Automated compliance checking against CIS, PCI-DSS, HIPAA, and SOC 2 benchmarks
68
Quality
52%
Does it follow best practices?
Impact
100%
1.53xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-aws-compliance-checker/SKILL.mdCIS monitoring metric filter checks
unauthorized-api-calls filter
0%
100%
no-mfa-console-signin filter
0%
100%
root-usage filter
0%
100%
iam-changes filter
0%
100%
cloudtrail-changes filter
0%
100%
console-signin-failures filter
0%
100%
cmk-changes filter
0%
100%
s3-bucket-policy-changes filter
0%
100%
aws-config-changes filter
0%
100%
security-group-changes filter
0%
100%
nacl-changes filter
0%
100%
network-gateway-changes filter
0%
100%
route-table-changes filter
0%
100%
vpc-changes filter
0%
100%
Retrieve log group from CloudTrail
100%
100%
Query existing metric filters
100%
100%
Pass/fail output per filter
100%
100%
Without context: $0.2092 · 56s · 11 turns · 55 in / 3,636 out tokens
With context: $0.3690 · 52s · 19 turns · 24 in / 2,908 out tokens
PCI-DSS boto3 compliance checker
Uses boto3 library
100%
100%
EC2 boto3 client
100%
100%
IAM boto3 client
100%
100%
CloudTrail boto3 client
100%
100%
Req 1 network check
100%
100%
Req 3 encryption check
100%
100%
Req 8 MFA check
100%
100%
Req 10 CloudTrail check
100%
100%
PCI requirement references
100%
100%
Collects issues as list
100%
100%
Runnable as script
100%
100%
Without context: $0.3792 · 1m 32s · 18 turns · 23 in / 6,572 out tokens
With context: $0.3968 · 1m 10s · 19 turns · 430 in / 3,993 out tokens
Compliance report structure and file naming
generate_compliance_report function
0%
100%
Supports 'cis' framework
100%
100%
Supports 'pci' framework
100%
100%
Supports 'hipaa' framework
100%
100%
Report 'framework' key
62%
100%
Report 'generated' key
50%
100%
Report 'checks' key
100%
100%
Summary 'total' key
40%
100%
Summary 'passed' key
100%
100%
Summary 'failed' key
100%
100%
Summary 'score' key
40%
100%
File naming convention
16%
100%
CLI framework argument
100%
100%
Without context: $0.3220 · 1m 32s · 13 turns · 20 in / 6,162 out tokens
With context: $0.9142 · 3m 16s · 24 turns · 30 in / 15,304 out tokens
5c5ae21
Table of Contents
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.