chunking-strategy
Provides chunking strategies for RAG systems. Generates chunk size recommendations (256-1024 tokens), overlap percentages (10-20%), and semantic boundary…
Provides AWS CloudFormation patterns for IAM roles, policies, managed policies, permission boundaries, and trust relationships. Use when modeling least-privilege access, cross-account assumptions, service roles, or reusable IAM stacks that other CloudFormation templates consume.
$ npx -y skills add giuseppe-trisciuoglio/developer-kit --skill aws-cloudformation-iam --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/aws-cloudformation-iamContext preview
The summary Claude sees to decide when to auto-load this skill.
Provides AWS CloudFormation patterns for IAM roles, policies, managed policies, permission boundaries, and trust relationships. Use when modeling least-privilege access, cross-account assumptions, service roles, or reusable IAM stacks that other CloudFormation templates consume.
name: aws-cloudformation-iam description: Provides AWS CloudFormation patterns for IAM roles, policies, managed policies, permission boundaries, and trust relationships. Use when modeling least-privilege access, cross-account assumptions, service roles, or reusable IAM stacks that other CloudFormation templates consume. allowed-tools: Read, Write, Bash
Use this skill to model IAM with CloudFormation in a way that stays secure, auditable, and maintainable.
The most important design concerns are:
Do not treat `SKILL.md` as a full IAM encyclopedia. Use the bundled references for larger policy examples and service-specific variants.
Identify who or what assumes the role (service principal, cross-account principal, or federated identity), then write the trust policy with explicit principals and conditions before adding permissions.
Use inline policies for role-specific access; use managed policies for shared patterns across principals. Scope actions and resources tightly, and use conditions where possible.
Use permission boundaries when teams create or extend roles in their own stacks, when guardrails are needed around privileged services (IAM, KMS, Organizations), or to separate maximum allowed permissions from application-specific policies.
Name roles and policies consistently so stack outputs and audits remain easy to trace.
For cross-account roles: trust only the exact source account or principal, add `sts:ExternalId` conditions when appropriate, keep permission and trust policies separate, and export only the ARNs that consuming accounts need.
Before rollout, use these commands to verify the template and IAM behavior:
# Validate CloudFormation template syntax aws cloudformation validate-template --template-body file://template.yaml # Preview changes before applying aws cloudformation create-change-set \ --stack-name <stack-name> \ --template-body file://template.yaml \ --change-set-type CREATE # Simulate whether a principal can perform specific actions aws iam simulate-principal-policy \ --policy-source-arn arn:aws:iam::123456789012:role/LambdaExecutionRole \ --action-names dynamodb:GetItem dynamodb:PutItem # Check for wildcards in IAM policies within the template aws cloudformation list-stack-resources --stack-name <stack-name>
After deployment, confirm policy attachments and stack outputs match the intended security model.
Resources:
LambdaExecutionRole:
Type: AWS::IAM::Role
Properties:
AssumeRolePolicyDocument:
Version: "2012-10-17"
Statement:
- Effect: Allow
Principal:
Service: lambda.amazonaws.com
Action: sts:AssumeRole
Policies:
- PolicyName: DynamoDbWritePolicy
PolicyDocument:
Version: "2012-10-17"
Statement:
- Effect: Allow
Action:
- dynamodb:GetItem
- dynamodb:PutItem
Resource: !GetAtt OrdersTable.ArnResources:
PartnerReadRole:
Type: AWS::IAM::Role
Properties:
AssumeRolePolicyDocument:
Version: "2012-10-17"
Statement:
- Effect: Allow
Principal:
AWS: arn:aws:iam::123456789012:role/partner-reader
Action: sts:AssumeRole
Condition:
StringEquals:
sts:ExternalId: partner-contract-001Keep the trust relationship narrow and pair it with a separate read-only permission policy.
Modular plugin marketplace for Claude Code and agentic CLIs, with validated, spec-driven skills, agents, commands, and workflows for Java, TypeScript, Python, PHP, AWS, and AI.
Repo: giuseppe-trisciuoglio/developer-kit
Provides chunking strategies for RAG systems. Generates chunk size recommendations (256-1024 tokens), overlap percentages (10-20%), and semantic boundary…
Provides workflows to write, debug, and optimize prompts for LLMs, including few-shot example selection, chain-of-thought structuring, system prompt design,…
Implements document chunking, embedding generation, vector storage, and retrieval pipelines for Retrieval-Augmented Generation systems. Use when building RAG…
Provides AWS CloudFormation patterns for Auto Scaling including EC2, ECS, and Lambda. Use when creating Auto Scaling groups, launch configurations, launch…
Provides AWS CloudFormation patterns for Amazon Bedrock resources including agents, knowledge bases, data sources, guardrails, prompts, flows, and inference…
Provides AWS CloudFormation patterns for CloudFront distributions, origins (ALB, S3, Lambda@Edge, VPC Origins), CacheBehaviors, Functions, SecurityHeaders,…