operationline 79
- Linux (Debian/Ubuntu): `sudo apt-get install postgresql-client` - Dangerous shell operationline 83
sudo yum install -y https://download.postgresql.org/pub/repos/yum/reporpms/EL-9-x86_64/pgdg-redhat-repo-latest.noarch.rpm - Network accessline 83
sudo yum install -y https://download.postgresql.org/pub/repos/yum/reporpms/EL-9-x86_64/pgdg-redhat-repo-latest.noarch.rpm - Dangerous shell operationline 84
sudo yum install -y postgresql17 - Network accessline 255
- Arrays must be serialized into a single column — PREFER `JSONB` when querying inside the value (`@>`, `?`, `jsonb_array_elements_text(data)`, indexed JSONB paths); MAY use `TEXT` for columns the database never inspects; `JSON` is also val - Network accessline 256
- SHOULD keep existing `JSON` columns as `JSON`; MAY upgrade to `JSONB` if JSONB-only operators or indexed paths are needed - Verify column types against the [supported data types list](https://docs.aws.amazon.com/aurora-dsql/latest/userg - Network accessline 257
- Verify column types against the [supported data types list](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-postgresql-compatibility-supported-data-types.html) - Network accessline 375
- [Aurora DSQL Documentation](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/) - Network accessline 376
- [Aurora DSQL Starter Kit](https://github.com/awslabs/aurora-dsql-starter-kit/tree/main) - Network accessline 377
- [Code Samples Repository](https://github.com/aws-samples/aurora-dsql-samples) - Network accessline 378
- [IAM Authentication Guide](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/using-database-and-iam-roles.html) - Network accessline 379
- [Getting Started Guide](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/getting-started.html) - Network accessline 380
- [PostgreSQL Compatibility](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-postgresql-compatibility.html) - Network accessline 381
- [Incompatible PostgreSQL Features](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-postgresql-compatibility-unsupported-features.html) - Network accessline 382
- [CloudFormation Resource](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-dsql-cluster.html)
plugins/databases-on-aws/skills/dsql/references/orm-guides/overview.md
- Network accessline 74
| Dialect | Provided by `aurora-dsql-hibernate-dialect` (auto-registered) - Network accessline 75
| ID generation | `@GeneratedValue(strategy = GenerationType.UUID)` - Network accessline 76
| OCC retry | Prefer the [aurora-dsql-jdbc-connector](https://github.com/awslabs/aurora-dsql-connectors/tree/main/java/jdbc) — built-in retry for SQLSTATE 40001. For manual `@Retryable`, match on `SQLException` and check `getSQLState() - Network accessline 100
- [Migrating from PostgreSQL to Aurora DSQL — framework and ORM compatibility](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-postgresql-compatibility-migration-guide.html#dsql-framework-compatibility)
plugins/databases-on-aws/skills/dsql/references/pg-migrations/index-conversion.md
- Network accessline 25
- [Asynchronous Indexes](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-create-index-async.html) - Network accessline 26
- [CREATE INDEX syntax support](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/create-index-syntax-support.html) - Network accessline 27
- [DSQL SQL Dialect Blog](https://aws.amazon.com/blogs/database/dsql-sql-dialect-how-amazon-aurora-dsql-differs-from-single-instance-postgresql/)
plugins/databases-on-aws/skills/dsql/references/pg-migrations/multi-region.md
- Network accessline 7
- [What is Aurora DSQL](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/what-is-aurora-dsql.html) - Network accessline 8
- [Multi-Region Clusters](https://awslabs.github.io/aurora-dsql-starter-kit/multi-region-clusters.html) - Network accessline 9
- [Multi-Region Endpoint Routing](https://aws.amazon.com/blogs/database/implement-multi-region-endpoint-routing-for-amazon-aurora-dsql/)
plugins/databases-on-aws/skills/dsql/references/pg-migrations/schema-objects.md
- Network accessline 9
- [Supported SQL Features](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-postgresql-compatibility-supported-sql-features.html) - Network accessline 10
- [Migration Guide](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-postgresql-compatibility-migration-guide.html) - Network accessline 11
- [Database Roles and IAM](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/using-database-and-iam-roles.html)
plugins/databases-on-aws/skills/dsql/references/pg-migrations/type-mapping.md
- Network accessline 7
For the authoritative list of supported types, run `dsql_lint(sql=..., fix=true)` or consult [DSQL Supported Data Types](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-postgresql-compatibility-supported-data-types.htm - Network accessline 8
consult [DSQL Supported Data Types](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-postgresql-compatibility-supported-data-types.html).
plugins/databases-on-aws/skills/dsql/references/troubleshooting.md
- Network accessline 96
See [cluster lifecycle](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/cluster-lifecycle.html) for state definitions and behavior. - Network accessline 142
See [full list of unsupported features](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with-postgresql-compatibility-unsupported-features.html), - Network accessline 213
- Use officially tested drivers from [aws-samples/aurora-dsql-samples](https://github.com/aws-samples/aurora-dsql-samples) - Network accessline 222
- [Aurora DSQL troubleshooting guide](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/troubleshooting.html#troubleshooting-connections) - Network accessline 223
- [Aurora DSQL PostgreSQL compatibility](https://docs.aws.amazon.com/aurora-dsql/latest/userguide/working-with.html)
plugins/deploy-on-aws/.claude-plugin/plugin.json
- Network accessline 4
}, "description": "Deploy applications to AWS with architecture recommendations, cost estimates, and IaC deployment. Generate validated AWS architecture diagrams as draw.io XML.", "homepage": "https://github.com/awslabs/agent-plugins", - Network accessline 5
"description": "Deploy applications to AWS with architecture recommendations, cost estimates, and IaC deployment. Generate validated AWS architecture diagrams as draw.io XML.", "homepage": "https://github.com/awslabs/agent-plugins", "ke - Network accessline 6
"homepage": "https://github.com/awslabs/agent-plugins", - Network accessline 18
"license": "Apache-2.0", "name": "deploy-on-aws", "repository": "https://github.com/awslabs/agent-plugins", - Network accessline 19
"name": "deploy-on-aws", "repository": "https://github.com/awslabs/agent-plugins", "version": "1.4.0" - Network accessline 20
"repository": "https://github.com/awslabs/agent-plugins",
plugins/deploy-on-aws/skills/aws-architecture-diagram/SKILL.md
- Broad permissionsline 1
Bash, Write, Read, Glob, Grep
plugins/deploy-on-aws/skills/elastic-beanstalk/SKILL.md
plugins/deploy-on-aws/skills/elastic-beanstalk/references/cluster-mode.md
- Network accessline 79
See [Configuration options for Beanstalk Cluster environments](https://docs.aws.amazon.com/elasticbeanstalk/latest/dg/command-options-general-eks.html) - Network accessline 122
For the managed policies on each role, the trust policies, and a ready-made `PassRole` policy, see [Permissions for Beanstalk Cluster](https://docs.aws.amazon.com/elasticbeanstalk/latest/dg/beanstalk-cluster-permissions.html). - Network accessline 123
`PassRole` policy, see [Permissions for Beanstalk Cluster](https://docs.aws.amazon.com/elasticbeanstalk/latest/dg/beanstalk-cluster-permissions.html). - Network accessline 244
See [Building container images for Beanstalk Cluster environments](https://docs.aws.amazon.com/elasticbeanstalk/latest/dg/beanstalk-cluster-app-versions.html) - Network accessline 310
The application role is also what the application uses to call AWS services at all, so scope it per environment rather than sharing one role across a set of services. See [Permissions for Beanstalk Cluster](https://docs.aws.amazon.com/elast - Network accessline 311
all, so scope it per environment rather than sharing one role across a set of services. See [Permissions for Beanstalk Cluster](https://docs.aws.amazon.com/elasticbeanstalk/latest/dg/beanstalk-cluster-permissions.html) for the trust policy - Network accessline 312
services. See [Permissions for Beanstalk Cluster](https://docs.aws.amazon.com/elasticbeanstalk/latest/dg/beanstalk-cluster-permissions.html) - Network accessline 352
With an Elastic Beanstalk-managed load balancer, it configures an HTTPS listener on port 443 and leaves port 80 closed. Always verify over `https://`. An - Network accessline 353
on port 443 and leaves port 80 closed. Always verify over `https://`. An - Network accessline 354
`http://` request hangs until it times out and reads as a broken deployment. - Network accessline 423
value another environment already uses is not dedicated at all. If the goal is separating environments from one another, different subnets are simpler and separate the cluster too. See [Multi-tenancy for Beanstalk Cluster environments](http - Network accessline 425
separate the cluster too. See [Multi-tenancy for Beanstalk Cluster environments](https://docs.aws.amazon.com/elasticbeanstalk/latest/dg/beanstalk-cluster-multi-tenancy.html). - Network accessline 431
http://service-<environment-name>.eb-<environment-name>.svc.cluster.local:<service-port> - Network accessline 478
See [Scaling Beanstalk Cluster environments](https://docs.aws.amazon.com/elasticbeanstalk/latest/dg/configuring-cluster-scaling.html) - Network accessline 491
1. `describe-environments` — status is `Ready`. 2. `describe-events --severity ERROR` — nothing there. 3. A request that exercises the behaviour the user asked for, over `https://`. - Network accessline 493
