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

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/auditing-azure-active-directory-configuration/SKILL.md

Quality

Content

68%Weight 40%Scale 1-5

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

The content is highly actionable with copy-paste commands across a well-sequenced six-step audit, but it inlines material that duplicates an unreferenced bundle file and lacks validation checkpoints for batch enumeration. Linking the existing reference and script files, plus adding completeness checks, would meaningfully raise the score.

Suggestions

Link the existing bundle files from the body (e.g., 'See [api-reference.md](references/api-reference.md) for endpoint details' and 'Run [agent.py](scripts/agent.py) for an automated audit') instead of inlining duplicate Graph API calls.

Add validation/completeness checkpoints for the batch enumeration steps, notably pagination handling for tenants with more than 999 users and confirmation that results are complete before reporting.

Trim or move the 'Key Concepts' definitions into the reference file, keeping only audit-specific framing that Claude would not already know.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with dense executable commands and minimal padding, though the 'Key Concepts' table spends tokens defining terms (e.g., Conditional Access, Legacy Authentication) that are partly explanatory rather than strictly necessary.	4 / 5
Actionability	All six workflow steps provide copy-paste ready PowerShell and az CLI commands hitting real Microsoft Graph endpoints, covering the common audit cases with concrete executable guidance.	5 / 5
Workflow Clarity	The six steps are clearly sequenced, but validation checkpoints and feedback loops are absent; for batch enumeration operations this leaves gaps (e.g., no pagination handling beyond $top 999, no verification of result completeness), matching the anchor with steps present but checkpoints missing.	3 / 5
Progressive Disclosure	Bundle files exist (references/api-reference.md, scripts/agent.py) but the body never links to or signals them, inlining Graph API calls that duplicate the reference file and leaving the provided scripts and references effectively buried and unnavigable.	2 / 5
	Total	14 / 20 Passed

Description

75%Weight 40%Scale 1-5

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

The description is specific, well-tooled, and distinct, but omits any explicit 'when to use' trigger guidance, which caps its completeness. Adding a concrete 'Use when...' clause would raise the score.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases (e.g., 'Use when auditing an Azure/Entra ID tenant's identity posture, reviewing conditional access coverage, or assessing privileged role assignments').

Include natural synonyms users might say, such as 'Azure AD audit', 'tenant security review', or 'MFA enforcement check', to broaden trigger term coverage.

Rephrase the gerund 'Auditing...to identify' as a third-person verb ('Audits...and identifies') for tighter voice and clearer capability framing.

Dimension	Reasoning	Score
Specificity	Names five concrete audit actions ('identify risky authentication policies, overly permissive role assignments, stale accounts, conditional access gaps, and guest user risks') plus specific tools, giving comprehensive coverage rather than just several actions.	5 / 5
Completeness	The description clearly states what the skill does but includes no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Strong natural keywords ('Azure Active Directory', 'Microsoft Entra ID', 'conditional access', 'role assignments', 'guest users') but missing common synonyms a user might say like 'Azure AD audit' or 'tenant review'.	4 / 5
Distinctiveness Conflict Risk	Clearly niched to Entra ID / Azure AD configuration auditing with named tools (AzureAD PowerShell, Microsoft Graph API, ScoutSuite), giving minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 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
Path: skills/auditing-azure-active-directory-configuration/SKILL.md
Commit: 54a7988

Reviewed: ~3 hours 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.