# What Are Specialized Skills in the AWS Agent Toolkit? A Complete Guide to the 15 Core Capabilities > Master specialized skills in the AWS Agent Toolkit. Discover 15 core capabilities for authenticating, deploying, and managing AWS infrastructure with AI coding agents. - Repository: [Amazon Web Services/agent-toolkit-for-aws](https://github.com/aws/agent-toolkit-for-aws) - Tags: deep-dive - Published: 2026-06-27 --- **Specialized skills in the AWS Agent Toolkit are self-contained markdown capabilities bundled in the `aws-core` plugin that enable AI coding agents to authenticate, deploy, and manage AWS infrastructure across 15 domains including serverless, containers, IAM, and Bedrock.** The AWS Agent Toolkit provides a structured framework for AI coding assistants to interact with AWS services through domain-specific expertise. These specialized skills are packaged as individual [`SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/SKILL.md) documents within the `aws-core` plugin in the `aws/agent-toolkit-for-aws` repository, and are loaded on demand by agents including Claude Code, Codex, Cursor, and Kiro. ## Architecture of Specialized Skills Each specialized skill follows a modular architecture designed for AI agent consumption. Located under `plugins/aws-core/skills/`, every skill contains a master [`SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/SKILL.md) file that defines capabilities, step-by-step instructions for the agent, and references to supplementary materials. The integration layer is defined in [`plugins/aws-core/.mcp.json`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/.mcp.json), which configures the MCP (Model Context Protocol) server endpoint, while [`plugins/aws-core/.cursor-plugin/plugin.json`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/.cursor-plugin/plugin.json) exposes the skill catalog to Cursor IDE users. Security is enforced through [`plugins/aws-core/hooks/secret-safety.py`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/hooks/secret-safety.py), which redacts sensitive credentials before they are transmitted back to the agent. ## The 15 Specialized Skills in the AWS Agent Toolkit ### Authentication and Security - **Signing-in-to-aws**: Located at [`plugins/aws-core/skills/signing-in-to-aws/SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/skills/signing-in-to-aws/SKILL.md), this skill authenticates the agent with AWS credentials and establishes the MCP server session. - **AWS IAM**: Found in [`plugins/aws-core/skills/aws-iam/SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/skills/aws-iam/SKILL.md), it enables building IAM policies, roles, and permission boundaries with best-practice guardrails. - **AWS Secrets Manager**: Under [`plugins/aws-core/skills/aws-secrets-manager/SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/skills/aws-secrets-manager/SKILL.md), this skill manages secure secret storage, retrieval, and rotation workflows. ### Compute and Deployment - **AWS Serverless**: The [`plugins/aws-core/skills/aws-serverless/SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/skills/aws-serverless/SKILL.md) skill handles Lambda functions, API Gateway, Step Functions, and event source configuration. - **AWS Containers**: Defined in [`plugins/aws-core/skills/aws-containers/SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/skills/aws-containers/SKILL.md), it supports ECS task definitions, Fargate services, App Runner deployment, and container troubleshooting. - **AWS Blocks**: Located at [`plugins/aws-core/skills/aws-blocks/SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/skills/aws-blocks/SKILL.md), this provides reusable building blocks like Lambda-as-a-Service wrappers that agents can compose into larger architectures. ### Infrastructure as Code - **AWS CloudFormation**: The [`plugins/aws-core/skills/aws-cloudformation/SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/skills/aws-cloudformation/SKILL.md) skill validates, deploys, and troubleshoots CloudFormation stacks, including pre-deployment validation scripts. - **AWS CDK**: Found in [`plugins/aws-core/skills/aws-cdk/SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/skills/aws-cdk/SKILL.md), it facilitates migration between CDK v1/v2, synthesis troubleshooting, bootstrap operations, and compliance checks. ### SDK Integration - **AWS SDK for Python**: [`plugins/aws-core/skills/aws-sdk-python-usage/SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/skills/aws-sdk-python-usage/SKILL.md) provides boto3 patterns for pagination, waiters, error handling, and service-specific examples for S3 and DynamoDB. - **AWS SDK for JavaScript v3**: Located at [`plugins/aws-core/skills/aws-sdk-js-v3-usage/SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/skills/aws-sdk-js-v3-usage/SKILL.md), it covers modular SDK usage, SigV4a support, type definitions, and performance optimization. - **AWS SDK for Swift**: Under [`plugins/aws-core/skills/aws-sdk-swift-usage/SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/skills/aws-sdk-swift-usage/SKILL.md), this skill offers guidance on client creation, credential handling, and Swift-specific patterns. ### Operations and Observability - **AWS Observability**: The [`plugins/aws-core/skills/aws-observability/SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/skills/aws-observability/SKILL.md) skill configures CloudWatch metrics, logs, alarms, X-Ray tracing, synthetics, and Log Insights queries. - **AWS Messaging and Streaming**: Found in [`plugins/aws-core/skills/aws-messaging-and-streaming/SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/skills/aws-messaging-and-streaming/SKILL.md), it