3. A request that exercises the behaviour the user asked for, over `https://`.
plugins/deploy-on-aws/skills/elastic-beanstalk/references/configuration.md
- Network accessline 22
See [Configuration options precedence](https://docs.aws.amazon.com/elasticbeanstalk/latest/dg/command-options.html#configuration-options-precedence) - Network accessline 54
See [Configuration options namespaces](https://docs.aws.amazon.com/elasticbeanstalk/latest/dg/command-options-general.html) - Network accessline 103
See [Environment secrets](https://docs.aws.amazon.com/elasticbeanstalk/latest/dg/AWSHowTo.secrets.env-vars.html) - Network accessline 118
See [Deployment policies and settings](https://docs.aws.amazon.com/elasticbeanstalk/latest/dg/using-features.rolling-version-deploy.html) - Network accessline 138
See [Health check setting](https://docs.aws.amazon.com/elasticbeanstalk/latest/dg/environments-cfg-alb.html#environments-cfg-alb-health) - Access to secretsline 147
[Credential-related source omitted]
plugins/sagemaker-ai/.claude-plugin/plugin.json
- Network accessline 4
}, "description": "Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI.", "homepage": "https://github.com/awslabs/agent-plugins" - Network accessline 5
"description": "Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI.", "homepage": "https://github.com/awslabs/agent-plugins", " - Network accessline 6
"homepage": "https://github.com/awslabs/agent-plugins", - Network accessline 18
"license": "Apache-2.0", "name": "sagemaker-ai", "repository": "https://github.com/awslabs/agent-plugins", - Network accessline 19
"name": "sagemaker-ai", "repository": "https://github.com/awslabs/agent-plugins", "version": "1.3.0" - Network accessline 20
"repository": "https://github.com/awslabs/agent-plugins",
plugins/sagemaker-ai/skills/dataset-evaluation/SKILL.md
- Network accessline 38
- **Important: training datasets and evaluation datasets have different format requirements.** - **Training datasets** must match the fine-tuning strategy format per `references/strategy_data_requirements.md` - **Evaluation datase - Network accessline 39
- **Training datasets** must match the fine-tuning strategy format per `references/strategy_data_requirements.md` - **Evaluation datasets** (for model evaluation) must match one of the [SageMaker evaluation dataset formats](https://doc - Network accessline 40
- **Evaluation datasets** (for model evaluation) must match one of the [SageMaker evaluation dataset formats](https://docs.aws.amazon.com/sagemaker/latest/dg/model-customize-evaluation-dataset-formats.html). - Network accessline 50
- Introduction: "This skill checks the structure of your dataset for model fine-tuning." - File types: This skill applies to files that are formatted according to the [Amazon SageMaker AI Developer Guide](https://docs.aws.amazon.com/sagemak - Network accessline 51
- File types: This skill applies to files that are formatted according to the [Amazon SageMaker AI Developer Guide](https://docs.aws.amazon.com/sagemaker/latest/dg/autopilot-llms-finetuning-data-format.html#autopilot-llms-finetuning-dataset
plugins/sagemaker-ai/skills/dataset-evaluation/scripts/format_detector.py
- Executable scriptline 1
Executable file
plugins/sagemaker-ai/skills/dataset-transformation/SKILL.md
- Network accessline 45
1. Try fetching the live documentation at https://docs.aws.amazon.com/sagemaker/latest/dg/model-customize-evaluation-dataset-formats.html to get the latest evaluation dataset schema definitions. 2. **If the fetch fails** (e.g., no internet
plugins/sagemaker-ai/skills/dataset-transformation/code_templates/transformation.py
- Executable scriptline 1
Executable file
plugins/sagemaker-ai/skills/dataset-transformation/references/sagemaker_dataset_formats.md
plugins/sagemaker-ai/skills/dataset-transformation/scripts/transformation_tools.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/sagemaker-ai/skills/finetuning-technique/scripts/get_recipes.py
- Executable scriptline 1
Executable file
plugins/sagemaker-ai/skills/finetuning/code_templates/dpo.py
- Executable scriptline 1
Executable file
plugins/sagemaker-ai/skills/finetuning/code_templates/rlaif_builtin.py
- Executable scriptline 1
Executable file
plugins/sagemaker-ai/skills/finetuning/code_templates/rlaif_custom_prompt.py
- Executable scriptline 1
Executable file
plugins/sagemaker-ai/skills/finetuning/code_templates/rlvr.py
- Executable scriptline 1
Executable file
plugins/sagemaker-ai/skills/finetuning/code_templates/sft.py
- Executable scriptline 1
Executable file
plugins/sagemaker-ai/skills/finetuning/references/eula_links.md
- Network accessline 3
| SageMaker Hub Model ID | Model Name | License URL(s) | | ---------- - Network accessline 4
| ----------------------------------------------------------- | ----------------------------- | --------------------------------------------------------------------------------------------------------------------------------- | | `huggingfa - Network accessline 5
| `huggingface-reasoning-qwen3-32b` | Qwen3-32B | https://huggingface.co/Qwen/Qwen3-32B/blob/main/LICENSE | - Network accessline 6
| `huggingface-reasoning-qwen3-14b` | Qwen3-14B | https://huggingface.co/Qwen/Qwen3-14B/blob/main/LICENSE | - Network accessline 7
| `huggingface-reasoning-qwen3-8b` | Qwen3-8B | https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE | - Network accessline 8
| `huggingface-reasoning-qwen3-4b` | Qwen3-4B | https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE | - Network accessline 9
| `huggingface-reasoning-qwen3-1-7b` | Qwen3-1.7B | https://huggingface.co/Qwen/Qwen3-1.7B/blob/main/LICENSE | - Network accessline 10
| `huggingface-reasoning-qwen3-06b` | Qwen3-0.6B | https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE | - Network accessline 11
| `huggingface-llm-qwen2-5-72b-instruct` | Qwen2.5-72B-Instruct | https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE | - Network accessline 12
| `huggingface-llm-qwen2-5-32b-instruct` | Qwen2.5-32B-Instruct | https://huggingface.co/Qwen/Qwen2.5-32B-Instruct/blob/main/LICENSE | - Network accessline 13
| `huggingface-llm-qwen2-5-14b-instruct` | Qwen2.5-14B-Instruct | https://huggingface.co/Qwen/Qwen2.5-14B-Instruct/blob/main/LICENSE | - Network accessline 14
| `huggingface-llm-qwen2-5-7b-instruct` | Qwen2.5-7B-Instruct | https://huggingface.co/Qwen/Qwen2.5-7B-Instruct/blob/main/LICENSE | - Network accessline 15
| `deepseek-llm-r1-distill-llama-70b` | DeepSeek-R1-Distill-Llama-70B | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B/blob/main/LICENSE | - Network accessline 16
| `deepseek-llm-r1-distill-qwen-32b` | DeepSeek-R1-Distill-Qwen-32B | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/blob/main/LICENSE | - Network accessline 17
| `deepseek-llm-r1-distill-qwen-14b` | DeepSeek-R1-Distill-Qwen-14B | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B/blob/main/LICENSE | - Network accessline 18
| `deepseek-llm-r1-distill-llama-8b` | DeepSeek-R1-Distill-Llama-8B | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B/blob/main/LICENSE | - Network accessline 19
| `deepseek-llm-r1-distill-qwen-7b` | DeepSeek-R1-Distill-Qwen-7B | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/blob/main/LICENSE | - Network accessline 20
| `deepseek-llm-r1-distill-qwen-1-5b` | DeepSeek-R1-Distill-Qwen-1.5B | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/blob/main/LICENSE | - Network accessline 21
| `openai-reasoning-gpt-oss-120b` | GPT-OSS-120B | https://huggingface.co/openai/gpt-oss-120b/blob/main/LICENSE<br>https://huggingface.co/openai/gpt-oss-120b/blob/main/USAGE_POLICY | - Network accessline 22
| `openai-reasoning-gpt-oss-20b` | GPT-OSS-20B | https://huggingface.co/openai/gpt-oss-20b/blob/main/LICENSE<br>https://huggingface.co/openai/gpt-oss-20b/blob/main/USAGE_POLICY | - Network accessline 23
| `meta-textgeneration-llama-3-3-70b-instruct` | Llama 3.3 70B Instruct | https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct/blob/main/LICENSE | - Network accessline 24
| `meta-textgeneration-llama-3-2-3b-instruct` | Llama 3.2 3B Instruct | https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/blob/main/LICENSE.txt | - Network accessline 25
| `meta-textgeneration-llama-3-2-1b-instruct` | Llama 3.2 1B Instruct | https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/blob/main/LICENSE.txt | - Network accessline 26
| `meta-textgeneration-llama-3-1-8b-instruct` | Llama 3.1 8B Instruct | https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/blob/main/LICENSE | - Network accessline 27
| `nova-textgeneration-pro` | Amazon Nova Pro | https://aws.amazon.com/service-terms/ | - Network accessline 28
| `nova-textgeneration-micro` | Amazon Nova Micro | https://aws.amazon.com/service-terms/ | - Network accessline 29
| `nova-textgeneration-lite` | Amazon Nova Lite | https://aws.amazon.com/service-terms/ | - Network accessline 30
| `nova-textgeneration-lite-v2` | Amazon Nova Lite v2 | https://aws.amazon.com/service-terms/ | - Network accessline 31
| `huggingface-reasoning-nvidia-nemotron-3-nano-30b-a3b-bf16` | Nemotron 3 Nano 30B | https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16/blob/main/LICENSE | - Network accessline 32
| `huggingface-vlm-qwen3-6-27b` | Qwen3.6-27B | https://huggingface.co/Qwen/Qwen3-VL-27B/blob/main/LICENSE | - Network accessline 33
| `huggingface-vlm-qwen3-5-27b` | Qwen3.5-27B | https://huggingface.co/Qwen/Qwen3-VL-27B/blob/main/LICENSE | - Network accessline 34
| `huggingface-vlm-qwen3-5-9b` | Qwen3.5-9B | https://huggingface.co/Qwen/Qwen3-VL-9B/blob/main/LICENSE | - Network accessline 35
| `huggingface-vlm-qwen3-5-4b` | Qwen3.5-4B | https://huggingface.co/Qwen/Qwen3-VL-4B/blob/main/LICENSE | - Network accessline 36
| `huggingface-vlm-gemma-4-31b-it` | Gemma 4 31B | https://huggingface.co/google/gemma-4-31b-it/blob/main/LICENSE | - Network accessline 37
| `meta-vlm-llama-4-scout-17b-16e-instruct` | Llama 4 Scout 17B | https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct/blob/main/LICENSE |
plugins/sagemaker-ai/skills/finetuning/scripts/mlflow_reference.py
plugins/sagemaker-ai/skills/finetuning/templates/nova_rlvr_reward_function_source_template.py
- Network accessline 1
""" Provide your custom reward function code below. Learn about the available libraries and templates that you can use at: https://docs.aws.amazon.com/sagemaker/latest/dg/customize-model.html. - Executable scriptline 1
Executable file - Network accessline 3
at: https://docs.aws.amazon.com/sagemaker/latest/dg/customize-model.html.
