air-gapped
Official@air-gapped
Specialized infrastructure engineering for air-gapped high-performance inference, Kubernetes orchestration, and secure enterprise software lifecycle management.
Agent Skills by air-gapped
Showing 58 vetted skills indexed across 2 GitHub repositories.
air-gappedansible-idrac-9-10
Branch Ansible playbooks for iDRAC 9/10 authentication and Redfish attribute differences.
air-gappedvllm-benchmarking
Benchmark production vLLM deployments for latency, throughput, and SLO compliance.
air-gappedopen-webui-embeddings
Wire HuggingFace TEI embeddings and reranking into Open WebUI via LiteLLM.
air-gappedthreat-model
Identify codebase threats via the four-question framework and output THREAT_MODEL.md.
air-gappedjinja-expert
Author and debug Jinja2 templates for HuggingFace, Ansible, and Kubernetes workflows.
air-gappedautoresearch
Execute autonomous experiments to improve software artifacts using a measurable metric.
air-gappedvllm-configuration
Configure and verify vLLM deployments in air-gapped environments.
air-gappedjira-confluence-mcp
Configure and harden Jira/Confluence MCP server deployments for air-gapped environments.
air-gappedsecure-boot-cert-rotation
Identify and remediate Secure Boot certificate expiries across Dell iDRAC, Linux hosts, and Harvester/KubeVirt VMs.
air-gappedvllm-gemma-4-31b
Benchmark Gemma-4-31B AWQ-4bit on vLLM for tensor-parallel configuration.
air-gappedgpu-host-tuning
Audit Linux GPU inference hosts for configuration gaps and performance bottlenecks.
air-gappedskill-improver
Automates iterative improvement of Claude Code skills via a scoring and mutation loop.
air-gappedvuln-scan
Scan codebases statically and output VULN-FINDINGS.json and VULN-FINDINGS.md.
air-gappedvllm-observability
Standardize Prometheus metrics, dashboards, and tracing guidance for vLLM deployments.
air-gappedbaml-expert
Generate typed Python clients from .baml sources with streaming support.
air-gappedvllm-quantization
Quantize LLM checkpoints for vLLM serving with FP8, NVFP4, and MXFP4 formats.
air-gappedvllm-reasoning-parsers
Map vLLM reasoning parsers for start/end tokens and streaming behavior.
air-gappedopenshift-app
Package, build, secure, and deploy applications on OpenShift Container Platform.
air-gappedaiperf
Benchmark latency, throughput, and telemetry across OpenAI-compatible inference servers.
air-gappedlmcache-mp
Run LMCache MP to share KV caches among vLLM pods in Kubernetes clusters.
air-gappedtriage
Verify, deduplicate, rank, and route security findings into TRIAGE.json and TRIAGE.md.
air-gappedvllm-performance-tuning
Optimize vLLM MoE performance tuning workflows across GPU hardware configurations.
air-gappedjira-best-practices
Map Jira work items to role-based container, deliverable, and breakdown hierarchies.
air-gappednvidia-nixl
Coordinate cross-node memory transfers and metadata exchange with NIXL.
Frequently Asked Questions About air-gapped
FAQPage SchemaWhat specific tasks can be performed using these infrastructure skills?▼
These skills enable the deployment, benchmarking, and optimization of inference clusters, secure management of Jira/Confluence instances, and validation of Kubernetes upgrade readiness in air-gapped environments.
Which technical personas benefit most from these capabilities?▼
Platform engineers, site reliability engineers, and security architects operating in restricted or high-security environments will find these skills essential for managing complex inference stacks and enterprise software governance.
What are the prerequisites for implementing these deployment patterns?▼
Successful implementation requires existing Kubernetes or OpenShift clusters, NVIDIA datacenter hardware, and access to internal container registries for air-gapped image distribution and configuration management.