cloud▌

Secure connectivity between on-premises infrastructure and multiple cloud platforms via VPN and dedicated connections. \n \n Supports four cloud providers (AWS, Azure, GCP, OCI) with provider-specific connection types: Site-to-Site VPN, Direct Connect, ExpressRoute, Cloud Interconnect, and FastConnect \n Covers three hybrid network patterns: hub-and-spoke, multi-region, and multi-cloud architectures with BGP dynamic routing and route propagation \n Includes high-availability configurations with

Stateful AI agents on Cloudflare Workers with WebSocket communication, persistent state, and scheduled tasks. \n \n Build agents using the Agents SDK that maintain state across client reconnections and scale via Durable Objects \n Support real-time WebSocket communication, HTTP endpoints, and automatic message history for chat-focused agents \n Schedule background tasks with delay, specific dates, or cron expressions; query state with embedded SQLite \n Extend Agent or AIChatAgent base classes,

Assess and migrate cloud workloads from AWS, GCP, and other providers to Azure services. \n \n Supports Lambda-to-Azure Functions migration with dedicated scenario reference and best practices \n Generates assessment reports mapping source services to Azure equivalents before any code conversion \n Converts source code to target Azure runtime models, with output isolated in a separate <source-folder>-azure/ directory \n Requires sequential phase execution: assessment first, then migration,

Access Azure AI Search, Speech, OpenAI, and Document Intelligence services through unified MCP tools. \n \n AI Search supports full-text, vector, hybrid, and semantic search with built-in AI enrichment for entity extraction and OCR \n Speech service handles real-time and batch speech-to-text transcription, text-to-speech synthesis with neural voices, and speaker diarization \n MCP tools provide direct commands for listing search indexes, querying indexes, transcribing audio, and synthesizing spe

Generate and maintain Terraform code following HashiCorp's official style conventions. \n \n Enforces two-space indentation, lowercase underscore naming, and standard file organization across terraform.tf , providers.tf , main.tf , variables.tf , outputs.tf , and locals.tf \n Requires type and description on all variables and outputs, with validation rules and sensitive flag support for credentials \n Prioritizes for_each over count for dynamic resources, applies security hardening (encryption,

Category: service

Proper Lambda function structure with error handling

Kubernetes workload deployment, configuration, security, and troubleshooting across single and multi-cluster environments. \n \n Covers Deployments, StatefulSets, DaemonSets, Jobs, Helm charts, RBAC policies, NetworkPolicies, and storage configuration with declarative YAML manifests \n Includes troubleshooting workflows for pod crashes, resource analysis, log inspection, and rollback procedures using kubectl commands \n Enforces security best practices: resource limits, health probes, least-priv

Defense-in-depth Kubernetes security through network policies, pod security standards, RBAC, and admission control. \n \n Covers three pod security levels (Privileged, Baseline, Restricted) enforced via namespace labels for graduated security posture \n Provides NetworkPolicy templates for default-deny, service-to-service communication, and DNS egress patterns \n Includes RBAC configuration examples for roles, cluster roles, and bindings to implement least-privilege access \n Demonstrates OPA Ga

Read this section first. The routing contract uses stable skill identifiers such as auth-tool, auth-web, and http-api, so it works across source files, generated artifacts, and local installs.