plugins/sagemaker-ai/skills/finetuning/templates/rlvr_reward_function_source_template.py
- Network accessline 1
""" Provide your custom reward function code below. Learn about the available libraries and templates that you can use at: https://docs.aws.amazon.com/sagemaker/latest/dg/customize-model.html. - Executable scriptline 1
Executable file - Network accessline 3
at: https://docs.aws.amazon.com/sagemaker/latest/dg/customize-model.html.
plugins/sagemaker-ai/skills/hyperpod-cluster-debugger/references/cluster-diagnostics-detail.md
- Network accessline 45
**Egress for AWS APIs.** The node needs HTTPS (443) outbound to reach the AWS services HyperPod uses: S3 (lifecycle scripts), ECR (container images), SageMaker (HyperPod control plane), SSM / SSMMessages / EC2Messages (Session Manager), STS - Dangerous shell operationline 386
sudo cat /opt/ml/config/resource_config.json | jq | grep -A 3 "$IP"
plugins/sagemaker-ai/skills/hyperpod-cluster-debugger/references/cluster-operations.md
plugins/sagemaker-ai/skills/hyperpod-cluster-debugger/scripts/diagnose-cluster.sh
- Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 129
trap '[[ ${#_CD_TEMP_FILES[@]} -gt 0 ]] && rm -f "${_CD_TEMP_FILES[@]}" 2>/dev/null || true' EXIT - Dangerous shell operationline 146
local remote="bash -c \"echo $cmd_b64 | base64 -d | bash\"" - Dangerous shell operationline 166
echo "$out" | grep -vE '^(Starting session with SessionId:|Exiting session with sessionId:|\s*$)' | grep -vE "^(bash -c \"echo [A-Za-z0-9+/=]+ \| base64 -d \| bash\"|echo '[A-Za-z0-9+/=]+'|[A-Za-z0-9+/=]{40,}={0,2})[[:spa - Dangerous shell operationline 167
| grep -vE "^(bash -c \"echo [A-Za-z0-9+/=]+ \| base64 -d \| bash\"|echo '[A-Za-z0-9+/=]+'|[A-Za-z0-9+/=]{40,}={0,2})[[:space:]]*\|?[[:space:]]*base64?[[:space:]]*-?d?[[:space:]]*\|?[[:space:]]*bash\"?\$" || true - Access to secretsline 186
[Credential-related source omitted] - Dangerous shell operationline 463
rm -f "$TMPFILE" - Access to secretsline 606
[Credential-related source omitted] - Access to secretsline 607
[Credential-related source omitted] - Dangerous shell operationline 756
rm -f "$_NODE_TRUNC_MARKER" 2>/dev/null || true - Access to secretsline 1177
[Credential-related source omitted] - Access to secretsline 1329
[Credential-related source omitted]
plugins/sagemaker-ai/skills/hyperpod-issue-report/SKILL.md
- Executable scriptline 1
Executable file - Network accessline 14
- AWS CLI configured with permissions: `sagemaker:DescribeCluster`, `sagemaker:ListClusterNodes`, `ssm:StartSession`, `s3:PutObject`, `s3:GetObject`, `eks:DescribeCluster` - Python 3.8+ and [uv](https://docs.astral.sh/uv/) (see [uv installa - Network accessline 15
- Python 3.8+ and [uv](https://docs.astral.sh/uv/) (see [uv installation docs](https://docs.astral.sh/uv/getting-started/installation/) for install options)
plugins/sagemaker-ai/skills/hyperpod-issue-report/references/collection-details.md
- Executable scriptline 1
Executable file
plugins/sagemaker-ai/skills/hyperpod-issue-report/references/troubleshooting.md
- Executable scriptline 1
Executable file
plugins/sagemaker-ai/skills/hyperpod-issue-report/scripts/hyperpod_issue_report.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 391
"echo \"Running EKS log collector...\"", "# Pinned to specific commit for reproducibility; update hash when bumping", "EKS_LOG_COLLECTOR_URL=\"https://raw.githubusercontent.com/awslabs/amazon-eks-ami/2ac5fc03 - Network accessline 392
"# Pinned to specific commit for reproducibility; update hash when bumping", "EKS_LOG_COLLECTOR_URL=\"https://raw.githubusercontent.com/awslabs/amazon-eks-ami/2ac5fc03a8030bb8bc3c1fc1e810209118a10656/log-collector-script/lin - Network accessline 393
"EKS_LOG_COLLECTOR_URL=\"https://raw.githubusercontent.com/awslabs/amazon-eks-ami/2ac5fc03a8030bb8bc3c1fc1e810209118a10656/log-collector-script/linux/eks-log-collector.sh\"", "EKS_LOG_COLLECTOR_SHA256=\"61c8940e9391330a9c67d - Network accessline 394
"EKS_LOG_COLLECTOR_SHA256=\"61c8940e9391330a9c67d8cd6720de3de3a1a90021546835f7f54f1fed2efb3f\"", "curl -f -o /tmp/eks-log-collector.sh \"${EKS_LOG_COLLECTOR_URL}\"", # nosec B108 - remote node shell script, not local Python - Network accessline 395
"curl -f -o /tmp/eks-log-collector.sh \"${EKS_LOG_COLLECTOR_URL}\"", # nosec B108 - remote node shell script, not local Python - Dangerous shell operationline 407
" rm -f /tmp/eks-log-collector.sh", - Dangerous shell operationline 424
" rm -f \"${EKS_TARBALL}\"", - Dangerous shell operationline 428
" rm -f /tmp/eks-log-collector.sh", - Dangerous shell operationline 433
"rm -f /tmp/eks-log-collector.sh", - Dangerous shell operationline 494
" rm -rf \"${OUTPUT_DIR}\" \"${TARBALL}\"",
plugins/sagemaker-ai/skills/hyperpod-nccl/references/debugging-guide.md
- Access to secretsline 39
[Credential-related source omitted] - Access to secretsline 40
[Credential-related source omitted] - Access to secretsline 41
[Credential-related source omitted] - Access to secretsline 42
[Credential-related source omitted] - Network accessline 355
# Example (replace <PORT> with the actual RAS port for your build): echo "verbose status" | nc -w 3 localhost <PORT> - Network accessline 356
echo "verbose status" | nc -w 3 localhost <PORT> - Network accessline 363
# Inside a K8s pod: kubectl exec -n <NS> <POD> -- sh -c "echo 'verbose status' | nc -w 3 localhost <PORT>" - Network accessline 364
kubectl exec -n <NS> <POD> -- sh -c "echo 'verbose status' | nc -w 3 localhost <PORT>" - Dangerous shell operationline 604
sudo setpci -s "$BDF" ECAP_ACS+0x6.w=0000 2>/dev/null - Dangerous shell operationline 640
rm -f /dev/shm/nccl-* - Dangerous shell operationline 644
sudo systemctl restart systemd-logind - Dangerous shell operationline 651
**Blast radius:** `rm -f /dev/shm/nccl-*` silently destroys any active NCCL shared-memory segments — running a collective at the same time will fail. `RemoveIPC=no` is a persistent systemd change; the `systemctl restart` logs out anyone in
plugins/sagemaker-ai/skills/hyperpod-nccl/references/operations.md
- Dangerous shell operationline 301
sudo systemctl restart systemd-logind
plugins/sagemaker-ai/skills/hyperpod-nccl/references/performance-testing.md
- Access to secretsline 121
[Credential-related source omitted]
plugins/sagemaker-ai/skills/hyperpod-nccl/scripts/nccl-diagnose.sh
- Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 61
[[ ${#_TEMP_FILES[@]} -gt 0 ]] && rm -f "${_TEMP_FILES[@]}" 2>/dev/null || true - Access to secretsline 185
[Credential-related source omitted] - Access to secretsline 200
[Credential-related source omitted] - Dangerous shell operationline 287
rm -f "$tmpfile" - Dangerous shell operationline 1499
cmd_b64=$(printf '%s' "$script_body" | base64 | tr -d '\n') || { rm -f "$tmpfile"; return 1; } - Dangerous shell operationline 1500
local remote="bash -c \"echo $cmd_b64 | base64 -d | bash\"" - Dangerous shell operationline 1501
python3 -c "import json,sys; print(json.dumps({'command':[sys.argv[1]]}))" "$remote" > "$tmpfile" 2>/dev/null || { rm -f "$tmpfile"; return 1; } - Dangerous shell operationline 1527
rm -f "$tmpfile" - Dangerous shell operationline 1529
echo "$out" | grep -vE '^(Starting session with SessionId:|Exiting session with sessionId:|\s*$)' | grep -vE "^(bash -c \"echo [A-Za-z0-9+/=]+ \| base64 -d \| bash\"|echo '[A-Za-z0-9+/=]+'|[A-Za-z0-9+/=]{40,}={0,2})[[:space - Dangerous shell operationline 1530
| grep -vE "^(bash -c \"echo [A-Za-z0-9+/=]+ \| base64 -d \| bash\"|echo '[A-Za-z0-9+/=]+'|[A-Za-z0-9+/=]{40,}={0,2})[[:space:]]*\|?[[:space:]]*base64?[[:space:]]*-?d?[[:space:]]*\|?[[:space:]]*bash\"?\$" || true - Network accessline 1547
[Credential-related source omitted] - Network accessline 1548
[Credential-related source omitted] - Network accessline 1549
[Credential-related source omitted] - Access to secretsline 1549
[Credential-related source omitted] - Network accessline 1550
[Credential-related source omitted] - Access to secretsline 1550
[Credential-related source omitted] - Network accessline 1551
[Credential-related source omitted] - Network accessline 1552
[Credential-related source omitted] - Access to secretsline 1552
[Credential-related source omitted] - Network accessline 1553
"http://169.254.169.254/latest/meta-data/placement/availability-zone" 2>/dev/null || echo "unknown") - Network accessline 1743
[Credential-related source omitted] - Network accessline 1744
[Credential-related source omitted] - Network accessline 1745
[Credential-related source omitted] - Access to secretsline 1745
[Credential-related source omitted] - Network accessline 1746
[Credential-related source omitted] - Access to secretsline 1746
[Credential-related source omitted] - Network accessline 1747
http://169.254.169.254/latest/meta-data/instance-type --connect-timeout 2 2>/dev/null || echo "") - Network accessline 1748
# Counts only included where AWS publishes them in the EC2 EFA # docs (https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/efa-acc-inst-types.html). - Network accessline 1749
# docs (https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/efa-acc-inst-types.html). - Network accessline 1959
NC_CMD=$(command -v nc 2>/dev/null || command -v ncat 2>/dev/null || echo "") - Network accessline 1978
fi else echo "[INFO] nc/ncat not found — cannot probe NCCL RAS" - Network accessline 1979
else echo "[INFO] nc/ncat not found — cannot probe NCCL RAS" fi - Network accessline 1980
echo "[INFO] nc/ncat not found — cannot probe NCCL RAS"
plugins/sagemaker-ai/skills/hyperpod-node-debugger/references/node-diagnostics-detail.md
- Dangerous shell operationline 427
