What problem does it solve? AI agents and developers frequently produce incorrect IAM configurations — wrong action names, missing confused deputy protections, unsafe condition operators, and over-permissive policies. This Skill provides verified corrections for these pitfalls plus structured workflows for role management and baseline policy generation. ## Core Features & Use Cases - Verified IAM Edge Cases: Corrections for policy evaluation quirks (ForAnyValue/ForAllValues with Null checks), STS session limits, Organizations behaviors, SAML/MFA specifics, and privilege escalation paths like iam:PassRole with wildcard resources. - IAM Role Management: Structured workflows for creating and maintaining service roles and execution roles with proper trust policies, aws:SourceArn/aws:SourceAccount confused deputy conditions, and scoped permissions. - Policy Generation: Generates baseline IAM policies from application source code or a Terraform plan JSON using the deterministic iam-policy-autopilot tool, with a Service Authorization Reference fallback for unsupported languages. - Use Case: A developer pastes Python boto3 code and asks for the minimal IAM policy — the Skill routes to iam-policy-autopilot with correct flags instead of hand-writing a hallucination-prone policy. ## Quick Start Ask the assistant to generate a least-privilege IAM policy from your application source code or Terraform plan JSON, or to review an IAM role trust policy for confused deputy protection.