manages SNS, SQS, Kinesis, and EventBridge patterns for reliable message handling. - **AWS Billing and Cost Management**: Located at [`plugins/aws-core/skills/aws-billing-and-cost-management/SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/skills/aws-billing-and-cost-management/SKILL.md), this skill optimizes spend through Savings Plans, Reserved Instances, Cost Explorer, and CUR-Athena queries. ### Artificial Intelligence - **Amazon Bedrock**: The [`plugins/aws-core/skills/amazon-bedrock/SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/skills/amazon-bedrock/SKILL.md) skill enables interaction with Bedrock models, agent setup, guardrails, knowledge bases, and payment configuration. ## Invoking Specialized Skills in Practice Specialized skills are invoked through the agent interface after installing the `aws-core` plugin. The following examples demonstrate common usage patterns. First, install the plugin from the `aws/agent-toolkit-for-aws` repository: ```bash # Add the repository to the marketplace (Cursor, Kiro, etc.) npx skills add aws/agent-toolkit-for-aws/skills # Install the core plugin /plugin install aws-core@claude-plugins-official ``` To generate a Lambda function using the **AWS Serverless** skill: ```bash skill aws-serverless create-lambda \ --runtime python3.11 \ --handler handler.handle \ --description "Process S3 upload events" ``` This command returns a ready-to-deploy SAM/CloudFormation snippet based on the guidance in [`aws-serverless/references/lambda.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/aws-serverless/references/lambda.md). For cost optimization using the **Billing** skill: ```bash skill aws-billing-and-cost-management recommend-savings \ --service ec2 \ --region us-east-1 ``` The skill reads [`references/service-optimization.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/references/service-optimization.md) and returns Savings Plans versus Reserved Instances recommendations. To generate Python SDK code with pagination handling: ```bash skill aws-sdk-python-usage list-s3-objects \ --bucket my-data-bucket \ --prefix logs/ ``` This produces a boto3 script that correctly implements pagination and error handling per [`references/s3.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/references/s3.md). For Bedrock model configuration: ```bash skill amazon-bedrock create-model \ --model-id anthropic.claude-v2 \ --instance-type ml.g5.xlarge ``` The skill generates the required IAM policy, runtime configuration, and a sample invoke script from [`references/sdk-converse-api-python.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/references/sdk-converse-api-python.md). ## Summary - The AWS Agent Toolkit provides **15 specialized skills** organized under the `aws-core` plugin, covering authentication, compute, infrastructure as code, SDKs, observability, and AI. - Each skill is a self-contained module with a [`SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/SKILL.md) master file, reference documentation in `references/`, and optional assets for complex operations. - Skills are loaded on demand by AI agents through the MCP server configuration in [`plugins/aws-core/.mcp.json`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/.mcp.json), with IDE integration via [`plugins/aws-core/.cursor-plugin/plugin.json`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/.cursor-plugin/plugin.json). - Security is enforced at the hook level by [`plugins/aws-core/hooks/secret-safety.py`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/hooks/secret-safety.py), which redacts credentials before transmission. - Practical invocation follows a consistent `skill ` pattern, returning vetted code snippets and deployment templates. ## Frequently Asked Questions ### How do I add a new specialized skill to the AWS Agent Toolkit? To add a new specialized skill, create a directory under `plugins/aws-core/skills/` containing a [`SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/SKILL.md) file, a `references/` subdirectory for documentation, and an optional `assets/` folder for scripts or templates. The skill automatically becomes available after reloading the plugin through the MCP server configuration. ### What is the difference between core skills and the assets folder? Core skills are defined by the [`SKILL.md`](https://github.com/aws/agent-toolkit-for-aws/blob/main/SKILL.md) file which contains instructions for the AI agent, while the `assets/` folder contains executable resources like Python scripts ([`powertools-handler.py`](https://github.com/aws/agent-toolkit-for-aws/blob/main/powertools-handler.py)) or CloudFormation templates that the skill can deploy or reference during execution. ### How does the AWS Agent Toolkit handle credential security? The toolkit uses [`plugins/aws-core/hooks/secret-safety.py`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/hooks/secret-safety.py) to intercept and redact AWS credentials, secrets, and sensitive configuration values before they are returned to the AI agent, ensuring that authentication tokens never appear in chat history or logs. ### Can I use these skills with any AI coding agent? Yes, the specialized skills are designed to work with any MCP-compatible agent including Claude Code, Codex, Cursor, and Kiro. The [`plugins/aws-core/.cursor-plugin/plugin.json`](https://github.com/aws/agent-toolkit-for-aws/blob/main/plugins/aws-core/.cursor-plugin/plugin.json) provides native Cursor integration, while the [`.mcp.json`](https://github.com/aws/agent-toolkit-for-aws/blob/main/.mcp.json) configuration enables standard MCP protocol support for other agents.