**Last-resort force** — if the node is stuck in `fail`, the HyperPod Slurm manual-recovery doc provides `scontrol update node=<ip-ipv4> state=down reason="Action:Replace"` as a last resort. Per the doc: "this requires administrator privileg - Dangerous shell operationline 427
**Last-resort force** — if the node is stuck in `fail`, the HyperPod Slurm manual-recovery doc provides `scontrol update node=<ip-ipv4> state=down reason="Action:Replace"` as a last resort. Per the doc: "this requires administrator privileg - Dangerous shell operationline 507
sudo nvidia-bug-report.sh # NVIDIA's authoritative bundle - Dangerous shell operationline 507
sudo nvidia-bug-report.sh # NVIDIA's authoritative bundle - Dangerous shell operationline 508
sudo tar -czf /tmp/nvidia-dcgm-logs.tgz /var/log/nvidia-dcgm/ - Dangerous shell operationline 508
sudo tar -czf /tmp/nvidia-dcgm-logs.tgz /var/log/nvidia-dcgm/ - Dangerous shell operationline 598
bash skills/hyperpod-ssm/scripts/ssm-exec.sh --target <TARGET> --region <REGION> 'sudo systemctl status slurmd && free -h && df -h' - Dangerous shell operationline 598
bash skills/hyperpod-ssm/scripts/ssm-exec.sh --target <TARGET> --region <REGION> 'sudo systemctl status slurmd && free -h && df -h' - Dangerous shell operationline 599
'sudo systemctl status slurmd && free -h && df -h' - Dangerous shell operationline 599
'sudo systemctl status slurmd && free -h && df -h' - Dangerous shell operationline 611
sudo systemctl start slurmd - Dangerous shell operationline 611
sudo systemctl start slurmd - Dangerous shell operationline 612
sudo systemctl enable slurmd # only if it was not enabled before - Dangerous shell operationline 612
sudo systemctl enable slurmd # only if it was not enabled before - Dangerous shell operationline 633
sudo systemctl restart slurmctld && sinfo && squeue - Dangerous shell operationline 633
sudo systemctl restart slurmctld && sinfo && squeue - Dangerous shell operationline 675
sudo du -h --max-depth=1 / 2>/dev/null | sort -hr | head -15 - Dangerous shell operationline 675
sudo du -h --max-depth=1 / 2>/dev/null | sort -hr | head -15 - Dangerous shell operationline 711
echo 1024 | sudo tee /proc/sys/vm/nr_hugepages # 1024 × 2 MiB = 2 GiB, runtime-only - Dangerous shell operationline 711
echo 1024 | sudo tee /proc/sys/vm/nr_hugepages # 1024 × 2 MiB = 2 GiB, runtime-only - Dangerous shell operationline 712
echo 'vm.nr_hugepages=1024' | sudo tee -a /etc/sysctl.d/99-hugepages.conf # persist across reboots - Dangerous shell operationline 712
echo 'vm.nr_hugepages=1024' | sudo tee -a /etc/sysctl.d/99-hugepages.conf # persist across reboots - Dangerous shell operationline 737
sudo journalctl --vacuum-size=500M - Dangerous shell operationline 737
sudo journalctl --vacuum-size=500M - Dangerous shell operationline 743
sudo rm -f /var/log/<specific-file>.log.N - Dangerous shell operationline 743
sudo rm -f /var/log/<specific-file>.log.N - Dangerous shell operationline 746
sudo apt-get clean 2>/dev/null || sudo yum clean all 2>/dev/null - Dangerous shell operationline 746
sudo apt-get clean 2>/dev/null || sudo yum clean all 2>/dev/null - Dangerous shell operationline 753
**Blast radius:** `journalctl --vacuum-size` and package-manager `clean` are low-risk. Targeted `rm` in `/var/log/` is safe for rotated-and-gzipped files (`*.gz`) but a blanket `rm -f /var/log/*.log.*` can delete logs an incident team needs - Dangerous shell operationline 753
**Blast radius:** `journalctl --vacuum-size` and package-manager `clean` are low-risk. Targeted `rm` in `/var/log/` is safe for rotated-and-gzipped files (`*.gz`) but a blanket `rm -f /var/log/*.log.*` can delete logs an incident team needs - Dangerous shell operationline 776
sudo dmesg -T | grep -i -B2 -A30 "Out of memory" | tail -80 - Dangerous shell operationline 776
sudo dmesg -T | grep -i -B2 -A30 "Out of memory" | tail -80 - Dangerous shell operationline 791
sudo find / -xdev -type f 2>/dev/null | awk -F/ '{print $1"/"$2"/"$3}' | sort | uniq -c | sort -rn | head -20 - Dangerous shell operationline 791
sudo find / -xdev -type f 2>/dev/null | awk -F/ '{print $1"/"$2"/"$3}' | sort | uniq -c | sort -rn | head -20 - Dangerous shell operationline 802
rm -rf ~/.cache/pip/* - Dangerous shell operationline 802
rm -rf ~/.cache/pip/* - Dangerous shell operationline 810
rm -rf ~/.cache/huggingface/<specific-model-dir> - Dangerous shell operationline 810
rm -rf ~/.cache/huggingface/<specific-model-dir> - Dangerous shell operationline 813
sudo journalctl --vacuum-size=200M - Dangerous shell operationline 813
sudo journalctl --vacuum-size=200M - Dangerous shell operationline 820
**Blast radius:** `rm -rf ~/.cache/huggingface/*` can destroy large model weights requiring slow re-downloads (potentially interrupting training on adjacent jobs that share the cache). `docker system prune -a --volumes -f` without care can - Dangerous shell operationline 820
**Blast radius:** `rm -rf ~/.cache/huggingface/*` can destroy large model weights requiring slow re-downloads (potentially interrupting training on adjacent jobs that share the cache). `docker system prune -a --volumes -f` without care can - Dangerous shell operationline 894
| Slurmd (Slurm only) | `sudo systemctl status slurmd` | - Dangerous shell operationline 894
| Slurmd (Slurm only) | `sudo systemctl status slurmd` | - Dangerous shell operationline 956
bash skills/hyperpod-ssm/scripts/ssm-exec.sh --target <TARGET> --region <REGION> 'sudo crictl ps -a | head -20 && sudo crictl logs --tail 30 <CONTAINER_ID> && journalctl -u containerd --no-pager -n 50' - Dangerous shell operationline 956
bash skills/hyperpod-ssm/scripts/ssm-exec.sh --target <TARGET> --region <REGION> 'sudo crictl ps -a | head -20 && sudo crictl logs --tail 30 <CONTAINER_ID> && journalctl -u containerd --no-pager -n 50' - Dangerous shell operationline 957
'sudo crictl ps -a | head -20 && sudo crictl logs --tail 30 <CONTAINER_ID> && journalctl -u containerd --no-pager -n 50' - Dangerous shell operationline 957
'sudo crictl ps -a | head -20 && sudo crictl logs --tail 30 <CONTAINER_ID> && journalctl -u containerd --no-pager -n 50'
plugins/sagemaker-ai/skills/hyperpod-node-debugger/references/node-issue-catalog.md
- Dangerous shell operationline 106
sudo systemctl status slurmd
plugins/sagemaker-ai/skills/hyperpod-node-debugger/scripts/check-efa-sg.sh
plugins/sagemaker-ai/skills/hyperpod-node-debugger/scripts/check-node-reachability.sh
- Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 94
# Read-only invariant: detect only, never `sudo modprobe efa` — loading kernel - Network accessline 233
[Credential-related source omitted] - Network accessline 236
[Credential-related source omitted] - Access to secretsline 236
[Credential-related source omitted] - Network accessline 237
[Credential-related source omitted] - Access to secretsline 237
[Credential-related source omitted] - Network accessline 238
[Credential-related source omitted] - Network accessline 239
[Credential-related source omitted] - Access to secretsline 239
[Credential-related source omitted] - Network accessline 240
http://169.254.169.254/latest/meta-data/local-ipv4 --connect-timeout 3 -m 5 2>/dev/null || echo "unknown")
plugins/sagemaker-ai/skills/hyperpod-node-debugger/scripts/check-vpc-config.sh
plugins/sagemaker-ai/skills/hyperpod-node-debugger/scripts/triage-cluster.sh
- Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 131
[[ ${#_TEMP_FILES[@]} -gt 0 ]] && rm -f "${_TEMP_FILES[@]}" 2>/dev/null || true - Dangerous shell operationline 164
local remote="bash -c \"echo $cmd_b64 | base64 -d | bash\"" - Dangerous shell operationline 179
echo "$out" | grep -vE '^(Starting session with SessionId:|Exiting session with sessionId:|\s*$)' | grep -vE "^(bash -c \"echo [A-Za-z0-9+/=]+ \| base64 -d \| bash\"|echo '[A-Za-z0-9+/=]+'|[A-Za-z0-9+/=]{40,}={0,2})[[:spa - Dangerous shell operationline 180
| grep -vE "^(bash -c \"echo [A-Za-z0-9+/=]+ \| base64 -d \| bash\"|echo '[A-Za-z0-9+/=]+'|[A-Za-z0-9+/=]{40,}={0,2})[[:space:]]*\|?[[:space:]]*base64?[[:space:]]*-?d?[[:space:]]*\|?[[:space:]]*bash\"?\$" || true - Access to secretsline 869
[Credential-related source omitted] - Access to secretsline 1017
[Credential-related source omitted]
plugins/sagemaker-ai/skills/hyperpod-performance-debugger/SKILL.md
- Network accessline 87
Run the standard `nccl-tests` recipes from [awslabs/awsome-distributed-training](https://github.com/awslabs/awsome-distributed-training/tree/main/micro-benchmarks/nccl-tests). For an N-node cluster, run all-reduce across every pair and reco - Network accessline 89
Expected `busbw` per SKU is published in the [AI-on-HyperPod NCCL test guide](https://awslabs.github.io/ai-on-sagemaker-hyperpod/docs/slurm-orchestration/validation-and-testing/performance-testing/nccl-tests). Benchmark the specific instanc - Network accessline 176
- Amazon SageMaker HyperPod troubleshooting guide (official): <https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md> - Network accessline 177
- AI-on-HyperPod NCCL performance tests (expected `busbw` per SKU): <https://awslabs.github.io/ai-on-sagemaker-hyperpod/docs/slurm-orchestration/validation-and-testing/performance-testing/nccl-tests> - Network accessline 178
- Amazon SageMaker HyperPod resiliency (NodeRecovery, HMA, auto-resume): <https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency.html> - Network accessline 179
- Amazon SageMaker HyperPod deep health checks: <https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency-slurm-deep-health-checks.html> - Network accessline 180
