Deploys any application, database, Helm chart, or Terraform module to Kubernetes via Qovery. Analyzes the user's codebase, creates missing Dockerfiles, provisions databases (container or managed), sets up environment variables, and deploys via Qovery CLI + API or Terraform provider. Supports Node.js, Python, Go, Java, Ruby, PHP, .NET, React, Vite, Next.js and more. Use when the user asks to deploy, ship, set up, or release an application on Qovery or Kubernetes via Qovery.
Guided onboarding for new Qovery users. Acts as a personal cloud architect — collects the user's role, experience level, industry, compliance needs, and constraints, then recommends and sets up the optimal Qovery configuration. Handles cloud provider selection, cluster creation (managed or BYOK), project/environment structure, security defaults, cost defaults, team invitations, and migration from other platforms (Heroku, Vercel, Render). Use when a user is new to Qovery or wants to set up the platform from scratch.
Reduces Kubernetes cluster and application costs on Qovery. Analyzes historical resource consumption, factors in the user's business context (seasonal patterns, growth stage, reliability requirements), estimates external resource costs from public cloud pricing, and proposes right-sizing, autoscaling, environment scheduling, spot instances, and database mode changes. Generates a cost report with CSV export and applies changes via CLI+API or Terraform. Use when the user asks to reduce costs, right-size, or optimize Qovery resource spend.
Creates temporary preview environments from pull requests via Qovery. Detects or creates a blueprint environment, clones it for each PR, switches git branches, configures auto-shutdown, and handles cleanup. Supports full-stack and single-service previews. Use when the user asks for a PR preview, branch preview, ephemeral environment, or per-PR deployment on Qovery.
Speeds up Qovery deployments. Analyzes deployment timelines via the V2 deployment history API, identifies bottlenecks (build, startup, health check, scheduling, image pull), classifies them as user-controllable or Qovery infrastructure, and proposes fixes — Dockerfile optimization, build cache strategies, health check tuning, deployment stage parallelism, image pull optimization. Generates a diagnostic report for Qovery support when the bottleneck is infrastructure-side. Use when the user complains about slow deployments or long build times on Qovery.
Generate Terraform manifests from an existing Qovery setup. Reads the current configuration from the Qovery API, generates HCL for the Qovery Terraform provider, imports existing resources into Terraform state, and validates in a test clone. Supports single or multiple environments. Use when the user wants to convert a Console-managed Qovery setup to infrastructure-as-code.
Diagnoses and fixes deployment failures, application crashes, build errors, connectivity problems, stuck deployments, and cluster issues on Qovery. Uses a systematic 8-layer diagnosis with MCP Server integration, CLI, and API, and generates runbooks for recurring issues. Use when the user reports a Qovery deployment that is failing, broken, stuck, or crashing. (For slow deployments use qovery-speedup; for cost optimization use qovery-optimize.)
Route Qovery requests to the right specialized skill and handle quick operations (list, status, stop, restart, logs, clone, scale). Activates on any generic Qovery mention. Use when the user mentions Qovery without a specific action, needs a simple operational command, or wants to discover available Qovery capabilities.