BagelHole/DevOps-Security-Agent-Skills

ai-pipeline-orchestration

Orchestrate AI/ML pipelines for data ingestion, model training, batch inference, and RAG indexing using Prefect, Airflow, or Dagster. Build reliable, observable, and retriable workflows for production AI systems.

原文の言語: 英語

llm-caching

Implement multi-layer LLM caching with exact match, semantic similarity, and provider-side prompt caching. Reduce API costs by 30–70%, cut latency, and improve throughput using Redis, GPTCache, and provider caching APIs.

原文の言語: 英語

llm-cost-optimization

Reduce LLM API and infrastructure costs through model selection, prompt caching, batching, caching, quantization, and self-hosting strategies. Track spend by team and model, set budgets, and implement cost-aware routing.

原文の言語: 英語

sre-dashboards

Design and operationalize SRE dashboards that surface reliability, latency, error, saturation, and capacity signals across services. Use when building observability views for SLOs, incident response, and executive reliability reporting.

原文の言語: 英語

model-serving-kubernetes

Deploy ML models on Kubernetes with KServe (formerly KFServing) and NVIDIA Triton Inference Server. Includes canary deployments, autoscaling, model versioning, A/B testing, and GPU resource management for production model serving.

原文の言語: 英語

vector-database-ops

Deploy, manage, and optimize vector databases for AI applications. Covers Qdrant, Weaviate, pgvector, and Pinecone — collection management, indexing strategies, backup, and performance tuning for production RAG and semantic search workloads.

原文の言語: 英語

openclaw-security-hardening

Harden OpenClaw self-hosted environments with baseline host controls, auth tightening, secret handling, network segmentation, and safe update/rollback workflows. Use when deploying OpenClaw in home labs, startups, or production-like local AI infrastructure.

原文の言語: 英語

audit-logging

Implement centralized audit logging and SIEM integration. Configure log retention and security monitoring. Use when implementing audit trail requirements.

原文の言語: 英語

aws-cloudtrail

Configure AWS CloudTrail for audit logging. Set up organization trails and event analysis. Use when auditing AWS activity.

原文の言語: 英語

azure-monitor-audit

Configure Azure Monitor and Activity Log for auditing. Set up diagnostic settings and log analytics. Use when auditing Azure activity.

原文の言語: 英語

gcp-audit-logs

Configure GCP Cloud Audit Logs for compliance. Set up log routing and BigQuery analysis. Use when auditing GCP activity.

原文の言語: 英語

business-continuity

Develop business continuity plans and impact analysis. Implement BCP testing and communication procedures. Use when building organizational resilience.

原文の言語: 英語

disaster-recovery

Implement disaster recovery strategies and runbooks. Configure RPO/RTO targets and failover procedures. Use when planning for business continuity.

原文の言語: 英語

incident-management

Implement incident management processes and escalation procedures. Configure on-call schedules and post-incident reviews. Use when managing production incidents.

原文の言語: 英語

runbook-creation

Create operational runbooks and standard operating procedures. Document troubleshooting guides and recovery procedures. Use when documenting operational knowledge.

原文の言語: 英語

fedramp-compliance

Implement FedRAMP requirements for federal cloud services. Configure NIST 800-53 controls and continuous monitoring. Use when providing cloud services to US federal agencies.

原文の言語: 英語

gdpr-compliance

Implement GDPR data protection requirements. Configure consent management, data subject rights, and privacy by design. Use when processing EU personal data.

原文の言語: 英語

hipaa-compliance

Implement HIPAA security and privacy rules. Configure PHI protections and BAA requirements. Use when handling healthcare data.

原文の言語: 英語

iso27001-compliance

Implement ISO 27001 Information Security Management System. Configure ISMS controls and risk management. Use when implementing enterprise security frameworks.

原文の言語: 英語

pci-dss-compliance

Implement PCI DSS requirements for payment card data. Configure cardholder data environment and security controls. Use when processing payment cards.

原文の言語: 英語

soc2-compliance

Implement SOC 2 Trust Services Criteria. Configure security, availability, and processing integrity controls. Use when achieving SOC 2 certification.

原文の言語: 英語

access-review

Conduct periodic access reviews and certifications. Implement access governance and recertification workflows. Use when managing access compliance.

原文の言語: 英語

asset-inventory

Maintain IT asset inventory and configuration management database. Track hardware, software, and cloud resources. Use when managing IT assets.

原文の言語: 英語

change-management

Implement change management processes. Configure CAB reviews, change windows, and rollback procedures. Use when managing production changes.

原文の言語: 英語

policy-as-code

Implement policy as code with OPA, Sentinel, and Kyverno. Automate policy enforcement in CI/CD and infrastructure. Use when enforcing compliance through automation.

原文の言語: 英語

vendor-management

Implement vendor risk management programs. Assess third-party security and maintain vendor inventory. Use when managing supplier security.

原文の言語: 英語

agent-evals

Build automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates. Use when shipping agent features, validating prompt changes, or gating deployments on quality.

原文の言語: 英語

agent-observability

Instrument AI agents with tracing, token metrics, latency, and cost visibility. Use for reliability and debugging.

原文の言語: 英語

ai-sre-incident-response

Build AI-focused SRE incident response practices for LLM outages, degraded quality, runaway cost events, and safety regressions.

原文の言語: 英語

llmops-platform-engineering

Build production LLMOps platforms with CI/CD, model promotion workflows, evaluation gates, rollback, and governance across cloud and self-hosted inference.

原文の言語: 英語

model-registry-governance

Establish model registry standards, governance controls, metadata schemas, approvals, and lifecycle policies for enterprise AI deployments.

原文の言語: 英語

rag-observability-evals

Monitor and evaluate RAG systems with retrieval quality metrics, groundedness checks, hallucination detection, and continuous regression testing.

原文の言語: 英語

devcontainers-nix

Create reproducible development environments with Dev Containers, Nix flakes, and Devbox for consistent toolchains across teams. Use when onboarding developers, standardizing build environments, or eliminating "works on my machine" problems.

原文の言語: 英語

ebpf-observability

Use eBPF for deep kernel-level observability — trace syscalls, network flows, and application behavior without code changes using Cilium, Tetragon, and bpftrace.

原文の言語: 英語

opentelemetry

Instrument applications and infrastructure with OpenTelemetry for unified traces, metrics, and logs. Use when implementing distributed tracing, service-level troubleshooting, or vendor-neutral observability.

原文の言語: 英語

platform-engineering

Build internal developer platforms (IDPs) with self-service infrastructure, golden paths, and developer portals using Backstage, Crossplane, and score.

原文の言語: 英語

aws-cost-optimization

Reduce AWS spend with rightsizing, autoscaling, commitment planning, and storage lifecycle policies. Use when running FinOps reviews, lowering cloud bills, or improving cost-per-request metrics.

原文の言語: 英語

aws-ec2

Manage EC2 instances, AMIs, and auto-scaling groups. Configure security groups, key pairs, and instance types. Use when deploying compute resources on AWS.

原文の言語: 英語

aws-ecs-fargate

Deploy containers on ECS and Fargate. Configure task definitions, services, and load balancing. Use when running containerized workloads on AWS.

原文の言語: 英語

aws-iam

Manage IAM users, roles, and policies. Implement least-privilege access and security best practices. Use when configuring AWS identity and access management.

原文の言語: 英語