- StartClusterHealthCheck API: <https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_StartClusterHealthCheck.html> - Network accessline 181
- Amazon EC2 instance topology / network-node-layer labels: <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/how-ec2-instance-topology-works.html> - Network accessline 182
- Amazon FSx for Lustre performance: <https://docs.aws.amazon.com/fsx/latest/LustreGuide/performance.html> - Network accessline 183
- Amazon FSx for OpenZFS metrics: <https://docs.aws.amazon.com/fsx/latest/OpenZFSGuide/fsx-openzfs-metrics.html> - Network accessline 184
- AWS Elastic Fabric Adapter and NCCL: <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/efa-start-nccl.html> - Network accessline 185
- awslabs/awsome-distributed-training NCCL tests: <https://github.com/awslabs/awsome-distributed-training/tree/main/micro-benchmarks/nccl-tests>
plugins/sagemaker-ai/skills/hyperpod-performance-debugger/references/perf-details.md
- Network accessline 17
Use the `nccl-tests` recipes from [awslabs/awsome-distributed-training](https://github.com/awslabs/awsome-distributed-training/tree/main/micro-benchmarks/nccl-tests). The repo ships `micro-benchmarks/nccl-tests/slurm/nccl-tests-container.sb - Network accessline 193
- Amazon SageMaker HyperPod troubleshooting guide (official): <https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md> - Network accessline 194
- AI-on-HyperPod NCCL performance test guide (expected `busbw` per SKU): <https://awslabs.github.io/ai-on-sagemaker-hyperpod/docs/slurm-orchestration/validation-and-testing/performance-testing/nccl-tests> - Network accessline 195
- AI-on-HyperPod GPU stress testing: <https://awslabs.github.io/ai-on-sagemaker-hyperpod/docs/validation-and-testing/performance-testing/gpu-stress-testing> - Network accessline 196
- Amazon SageMaker HyperPod resiliency (NodeRecovery, Health Monitoring Agent, auto-resume): <https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency.html> - Network accessline 197
- Amazon SageMaker HyperPod deep health checks: <https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-deep-health-checks.html> - Network accessline 198
- AWS Elastic Fabric Adapter and NCCL: <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/efa-start-nccl.html> - Network accessline 199
- Amazon FSx for Lustre performance: <https://docs.aws.amazon.com/fsx/latest/LustreGuide/performance.html> - Network accessline 200
- Amazon FSx for OpenZFS metrics: <https://docs.aws.amazon.com/fsx/latest/OpenZFSGuide/fsx-openzfs-metrics.html> - Network accessline 201
- awslabs/awsome-distributed-training NCCL tests: <https://github.com/awslabs/awsome-distributed-training/tree/main/micro-benchmarks/nccl-tests> - Network accessline 202
- Amazon EC2 instance topology (network-node-layer ordering): <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/how-ec2-instance-topology-works.html>
plugins/sagemaker-ai/skills/hyperpod-performance-debugger/scripts/perf-snapshot.sh
plugins/sagemaker-ai/skills/hyperpod-slurm-debugger/SKILL.md
- Network accessline 38
- `sagemaker:DescribeCluster`, `sagemaker:ListClusterNodes` - `ssm:StartSession` on the HyperPod-created SSM document - [Session Manager plugin](https://docs.aws.amazon.com/systems-manager/latest/userguide/session-manager-working-with-ins - Network accessline 39
- `ssm:StartSession` on the HyperPod-created SSM document - [Session Manager plugin](https://docs.aws.amazon.com/systems-manager/latest/userguide/session-manager-working-with-install-plugin.html) installed locally. - Network accessline 40
- [Session Manager plugin](https://docs.aws.amazon.com/systems-manager/latest/userguide/session-manager-working-with-install-plugin.html) - Network accessline 128
Link: <https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md> - Network accessline 144
- <https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md> - Network accessline 145
- <https://slurm.schedmd.com/scontrol.html> (`state=resume` semantics) - Network accessline 180
controller log spams `Unable to contact slurmdbd`. Restore `slurmdbd` before considering controller restart. <https://slurm.schedmd.com/accounting.html> · - Network accessline 181
considering controller restart. <https://slurm.schedmd.com/accounting.html> · [details](references/slurm-details.md#slurmdbd-connectivity). - Network accessline 182
<https://slurm.schedmd.com/accounting.html> · - Network accessline 184
- **Stale config** — `slurm.conf` / `topology.conf` mtime > slurmctld start. `scontrol reconfigure` first; restart is fallback. <https://slurm.schedmd.com/scontrol.html> · - Network accessline 185
`scontrol reconfigure` first; restart is fallback. <https://slurm.schedmd.com/scontrol.html> · [details](references/slurm-details.md#scontrol-reconfigure-vs-restart). - Network accessline 186
<https://slurm.schedmd.com/scontrol.html> · - Network accessline 191
- <https://slurm.schedmd.com/slurmctld.html> - Network accessline 192
- <https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md> - Network accessline 209
Link: <https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency-slurm-replace-faulty-instance.html> - Network accessline 229
Link: <https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency-slurm-auto-resume.html>
plugins/sagemaker-ai/skills/hyperpod-slurm-debugger/references/slurm-details.md
- Network accessline 21
- HyperPod Slurm troubleshooting: <https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md> - Network accessline 22
<https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md> - Network accessline 23
- Replace a faulty Slurm instance: <https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency-slurm-replace-faulty-instance.html> - HyperPod auto-resume: - Network accessline 24
<https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency-slurm-replace-faulty-instance.html> - Network accessline 25
- HyperPod auto-resume: <https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency-slurm-auto-resume.html> - `BatchRebootClusterNodes`: - Network accessline 26
<https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency-slurm-auto-resume.html> - Network accessline 27
- `BatchRebootClusterNodes`: <https://docs.aws.amazon.com/cli/latest/reference/sagemaker/batch-reboot-cluster-nodes.html> - `BatchReplaceClusterNodes`: - Network accessline 28
<https://docs.aws.amazon.com/cli/latest/reference/sagemaker/batch-reboot-cluster-nodes.html> - Network accessline 29
- `BatchReplaceClusterNodes`: <https://docs.aws.amazon.com/cli/latest/reference/sagemaker/batch-replace-cluster-nodes.html> - `scontrol(1)`: <https://slurm.schedmd.com/scontrol.html> - Network accessline 30
<https://docs.aws.amazon.com/cli/latest/reference/sagemaker/batch-replace-cluster-nodes.html> - Network accessline 31
- `scontrol(1)`: <https://slurm.schedmd.com/scontrol.html> - Network accessline 32
- `slurmctld(8)`: <https://slurm.schedmd.com/slurmctld.html> - Network accessline 33
- `slurm.conf(5)`: <https://slurm.schedmd.com/slurm.conf.html> - Network accessline 34
- Slurm accounting: <https://slurm.schedmd.com/accounting.html> - Network accessline 35
- Slurm authentication (munge): <https://slurm.schedmd.com/authentication.html> - Network accessline 63
<https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency-slurm-auto-resume.html> - Dangerous shell operationline 69
sudo journalctl -u slurmctld --since "2 hours ago" | grep -E 'auto.?resume|Action:Replace|replac' - Network accessline 126
Re-issue procedure: <https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency-slurm-replace-faulty-instance.html> - Network accessline 159
| ------------------------------- | ------------------------------------------------------------------- | | `slurmd` stopped, logs clean | HyperPod Slurm troubleshooting (Authoritative recovery) | | `slurmd` crashing, munge e - Network accessline 160
| `slurmd` stopped, logs clean | HyperPod Slurm troubleshooting (Authoritative recovery) | | `slurmd` crashing, munge errors | <https://slurm.schedmd.com/authentication.html> | | Disk full - Network accessline 161
| `slurmd` crashing, munge errors | <https://slurm.schedmd.com/authentication.html> | - Network accessline 181
- <https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md> - Network accessline 182
- <https://slurm.schedmd.com/scontrol.html> (`state=resume` semantics) - Network accessline 198
Per [`slurmctld(8)`](https://slurm.schedmd.com/slurmctld.html), without `-c` the restart - Dangerous shell operationline 226
sudo ls -la "$STATE" # should have recent state files - Network accessline 234
- <https://slurm.schedmd.com/slurmctld.html> - Network accessline 235
- <https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md> - Network accessline 244
**`scontrol reconfigure`** — no downtime. Reloads `slurm.conf` in place. Per [`scontrol(1)`](https://slurm.schedmd.com/scontrol.html), cannot change daemons' - Network accessline 245
[`scontrol(1)`](https://slurm.schedmd.com/scontrol.html), cannot change daemons' - Network accessline 247
daemons + commands per [`slurm.conf(5)`](https://slurm.schedmd.com/slurm.conf.html). - Dangerous shell operationline 293
sudo grep -E 'StorageHost|StoragePort|StorageUser' "$SLURMDBD_CONF" - Network accessline 295
nc -vz <StorageHost> <StoragePort> # default port 3306 - Network accessline 300
| Cause | Link | | --------------------------------------------- | ------------------------------------------------ | | `slurmdbd` daemon stopped or crashed - Network accessline 301
| --------------------------------------------- | ------------------------------------------------ | | `slurmdbd` daemon stopped or crashed | <https://slurm.schedmd.com/accounting.html> | | MySQL / MariaDB endpoint unreachable - Network accessline 302
