Name: cloud-security
Rating: 72.8 (1 reviews)
Author: alirezarezvani

cloud-security

Use when assessing cloud infrastructure for security misconfigurations, IAM privilege escalation paths, S3 public exposure, open security group rules, or IaC security gaps. Covers AWS, Azure, and GCP posture assessment with MITRE ATT&CK mapping.

Quality

91%

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

The canonical home for this skill is cloud-security in alirezarezvani/claude-skills

Quality

Content

83%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.

A highly actionable, well-sequenced skill body with executable examples and validation-driven workflows. Its weakness is progressive disclosure: large reference tables are inlined rather than split into the referenced (but missing) bundle files, so the SKILL.md carries content that should live one level deeper.

Suggestions

Move the dense lookup tables (IAM Privilege Escalation Patterns, IAM Finding Severity Guide, S3/SG check matrices, Provider Coverage Matrix) into references/ files (e.g. the already-referenced cspm-checks.md) and link them from the body, keeping SKILL.md as an overview.

Create the referenced scripts/cloud_posture_check.py and references/cspm-checks.md so the in-text links resolve to real bundle files rather than dangling references.

Trim restated context Claude already knows — the repeated 'this is NOT incident-response / pen-testing' framing and explanatory sentences bracketing self-explanatory tables — to tighten conciseness toward a lean 5.

Dimension	Reasoning	Score
Conciseness	Mostly efficient: dense reference tables (exit codes, severity matrices, port rules) and executable bash earn their tokens, but the prose restates some concepts Claude already knows (e.g., the 'This is NOT incident response' framing and explanatory sentences around tables) that could be trimmed. Falls just above the midpoint between efficient (4) and lean (5).	4 / 5
Actionability	Copy-paste-ready bash and HCL examples cover the common cases (IAM/S3/SG checks, AWS CLI pipes, CI/CD gating, Terraform bad-vs-good), with concrete flags (--check, --severity-modifier) and exit-code semantics — fully executable guidance.	5 / 5
Workflow Clarity	Three explicitly sequenced workflows (20-min quick check, multi-day assessment, CI/CD gate) with a validation checkpoint: Workflow 3 validates IaC findings via exit code 2 and blocks deployment, and exit codes 0/1/2 define the remediation decision loop. Re-reading anchors, this matches the explicit-validation anchor better than the score-4 'minor validation gaps'.	5 / 5
Progressive Disclosure	The body is a single ~340-line SKILL.md with a heavy inlined reference layer (severity matrices, port tables, coverage matrix) that belongs in separate files, and the only external pointer — 'references/cspm-checks.md' and scripts/cloud_posture_check.py — cannot be verified because references/ and scripts/ directories are absent from the bundle, leaving references structurally buried and unsupported.	3 / 5
	Total	17 / 20 Passed

Description

98%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.

A strong description: third-person voice, explicit 'Use when' trigger, and concrete capability enumeration across three cloud providers with MITRE mapping. No vague fluff or over-claims; every token earns its place.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete assessment targets — 'IAM privilege escalation paths', 'S3 public exposure', 'open security group rules', 'IaC security gaps' — with comprehensive coverage across AWS/Azure/GCP and MITRE mapping, matching the score-5 anchor.	5 / 5
Completeness	Opens with an explicit 'Use when assessing...' trigger clause (the 'when') and follows with the concrete capabilities covered (the 'what'), satisfying both halves with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user-facing phrases ('security misconfigurations', 'IAM privilege escalation', 'S3 public exposure', 'IaC security gaps') plus cloud-specific terms and MITRE ATT&CK, giving comprehensive keyword coverage with synonyms.	5 / 5
Distinctiveness Conflict Risk	The cloud-posture niche is sharply scoped and explicitly contrasted with sibling skills in the body; triggers are distinct from incident-response, threat-detection, and security-pen-testing, minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 suspicious	Warning
referenced_paths_exist	Referenced path issues: 13 missing	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/cloud-security/SKILL.md
Commit: 19392f7

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.