iam
AWS Identity and Access Management for users, roles, policies, and permissions. Use when creating IAM policies, configuring cross-account access, setting up service roles, troubleshooting permission errors, or managing access control.
86
82%
Does it follow best practices?
Impact
94%
1.04xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that follows best practices. It uses third person voice, provides specific concrete actions, includes a comprehensive 'Use when...' clause with natural trigger terms, and is clearly distinguishable from other skills through AWS IAM-specific terminology.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'creating IAM policies, configuring cross-account access, setting up service roles, troubleshooting permission errors, managing access control' - these are distinct, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('AWS Identity and Access Management for users, roles, policies, and permissions') and when with explicit 'Use when...' clause listing five specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'IAM', 'policies', 'permissions', 'cross-account access', 'service roles', 'permission errors', 'access control' - these match how users naturally describe AWS identity management tasks. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with AWS IAM-specific terminology ('IAM policies', 'cross-account access', 'service roles') that clearly differentiates it from general cloud, security, or other AWS service skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable IAM skill with excellent executable examples in both CLI and Python. The main weaknesses are some unnecessary conceptual explanations that Claude already knows, and missing validation/verification steps in the workflows for operations that could have security implications. The content would benefit from trimming the Core Concepts section and adding explicit verification commands after each IAM modification.
Suggestions
Remove or significantly trim the Core Concepts section—Claude already understands IAM principals, policies, roles, and trust relationships
Add verification steps after IAM operations (e.g., 'aws iam get-role --role-name MyLambdaRole' to confirm creation before attaching policies)
Consider splitting CLI Reference and Best Practices into separate reference files to reduce the main skill's token footprint
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is generally efficient but includes some explanatory text Claude already knows (e.g., 'IAM is foundational to AWS security—every AWS API call is authenticated and authorized through IAM'). The Core Concepts section explains basic IAM concepts that Claude understands well. | 2 / 3 |
Actionability | Excellent executable examples throughout—complete CLI commands with heredocs for JSON policies, full boto3 code snippets, and specific troubleshooting commands. All code is copy-paste ready with realistic ARNs and resource names. | 3 / 3 |
Workflow Clarity | Multi-step processes are shown (create trust policy → create role → attach policy) but lack explicit validation checkpoints. For IAM operations that can lock out access or create security issues, there should be verification steps like confirming role creation succeeded before attaching policies. | 2 / 3 |
Progressive Disclosure | Good table of contents and section organization, but the document is somewhat monolithic at ~200 lines. The CLI Reference table and Best Practices could be separate files. External references are provided but only as documentation links, not as skill-specific detailed guides. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- itsmostafa/aws-agent-skills
- Commit
5df6da7
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.