| `slurmdbd` daemon stopped or crashed | <https://slurm.schedmd.com/accounting.html> | - Network accessline 303
| MySQL / MariaDB endpoint unreachable | Restore SG / VPC route; slurmdbd self-recovers | | `slurmdbd.conf` `StoragePass` wrong / rotated | <https://slurm.schedmd.com/slurmdbd.conf.html> | | Disk full on slurmdbd host - Network accessline 304
| `slurmdbd.conf` `StoragePass` wrong / rotated | <https://slurm.schedmd.com/slurmdbd.conf.html> | - Network accessline 306
| Schema migration pending after Slurm upgrade | <https://slurm.schedmd.com/upgrades.html> |
plugins/sagemaker-ai/skills/hyperpod-slurm-debugger/scripts/slurm-diagnose.sh
- Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 141
echo " Install: sudo yum install expect | sudo apt install expect | brew install expect" >&2 - Dangerous shell operationline 212
# command parameter is a fixed `sh -c "echo <BASE64> | base64 -d | bash"`; the - Dangerous shell operationline 250
local wrapper="sh -c \"echo $b64 | base64 -d | bash\"" - Network accessline 250
local wrapper="sh -c \"echo $b64 | base64 -d | bash\"" local params params=$(jq -nc --arg c "$wrapper" '{command: [$c]}') - Network accessline 251
local params params=$(jq -nc --arg c "$wrapper" '{command: [$c]}') local out rc=0 - Network accessline 252
params=$(jq -nc --arg c "$wrapper" '{command: [$c]}') - Network accessline 445
info "(case-sensitive, no spaces, no trailing punctuation)" hint "for re-issue procedure, see:" info " https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency-slurm-replace-faulty-instance.html" - Network accessline 446
hint "for re-issue procedure, see:" info " https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency-slurm-replace-faulty-instance.html" info " references/slurm-details.md#action-reason-string-validation" - Network accessline 447
info " https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency-slurm-replace-faulty-instance.html" - Network accessline 460
info "AWS docs: do NOT change node state or restart slurmctld until this completes." info "If a replacement seems stuck > 30 min, see:" info " https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency-slurm-replace- - Network accessline 461
info "If a replacement seems stuck > 30 min, see:" info " https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency-slurm-replace-faulty-instance.html" fi - Network accessline 462
info " https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency-slurm-replace-faulty-instance.html" - Network accessline 490
info "$(head -3 <<< "$DBD_OUT")" hint "diagnostic and recovery procedure:" info " https://slurm.schedmd.com/accounting.html" - Network accessline 491
hint "diagnostic and recovery procedure:" info " https://slurm.schedmd.com/accounting.html" info " references/slurm-details.md#slurmdbd-connectivity" - Network accessline 492
info " https://slurm.schedmd.com/accounting.html" - Network accessline 535
warn "$CONF_PATH modified ${DELTA}s after slurmctld last started — config may be stale in memory" hint "for the reload-vs-restart decision and procedure, see:" info " https://slurm.schedmd.com/scontrol.html" - Network accessline 536
hint "for the reload-vs-restart decision and procedure, see:" info " https://slurm.schedmd.com/scontrol.html" info " https://slurm.schedmd.com/slurm.conf.html" - Network accessline 537
info " https://slurm.schedmd.com/scontrol.html" - Network accessline 538
info " https://slurm.schedmd.com/slurm.conf.html" - Network accessline 623
if [[ "$disk_num" =~ ^[0-9]+$ && "$disk_num" -ge 95 ]]; then bad " $slurm_node: root volume ${disk} — clean up before any restart" info " HyperPod storage layout: https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubl - Network accessline 624
bad " $slurm_node: root volume ${disk} — clean up before any restart" info " HyperPod storage layout: https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md" ISSUES+=("disk- - Network accessline 625
info " HyperPod storage layout: https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md" - Network accessline 630
bad " $slurm_node: slurmd is '$slurmd_status'" info " for recovery procedure, see:" info " https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md" - Network accessline 631
info " for recovery procedure, see:" info " https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md" fi - Network accessline 632
info " https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md" - Network accessline 635
bad " $slurm_node: srun reports auth/munge error — slurmd-controller trust broken" info " for munge troubleshooting, see Slurm authentication docs:" info " https://slurm.schedmd.com/authentication.html" - Network accessline 636
info " for munge troubleshooting, see Slurm authentication docs:" info " https://slurm.schedmd.com/authentication.html" fi - Network accessline 637
info " https://slurm.schedmd.com/authentication.html" - Network accessline 733
done info " HyperPod Slurm troubleshooting:" info " https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md" - Network accessline 734
info " HyperPod Slurm troubleshooting:" info " https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md" info " diagnostic context: references/slurm-details.md#-b-unexpected-re - Network accessline 735
info " https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md" - Network accessline 744
done info " HyperPod Slurm troubleshooting:" info " https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md" - Network accessline 745
info " HyperPod Slurm troubleshooting:" info " https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md" info " if the node flaps after a manual recovery → route to hyperpod-no - Network accessline 746
info " https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md" - Network accessline 757
hint "Section C — controller-state issue ($CTRL_RESTART_REASON):" info " Slurm slurmctld(8) — for what is preserved across a controller restart:" info " https://slurm.schedmd.com/slurmctld.html" - Network accessline 758
info " Slurm slurmctld(8) — for what is preserved across a controller restart:" info " https://slurm.schedmd.com/slurmctld.html" info " HyperPod Slurm troubleshooting:" - Network accessline 759
info " https://slurm.schedmd.com/slurmctld.html" - Network accessline 760
info " HyperPod Slurm troubleshooting:" info " https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md" if [[ ${#FAIL_NODES[@]} -gt 0 ]]; then - Network accessline 761
info " https://github.com/aws/sagemaker-hyperpod-cluster-setup/blob/troubleshooting-doc-20250917/troubleshoot/index.md" - Network accessline 776
info " the most common cause is --auto-resume on sbatch instead of srun." info " Use SageMaker HyperPod auto-resume:" info " https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency-slurm-auto-resume.html" - Network accessline 777
info " Use SageMaker HyperPod auto-resume:" info " https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency-slurm-auto-resume.html" info " diagnostic context: references/slurm-details.md#hyperpod-auto-resume" - Network accessline 778
info " https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-hyperpod-resiliency-slurm-auto-resume.html"
plugins/sagemaker-ai/skills/hyperpod-ssm/SKILL.md
- Executable scriptline 1
Executable file - Dangerous shell operationline 15
- **`unbuffer`** (from the `expect` package) — wraps `aws ssm start-session` with a PTY so the session-manager-plugin flushes stdout instead of racing to close. Without it, calls intermittently return empty output with `Cannot perform start - Dangerous shell operationline 96
| CloudWatch agent | `sudo systemctl status amazon-cloudwatch-agent` |
plugins/sagemaker-ai/skills/hyperpod-ssm/references/troubleshooting.md
plugins/sagemaker-ai/skills/hyperpod-ssm/scripts/get-cluster-info.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/sagemaker-ai/skills/hyperpod-ssm/scripts/list-nodes.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/sagemaker-ai/skills/hyperpod-ssm/scripts/ssm-exec.sh
- Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 42
trap 'rm -f "$TMPFILE"' EXIT - Network accessline 91
# caller intermittently sees empty stdout even when the command ran. Running # under `unbuffer` (expect) attaches a PTY, which forces line-buffered I/O # and eliminates the race. See https://github.com/aws/amazon-ssm-agent/issues/358. - Network accessline 92
# under `unbuffer` (expect) attaches a PTY, which forces line-buffered I/O # and eliminates the race. See https://github.com/aws/amazon-ssm-agent/issues/358. # If `unbuffer` isn't on PATH, fall back to the bare invocation. - Network accessline 93
# and eliminates the race. See https://github.com/aws/amazon-ssm-agent/issues/358. - Dangerous shell operationline 105
echo " Install with: sudo yum install expect | sudo apt install expect | brew install expect" >&2
plugins/sagemaker-ai/skills/hyperpod-version-checker/SKILL.md
- Executable scriptline 1
Executable file
plugins/sagemaker-ai/skills/hyperpod-version-checker/scripts/hyperpod_check_versions.sh
- Executable scriptline 1
#!/usr/bin/env bash - Network accessline 67
[Credential-related source omitted] - Access to secretsline 68
[Credential-related source omitted] - Network accessline 70
[Credential-related source omitted] - Network accessline 71
[Credential-related source omitted] - Network accessline 72
[Credential-related source omitted] - Access to secretsline 72
[Credential-related source omitted]
plugins/sagemaker-ai/skills/model-deployment/code_templates/deploy-nova-bedrock.py
