security by lloydchang
Cloud Compliance Auditor Skill lloydchang/cloud-compliance-auditor
Automated cloud compliance auditing across AWS, Azure, and GCP. Performs security assessments, policy compliance checks, and generates remediation recommendations. Supports multiple compliance frameworks including CIS, NIST, PCI-DSS, HIPAA, and SOC2.
What it changes View full report → Passed 22 of 23 test cases with the skill, and 7 of 23 without it.
Without skill 30%
With skill 96%
Checks it passed that the model alone missed and 13 more in the full report
15 fixed7 passed either way1 still failing0 broke
Pass-rate lift +65 pp
Tokens +71%
Agent turns 0%
Response time -67% Model gemini-3.6-flashMeasured 8/4/2026 v1 22 of 23 cases passed with skill
Use this skill Claude Code DecimalAI agent CLI & files
Save it into your project's skills folder. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/lloydchang-cloud-compliance-auditor/SKILL.md https://app.decimal.ai/s/lloydchang-cloud-compliance-auditor/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add lloydchang-cloud-compliance-auditor, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"
Linked stays up to date: your agents get the author's new versions automatically.
Editable copy is yours to change; the author's updates won't reach it.
Install linked skill Create editable copy
1 · One-time — install the CLI (
docs ↗ )
$ pip install "decimalai>=0.15"Copy
2 · Get the skill — writes .agents/skills/lloydchang-cloud-compliance-auditor/ and pins it in .decimal/skills.lock
$ decimalai skills add lloydchang-cloud-compliance-auditorCopy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/lloydchang-cloud-compliance-auditor/SKILL.md https://app.decimal.ai/s/lloydchang-cloud-compliance-auditor/SKILL.mdCopy
Safety checks: 3 of 3 passed
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt In the auditor tool's YAML configuration, what standard SLA window string is assigned to high severity findings under severity_thresholds?
What was checked, without and with the skill Checked Without skill With skill Specifies within_24h for high severity issues
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 360 lines single file
Cloud Compliance Auditor Skill
Overview
The Cloud Compliance Auditor skill provides comprehensive automated compliance auditing across multi-cloud environments. It continuously monitors cloud resources for security posture, policy compliance, and generates actionable remediation recommendations.
Capabilities
Core Functions
Multi-Cloud Security Analysis : Analyzes AWS Security Hub, Azure Policy, and GCP Security Center findingsCompliance Framework Validation : Checks against CIS, NIST, PCI-DSS, HIPAA, and SOC2 standardsAutomated Remediation : Generates and applies automated remediation for common compliance violationsComprehensive Reporting : Produces detailed compliance reports with executive summaries
Supported Cloud Providers
AWS : Security Hub, Config, GuardDuty, IAM, CloudTrailAzure : Security Center, Policy, Sentinel, Azure ADGCP : Security Command Center, Cloud Asset Inventory, IAM audit logs
Compliance Frameworks
CIS Controls : Center for Internet Security benchmarksNIST : National Institute of Standards and Technology frameworksPCI-DSS : Payment Card Industry Data Security StandardHIPAA : Health Insurance Portability and Accountability ActSOC2 : Service Organization Control 2
Usage
Basic Compliance Check
# Run compliance audit across all clouds
skill invoke cloud-compliance-auditor audit --framework CIS --severity HIGH
# Audit specific AWS account
skill invoke cloud-compliance-auditor aws-audit --account-id 123456789012 --region us-east-1
Track record Benchmark 22 / 23
test cases passed, vs 7 / 23 without
Adoption
Users 5
Times used 77 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported lloydchang / agentic-reconciliation-engine
core/ai/skills/cloud-compliance-auditor/SKILL.md
View on GitHub ↗ License AGPL-3.0Imported 8/1/2026Version v1