auditing-cloud-with-cis-benchmarks

Audit AWS, Azure, and GCP environments against the CIS Foundations Benchmarks by running automated scans with tools like Prowler and ScoutSuite, interpreting failed controls, and tracking remediation for continuous compliance. Use when conducting a cloud security audit, validating CIS benchmark compliance (CIS v5 AWS, v4 Azure, v4 GCP), or setting up continuous cloud compliance monitoring.

Quality

82%

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

Quality

Content

65%Weight 40%Scale 1-3

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 workflow skill with strong concrete commands, but it loses points for missing validation checkpoints in its destructive remediation steps, some avoidable verbosity, and bundle files that are never linked from the body.

Suggestions

Add explicit validation/verification checkpoints to Step 4 (e.g., re-run the relevant Prowler check or the matching boto3 call after each remediation to confirm the control now passes), since the batch/destructive operations currently lack feedback loops.

Link the existing bundle files from the body (e.g., 'For boto3 check snippets see references/api-reference.md' and 'For a runnable single-account audit see scripts/agent.py') so the inlined commands can be trimmed and the skill uses real progressive disclosure.

Remove or move the ASCII coverage-areas table and the 'Key Concepts' glossary; these largely restate CIS structure Claude already knows and pad the token budget.

Dimension	Reasoning	Score
Conciseness	Mostly high-signal commands and pipelines, but the ASCII coverage-areas table and the 'Key Concepts' glossary explain concepts Claude largely already knows and could be trimmed. Not a 3 because some unnecessary explanation remains; not a 1 because it is not padded with basic filler.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands throughout (prowler scans, aws iam/s3api/cloudtrail/securityhub calls, jq parsing pipelines), matching the 'fully executable code/commands' anchor.	3 / 3
Workflow Clarity	A clear 5-step sequence exists, but Step 4 performs batch/destructive remediation (deleting root keys, bulk-enforcing encryption) with no validation or verification checkpoint, which caps workflow clarity at 2 per the destructive-operations guideline.	2 / 3
Progressive Disclosure	The body is well-sectioned but never references the provided bundle files (references/api-reference.md and scripts/agent.py), while inlining detail that could live in them. References present but not signaled and content that should be separate is inline.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 strong, third-person description that names specific tools and concrete actions, includes natural 'Use when' triggers, and is clearly distinguishable from neighboring skills. No fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('running automated scans with tools like Prowler and ScoutSuite, interpreting failed controls, and tracking remediation') plus named tools, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers both what (audit AWS/Azure/GCP against CIS Benchmarks, interpret failures, track remediation) and when via an explicit 'Use when...' clause with multiple triggers.	3 / 3
Trigger Term Quality	Natural trigger phrases users would say ('conducting a cloud security audit', 'validating CIS benchmark compliance', 'setting up continuous cloud compliance monitoring') give good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (CIS benchmark cloud compliance auditing) with distinct triggers and named tools, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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
Path: skills/auditing-cloud-with-cis-benchmarks/SKILL.md
Commit: e612f49

Reviewed: 7 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.