plugins/sagemaker-ai/skills/model-deployment/code_templates/deploy-nova-sagemaker.py
plugins/sagemaker-ai/skills/model-deployment/code_templates/deploy-oss-bedrock.py
- Executable scriptline 1
Executable file
plugins/sagemaker-ai/skills/model-deployment/code_templates/deploy-oss-sagemaker.py
plugins/sagemaker-ai/skills/model-deployment/references/deploy-nova-sagemaker.md
- Access to secretsline 144
[Credential-related source omitted]
plugins/sagemaker-ai/skills/model-deployment/references/model-licenses.md
- Network accessline 7
| Model ID | License | License URL | Notes - Network accessline 8
| ----------------------------------------------------------- | ------------------------- | ----------------------------------------------------------------------------------- | -------------------------------------------------------------- - Network accessline 9
| `huggingface-reasoning-qwen3-32b` | Apache 2.0 | https://huggingface.co/Qwen/Qwen3-32B/blob/main/LICENSE | Say: "This model is licensed under **Apache 2.0**. Please revi - Network accessline 10
| `huggingface-reasoning-qwen3-14b` | Apache 2.0 | https://huggingface.co/Qwen/Qwen3-14B/blob/main/LICENSE | Say: "This model is licensed under **Apache 2.0**. Please revi - Network accessline 11
| `huggingface-reasoning-qwen3-8b` | Apache 2.0 | https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE | Say: "This model is licensed under **Apache 2.0**. Please revi - Network accessline 12
| `huggingface-reasoning-qwen3-4b` | Apache 2.0 | https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE | Say: "This model is licensed under **Apache 2.0**. Please revi - Network accessline 13
| `huggingface-reasoning-qwen3-1-7b` | Apache 2.0 | https://huggingface.co/Qwen/Qwen3-1.7B/blob/main/LICENSE | Say: "This model is licensed under **Apache 2.0**. Please revi - Network accessline 14
| `huggingface-reasoning-qwen3-06b` | Apache 2.0 | https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE | Say: "This model is licensed under **Apache 2.0**. Please revi - Network accessline 15
| `huggingface-llm-qwen2-5-72b-instruct` | Qwen License Agreement | https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE | Say: "This model is licensed under the **Qwen License Agreemen - Network accessline 16
| `huggingface-llm-qwen2-5-32b-instruct` | Apache 2.0 | https://huggingface.co/Qwen/Qwen2.5-32B-Instruct/blob/main/LICENSE | Say: "This model is licensed under **Apache 2.0**. Please revi - Network accessline 17
| `huggingface-llm-qwen2-5-14b-instruct` | Apache 2.0 | https://huggingface.co/Qwen/Qwen2.5-14B-Instruct/blob/main/LICENSE | Say: "This model is licensed under **Apache 2.0**. Please revi - Network accessline 18
| `huggingface-llm-qwen2-5-7b-instruct` | Apache 2.0 | https://huggingface.co/Qwen/Qwen2.5-7B-Instruct/blob/main/LICENSE | Say: "This model is licensed under **Apache 2.0**. Please revi - Network accessline 19
| `deepseek-llm-r1-distill-llama-70b` | MIT | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B/blob/main/LICENSE | Say: "This model is licensed under **MIT**. Please review the - Network accessline 20
| `deepseek-llm-r1-distill-qwen-32b` | MIT | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/blob/main/LICENSE | Say: "This model is licensed under **MIT**. Please review the - Network accessline 21
| `deepseek-llm-r1-distill-qwen-14b` | MIT | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B/blob/main/LICENSE | Say: "This model is licensed under **MIT**. Please review the - Network accessline 22
| `deepseek-llm-r1-distill-llama-8b` | MIT | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B/blob/main/LICENSE | Say: "This model is licensed under **MIT**. Please review the - Network accessline 23
| `deepseek-llm-r1-distill-qwen-7b` | MIT | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/blob/main/LICENSE | Say: "This model is licensed under **MIT**. Please review the - Network accessline 24
| `deepseek-llm-r1-distill-qwen-1-5b` | MIT | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/blob/main/LICENSE | Say: "This model is licensed under **MIT**. Please review the - Network accessline 25
| `openai-reasoning-gpt-oss-120b` | Apache 2.0 | https://huggingface.co/openai/gpt-oss-120b/blob/main/LICENSE | Say: "This model is licensed under **Apache 2.0**. Please revi - Network accessline 26
| `openai-reasoning-gpt-oss-20b` | Apache 2.0 | https://huggingface.co/openai/gpt-oss-20b/blob/main/LICENSE | Say: "This model is licensed under **Apache 2.0**. Please revi - Network accessline 27
| `meta-textgeneration-llama-3-3-70b-instruct` | Llama 3.3 Community | https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct/blob/main/LICENSE | Say: "This model is licensed under **Llama 3.3 Community Licen - Network accessline 28
| `meta-textgeneration-llama-3-2-3b-instruct` | Llama 3.2 Community | https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/blob/main/LICENSE.txt | Say: "This model is licensed under **Llama 3.2 Community Licen - Network accessline 29
| `meta-textgeneration-llama-3-2-1b-instruct` | Llama 3.2 Community | https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/blob/main/LICENSE.txt | Say: "This model is licensed under **Llama 3.2 Community Licen - Network accessline 30
| `meta-textgeneration-llama-3-1-8b-instruct` | Llama 3.1 Community | https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/blob/main/LICENSE | Say: "This model is licensed under **Llama 3.1 Community Licen - Network accessline 31
| `nova-textgeneration-pro` | AWS Service Terms | https://aws.amazon.com/service-terms/ | Say: "This model is subject to the AWS Service Terms: {URL}. W - Network accessline 32
| `nova-textgeneration-micro` | AWS Service Terms | https://aws.amazon.com/service-terms/ | Say: "This model is subject to the AWS Service Terms: {URL}. W - Network accessline 33
| `nova-textgeneration-lite` | AWS Service Terms | https://aws.amazon.com/service-terms/ | Say: "This model is subject to the AWS Service Terms: {URL}. W - Network accessline 34
| `nova-textgeneration-lite-v2` | AWS Service Terms | https://aws.amazon.com/service-terms/ | Say: "This model is subject to the AWS Service Terms: {URL}. W - Network accessline 35
| `huggingface-reasoning-nvidia-nemotron-3-nano-30b-a3b-bf16` | NVIDIA Open Model License | https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16/blob/main/LICENSE | Say: "This model is licensed under the **NVIDIA Open Model Lic - Network accessline 36
| `huggingface-vlm-qwen3-6-27b` | Apache 2.0 | https://huggingface.co/Qwen/Qwen3-VL-27B/blob/main/LICENSE | Say: "This model is licensed under **Apache 2.0**. Please revi - Network accessline 37
| `huggingface-vlm-qwen3-5-27b` | Apache 2.0 | https://huggingface.co/Qwen/Qwen3-VL-27B/blob/main/LICENSE | Say: "This model is licensed under **Apache 2.0**. Please revi - Network accessline 38
| `huggingface-vlm-qwen3-5-9b` | Apache 2.0 | https://huggingface.co/Qwen/Qwen3-VL-9B/blob/main/LICENSE | Say: "This model is licensed under **Apache 2.0**. Please revi - Network accessline 39
| `huggingface-vlm-qwen3-5-4b` | Apache 2.0 | https://huggingface.co/Qwen/Qwen3-VL-4B/blob/main/LICENSE | Say: "This model is licensed under **Apache 2.0**. Please revi - Network accessline 40
| `huggingface-vlm-gemma-4-31b-it` | Gemma Terms of Use | https://huggingface.co/google/gemma-4-31b-it/blob/main/LICENSE | Say: "This model is licensed under **Gemma Terms of Use**. Ple - Network accessline 41
| `meta-vlm-llama-4-scout-17b-16e-instruct` | Llama 4 Community | https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct/blob/main/LICENSE | Say: "This model is licensed under **Llama 4 Community License
plugins/sagemaker-ai/skills/model-evaluation/code_templates/custom_scorer_evaluator.py
plugins/sagemaker-ai/skills/model-evaluation/code_templates/llmaaj_evaluator.py
plugins/sagemaker-ai/skills/model-evaluation/references/llmaaj-evaluation.md
- Network accessline 55
> "Do you have predefined custom metrics you'd like to use? If so, they must follow the Bedrock custom metrics format: https://docs.aws.amazon.com/bedrock/latest/userguide/model-evaluation-custom-metrics-prompt-formats.html - Network accessline 209
> **Important: Amazon Bedrock Evaluations Terms** > > This feature is powered by Amazon Bedrock Evaluations. Your use of this feature is subject to pricing of Amazon Bedrock Evaluations, the [Service Terms](https://aws.amazon.com/service-te - Network accessline 210
> > This feature is powered by Amazon Bedrock Evaluations. Your use of this feature is subject to pricing of Amazon Bedrock Evaluations, the [Service Terms](https://aws.amazon.com/service-terms/) applicable to Amazon Bedrock, and the terms - Network accessline 211
> This feature is powered by Amazon Bedrock Evaluations. Your use of this feature is subject to pricing of Amazon Bedrock Evaluations, the [Service Terms](https://aws.amazon.com/service-terms/) applicable to Amazon Bedrock, and the terms th
plugins/sagemaker-ai/skills/model-evaluation/references/supported-judge-models.md
- Network accessline 3
Reference: [Amazon Bedrock LLM-as-Judge Evaluation](https://docs.aws.amazon.com/bedrock/latest/userguide/evaluation-judge.html)
plugins/sagemaker-ai/skills/model-evaluation/scripts/nova_reward_function_source_template.py
- Network accessline 1
""" Provide your custom reward function code below. Learn about the available libraries and templates that you can use at: https://docs.aws.amazon.com/sagemaker/latest/dg/customize-model.html. - Executable scriptline 1
Executable file - Network accessline 3
at: https://docs.aws.amazon.com/sagemaker/latest/dg/customize-model.html.
