auditing-azure-active-directory-configuration

Auditing Microsoft Entra ID (Azure Active Directory) configuration to identify risky authentication policies, overly permissive role assignments, stale accounts, conditional access gaps, and guest user risks using AzureAD PowerShell, Microsoft Graph API, and ScoutSuite.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-structured audit skill whose main weaknesses are missing validation checkpoints in the workflow and un-signaled bundle files. Tightening the concept/tool prose and linking the existing references would lift both weak dimensions.

Suggestions

Add explicit validation checkpoints between steps (e.g. confirm Connect-MgGraph succeeded and that each query returned results before proceeding, with a retry/fix loop on errors).

Link the existing bundle files from the body — point the relevant steps to references/api-reference.md for endpoint details and scripts/agent.py for the automated runner — so progressive disclosure is one level deep and clearly signaled.

Trim the 'Key Concepts' and 'Tools & Systems' sections to only terms/tools Claude would not already know, reducing token overhead.

Dimension	Reasoning	Score
Conciseness	The command blocks are lean and actionable, but the 'Key Concepts' table and 'Tools & Systems' section restate well-known Entra ID concepts (Conditional Access, Security Defaults, Legacy Authentication) that Claude already knows, adding unnecessary tokens.	2 / 3
Actionability	Provides fully executable, copy-paste-ready PowerShell and 'az rest'/'az ad' commands with specific Graph endpoints, filters, and JMESPath queries rather than pseudocode.	3 / 3
Workflow Clarity	Six steps are clearly sequenced, but there are no explicit validation/verification checkpoints or error-recovery feedback loops for these tenant-wide batch queries, which caps workflow clarity at 2 per the rubric's destructive/batch-operations guideline.	2 / 3
Progressive Disclosure	Sections are well-organized, but bundle files (references/api-reference.md, scripts/agent.py) exist yet are never referenced or linked from the body, and inline concept/tool content that could live in separate files is not split out.	2 / 3
	Total	9 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-scoped description with strong trigger terms and low conflict risk, weakened only by the absence of an explicit 'when to use' trigger clause. Adding a 'Use when...' sentence would raise completeness to full marks.

Suggestions

Append an explicit trigger clause, e.g. 'Use when auditing an Azure/Entra ID tenant's identity posture, reviewing conditional access and MFA enforcement, or preparing for a compliance/tenant-integration review.'

Keep the concrete action list but pair it with the 'Use when' phrasing so both 'what' and 'when' are explicit.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('identify risky authentication policies, overly permissive role assignments, stale accounts, conditional access gaps, and guest user risks') and names the tools used, matching the multi-action anchor.	3 / 3
Completeness	Clearly states what the skill does but lacks any 'Use when...' clause or equivalent explicit trigger guidance, so the 'when' is only implied — capping completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Covers natural terms a user would say — 'Microsoft Entra ID (Azure Active Directory)', 'conditional access', 'role assignments', 'stale accounts', 'guest user risks', 'AzureAD PowerShell' — with both current and legacy naming variants.	3 / 3
Distinctiveness Conflict Risk	The Azure/Entra ID identity-auditing niche with named tooling is distinct and unlikely to trigger for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: mukul975/Anthropic-Cybersecurity-Skills
Commit: 673da1f

Reviewed: 13 days ago

Table of Contents

Discovery Implementation Validation

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.