Provides verified corrections for IAM behaviors that AI agents frequently get wrong — policy evaluation edge cases, trust policy gotchas, STS session limits, Organizations quirks, and SAML/MFA specifics. Also provides structured workflows for IAM role management and baseline policy generation from application source code or a Terraform plan JSON.
安装
npx skills add aws/agent-toolkit-for-aws --skill aws-iamnpx skills add aws/agent-toolkit-for-aws --skill aws-iam -a claude-code -gnpx skills add aws/agent-toolkit-for-aws --skill aws-iam -a codex -ggemini skills install https://github.com/aws/agent-toolkit-for-aws.git --path skills/core-skills/aws-iamgh skill install aws/agent-toolkit-for-aws aws-iamgit clone --depth 1 https://github.com/aws/agent-toolkit-for-aws /tmp/aws__agent-toolkit-for-aws
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/aws__agent-toolkit-for-aws/skills/core-skills/aws-iam ~/.claude/skills/aws-iam # Claude Code
cp -R /tmp/aws__agent-toolkit-for-aws/skills/core-skills/aws-iam ~/.agents/skills/aws-iam # Codex, Cursor, Gemini CLI, Copilot, OpenCode