plugins/sagemaker-ai/skills/model-evaluation/scripts/reward_function_source_template.py
- Network accessline 1
""" Provide your custom reward function code below. Learn about the available libraries and templates that you can use at: https://docs.aws.amazon.com/sagemaker/latest/dg/customize-model.html. - Executable scriptline 1
Executable file - Network accessline 3
at: https://docs.aws.amazon.com/sagemaker/latest/dg/customize-model.html.
plugins/sagemaker-ai/skills/model-evaluation/scripts/validate_custom_metrics.py
- Executable scriptline 1
Executable file
plugins/sagemaker-ai/skills/model-selection/SKILL.md
- Network accessline 57
Present all available models to the user with their licenses before making any recommendations. Cross-reference the model list with `references/model-licenses.md` and display each as `<model name> - [<license>](<url>)`. For example: "Qwen3-
plugins/sagemaker-ai/skills/model-selection/references/model-licenses.md
- Network accessline 3
| SageMaker Hub Model ID | Model Name | License URL(s) | | ---------- - Network accessline 4
| ----------------------------------------------------------- | ----------------------------- | --------------------------------------------------------------------------------------------------------------------------------- | | `huggingfa - Network accessline 5
| `huggingface-reasoning-qwen3-32b` | Qwen3-32B | https://huggingface.co/Qwen/Qwen3-32B/blob/main/LICENSE | - Network accessline 6
| `huggingface-reasoning-qwen3-14b` | Qwen3-14B | https://huggingface.co/Qwen/Qwen3-14B/blob/main/LICENSE | - Network accessline 7
| `huggingface-reasoning-qwen3-8b` | Qwen3-8B | https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE | - Network accessline 8
| `huggingface-reasoning-qwen3-4b` | Qwen3-4B | https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE | - Network accessline 9
| `huggingface-reasoning-qwen3-1-7b` | Qwen3-1.7B | https://huggingface.co/Qwen/Qwen3-1.7B/blob/main/LICENSE | - Network accessline 10
| `huggingface-reasoning-qwen3-06b` | Qwen3-0.6B | https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE | - Network accessline 11
| `huggingface-llm-qwen2-5-72b-instruct` | Qwen2.5-72B-Instruct | https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE | - Network accessline 12
| `huggingface-llm-qwen2-5-32b-instruct` | Qwen2.5-32B-Instruct | https://huggingface.co/Qwen/Qwen2.5-32B-Instruct/blob/main/LICENSE | - Network accessline 13
| `huggingface-llm-qwen2-5-14b-instruct` | Qwen2.5-14B-Instruct | https://huggingface.co/Qwen/Qwen2.5-14B-Instruct/blob/main/LICENSE | - Network accessline 14
| `huggingface-llm-qwen2-5-7b-instruct` | Qwen2.5-7B-Instruct | https://huggingface.co/Qwen/Qwen2.5-7B-Instruct/blob/main/LICENSE | - Network accessline 15
| `deepseek-llm-r1-distill-llama-70b` | DeepSeek-R1-Distill-Llama-70B | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B/blob/main/LICENSE | - Network accessline 16
| `deepseek-llm-r1-distill-qwen-32b` | DeepSeek-R1-Distill-Qwen-32B | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/blob/main/LICENSE | - Network accessline 17
| `deepseek-llm-r1-distill-qwen-14b` | DeepSeek-R1-Distill-Qwen-14B | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B/blob/main/LICENSE | - Network accessline 18
| `deepseek-llm-r1-distill-llama-8b` | DeepSeek-R1-Distill-Llama-8B | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B/blob/main/LICENSE | - Network accessline 19
| `deepseek-llm-r1-distill-qwen-7b` | DeepSeek-R1-Distill-Qwen-7B | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/blob/main/LICENSE | - Network accessline 20
| `deepseek-llm-r1-distill-qwen-1-5b` | DeepSeek-R1-Distill-Qwen-1.5B | https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/blob/main/LICENSE | - Network accessline 21
| `openai-reasoning-gpt-oss-120b` | GPT-OSS-120B | https://huggingface.co/openai/gpt-oss-120b/blob/main/LICENSE<br>https://huggingface.co/openai/gpt-oss-120b/blob/main/USAGE_POLICY | - Network accessline 22
| `openai-reasoning-gpt-oss-20b` | GPT-OSS-20B | https://huggingface.co/openai/gpt-oss-20b/blob/main/LICENSE<br>https://huggingface.co/openai/gpt-oss-20b/blob/main/USAGE_POLICY | - Network accessline 23
| `meta-textgeneration-llama-3-3-70b-instruct` | Llama 3.3 70B Instruct | https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct/blob/main/LICENSE | - Network accessline 24
| `meta-textgeneration-llama-3-2-3b-instruct` | Llama 3.2 3B Instruct | https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/blob/main/LICENSE.txt | - Network accessline 25
| `meta-textgeneration-llama-3-2-1b-instruct` | Llama 3.2 1B Instruct | https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/blob/main/LICENSE.txt | - Network accessline 26
| `meta-textgeneration-llama-3-1-8b-instruct` | Llama 3.1 8B Instruct | https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/blob/main/LICENSE | - Network accessline 27
| `nova-textgeneration-pro` | Amazon Nova Pro | https://aws.amazon.com/service-terms/ | - Network accessline 28
| `nova-textgeneration-micro` | Amazon Nova Micro | https://aws.amazon.com/service-terms/ | - Network accessline 29
| `nova-textgeneration-lite` | Amazon Nova Lite | https://aws.amazon.com/service-terms/ | - Network accessline 30
| `nova-textgeneration-lite-v2` | Amazon Nova Lite v2 | https://aws.amazon.com/service-terms/ | - Network accessline 31
| `huggingface-reasoning-nvidia-nemotron-3-nano-30b-a3b-bf16` | Nemotron 3 Nano 30B | https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16/blob/main/LICENSE | - Network accessline 32
| `huggingface-vlm-qwen3-6-27b` | Qwen3.6-27B | https://huggingface.co/Qwen/Qwen3-VL-27B/blob/main/LICENSE | - Network accessline 33
| `huggingface-vlm-qwen3-5-27b` | Qwen3.5-27B | https://huggingface.co/Qwen/Qwen3-VL-27B/blob/main/LICENSE | - Network accessline 34
| `huggingface-vlm-qwen3-5-9b` | Qwen3.5-9B | https://huggingface.co/Qwen/Qwen3-VL-9B/blob/main/LICENSE | - Network accessline 35
| `huggingface-vlm-qwen3-5-4b` | Qwen3.5-4B | https://huggingface.co/Qwen/Qwen3-VL-4B/blob/main/LICENSE | - Network accessline 36
| `huggingface-vlm-gemma-4-31b-it` | Gemma 4 31B | https://huggingface.co/google/gemma-4-31b-it/blob/main/LICENSE | - Network accessline 37
| `meta-vlm-llama-4-scout-17b-16e-instruct` | Llama 4 Scout 17B | https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct/blob/main/LICENSE |
plugins/sagemaker-ai/skills/model-selection/scripts/get_model_names.py
- Executable scriptline 1
Executable file
plugins/sagemaker-ai/skills/sdk-getting-started/references/execution-role-setup.md
- Network accessline 15
> What IAM role should SageMaker use to run jobs? I need the full ARN (e.g., `arn:aws:iam::123456789012:role/MySageMakerRole`). > > If you don't have one yet, see: https://github.com/awslabs/agent-plugins/tree/main/plugins/sagemaker-ai#auth - Network accessline 17
> If you don't have one yet, see: https://github.com/awslabs/agent-plugins/tree/main/plugins/sagemaker-ai#authentication-and-authorization - Network accessline 29
- **AccessDenied** → warn: "⚠<U+FE0F> Cannot verify role (missing iam:GetRole). Proceeding with unverified role." Continue. - **Role found** → check `AssumeRolePolicyDocument` for trust principals: - `sagemaker.amazonaws.com` missing → STOP. Tel - Network accessline 30
- **Role found** → check `AssumeRolePolicyDocument` for trust principals: - `sagemaker.amazonaws.com` missing → STOP. Tell user their role needs `sagemaker.amazonaws.com` in the trust policy. Link to [plugin README](https://github.com/aws - Network accessline 31
- `sagemaker.amazonaws.com` missing → STOP. Tell user their role needs `sagemaker.amazonaws.com` in the trust policy. Link to [plugin README](https://github.com/awslabs/agent-plugins/tree/main/plugins/sagemaker-ai#authentication-and-authori - Network accessline 37
For required IAM permissions and trust policy setup, see the [plugin README — Authentication and Authorization](https://github.com/awslabs/agent-plugins/tree/main/plugins/sagemaker-ai#authentication-and-authorization).
plugins/sagemaker-ai/skills/use-case-specification/SKILL.md
- Network accessline 68
A use case specification is a design principle recommended by the [AWS Responsible AI Lens](https://docs.aws.amazon.com/wellarchitected/latest/responsible-ai-lens/design-principles.html).
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md plugins/amazon-location-service/skills/amazon-location-service/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md plugins/amazon-location-service/skills/amazon-location-service/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Native | Manifest .github/copilot-instructions.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md plugins/amazon-location-service/skills/amazon-location-service/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/awslabs-agent-plugins/)