BagelHole/DevOps-Security-Agent-Skills

AI Pipeline Orchestration builds reliable workflows for document ingestion, batch inference, model training, and RAG indexing. Use it to schedule recurring AI jobs and manage dependencies in production pipelines.

AI SRE Incident Response builds runbooks and alerting for LLM outages, quality regressions, safety incidents, and runaway cost events. Use it when AI services need SRE-style monitoring, rollback, and escalation procedures.

AWS CloudTrail configures audit logging for AWS account activity, including organization trails and event selectors. Use it to investigate incidents, meet compliance needs, and alert on sensitive API calls.

Access Review conducts periodic access certifications and reviews across identity systems like AWS IAM, GitHub, and Okta. Use it to find stale accounts, unused permissions, and generate audit evidence for compliance reviews.

Agent Evals builds repeatable tests for AI agent behavior using golden datasets, tool-call checks, safety prompts, and judge-based scoring. Use it to validate prompt changes, catch regressions, and gate deployments on quality.

Agent Observability instruments AI agents with logs, traces, metrics, token usage, latency, and cost telemetry. Use it to debug reliability issues, set SLOs, and monitor agent or LLM workloads.

Asset Inventory maintains an IT asset inventory and CMDB data for hardware, software, cloud resources, and related configuration. Use it when discovering assets, enforcing tags, or preparing compliance audits.

Audit Logging implements centralized audit trails, log retention, and SIEM integration for infrastructure and applications. Use it when you need compliance logging, security monitoring, or forensic analysis.

Azure Monitor Audit configures Azure Monitor, Activity Logs, and Log Analytics for centralized auditing. Use it to collect diagnostic data, enforce diagnostic settings, and investigate security or compliance events in Azure.

Business Continuity Planning helps develop business continuity plans, business impact analyses, communication procedures, and recovery testing. Use it when building organizational resilience or meeting continuity compliance requirements.

Change Management implements structured production change controls, including classification, CAB reviews, change windows, and rollback planning. Use it when managing releases, emergency fixes, and compliance-related change processes.

Disaster Recovery implements disaster recovery strategies, including RTO/RPO planning, cross-region failover, and DR testing. Use it when designing business continuity runbooks and automated failover procedures.

FedRAMP Compliance implements FedRAMP requirements for cloud services used by US federal agencies. Use it to map NIST 800-53 controls, maintain continuous monitoring, and prepare for 3PAO assessments or POA&M tracking.

GCP Audit Logs helps configure Cloud Audit Logs for compliance, security investigation, and operational monitoring. Use it to enable data access logging, route logs to BigQuery or storage, and query activity in GCP.

GDPR Compliance implements GDPR data protection requirements for EU/EEA personal data. Use it for consent management, DSAR workflows, DPIAs, retention, and privacy by design.

HIPAA Compliance implements HIPAA Security, Privacy, and Breach Notification Rule checks for systems that handle ePHI. Use it to configure safeguards, BAAs, encryption, access controls, and incident response.

ISO 27001 Compliance helps implement an Information Security Management System aligned with ISO/IEC 27001:2022. Use it for scope definition, risk assessment, Annex A controls, and audit preparation.

Incident Management implements severity levels, escalation paths, war room procedures, and post-incident reviews for production systems. Use it to coordinate outages, on-call response, and compliance-driven incident handling.

LLM Caching implements exact-match, semantic, and provider-side prompt caching for LLM calls. Use it when repeated or similar prompts need lower API cost, faster responses, or higher throughput.

LLM Cost Optimization reduces API and infrastructure spend with model right-sizing, caching, batching, prompt compression, quantization, and self-hosting. Use it when you need to track AI costs, set budgets, or route requests by cost.

PCI DSS Compliance helps implement PCI DSS v4.0 controls for payment card data in the cardholder data environment. Use it when scoping a CDE, choosing an SAQ, or preparing for PCI assessment and scanning.

Policy As Code implements policy checks with OPA/Rego, Kyverno, and related tools to enforce compliance in CI/CD and infrastructure. Use it to block unsafe Terraform, Kubernetes, and cloud changes before deployment.

Runbook Creation helps document operational procedures, troubleshooting steps, and recovery actions for on-call engineers. Use it when turning tribal knowledge into runbooks or standard operating procedures.

SOC 2 Compliance implements Trust Services Criteria controls, evidence collection, and continuous monitoring for Type I and Type II audits. Use it to map controls, automate auditor evidence, and track security, availability, and integrity requirements.

Vendor Management implements a vendor risk management program for assessing third-party security, tracking contracts, and monitoring SLAs. Use it when onboarding vendors, running reassessments, or preparing SOC 2 and ISO 27001 evidence.