Design and build AI agents with persistent memory, tool use, and multi-turn conversation. Covers architecture selection, memory design, model selection, tool configuration, and implementation patterns across agent frameworks. Use when creating, debugging, or improving AI agents.
Automate configuration management and application deployment with Ansible. Use when tasks mention ansible-playbook, inventory files, Ansible roles, ad-hoc commands, ansible-galaxy, or agentless SSH automation.
Deploy Kubernetes apps declaratively with Argo CD applications and projects. Use when tasks mention argocd, Argo CD, argocd app sync, Application CRD, AppProject, or GitOps with Argo CD.
Generate Astryx design system components, themes, and layouts for React 19 applications. Use when building UIs with @astryxdesign/core, creating or extending themes with defineTheme, styling components with StyleX or Tailwind, scaffolding pages from templates, migrating from shadcn or Radix, or working with the Astryx…
Query Datadog observability data including logs, metrics, monitors, dashboards, hosts, APM spans, and incidents via direct API. Use when investigating production issues, checking monitors, searching logs, alerting, or accessing Datadog data.
Build, run, debug, and manage Docker containers, images, compose files, networking, volumes, registries, Buildx/Bake, Scout/SBOM, Swarm, and Docker AI tooling. Use when the user mentions docker, containers, containerizing, Dockerfile, compose, image registry, volumes, or any docker subcommand.
Write and maintain GitHub Actions CI workflows, including workflow YAML structure, triggers, runners, matrix builds, caching, testing patterns, and secrets management. Use when working with .github/workflows, GitHub Actions, CI pipelines, workflow dispatch, or action configuration.
GitHub operations via gh CLI for issues, PRs, CI runs, code review, and API queries. Use when checking PR status or CI, creating or commenting on issues, listing or filtering PRs and issues, or viewing run logs.
Package and deploy Kubernetes applications with Helm charts and releases. Use when tasks mention helm, Helm charts, helm install, helm upgrade, Helm repositories, values.yaml, or Helm releases.
Manage Kubernetes resources, contexts, and workloads with kubectl. Use when tasks mention kubectl, Kubernetes resources, kubeconfig, kubectl apply, kubectl get pods, Kubernetes contexts, or KUBECONFIG.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Specialized agent for MedusaJS v2.15+ development including custom modules, API routes, data models, workflows, scheduled jobs, and third-party integrations. Provides expert guidance on commerce platform architecture and plugin development.
Generate and validate Mermaid.js diagrams from text descriptions. Use when creating flowcharts, sequence diagrams, Gantt charts, class diagrams, state diagrams, ER diagrams, git graphs, user journeys, quadrant charts, XY charts, pie charts, architecture diagrams, block diagrams, requirement diagrams, treemaps…
Manage cloud infrastructure with Pulumi using general-purpose programming languages. Use when tasks mention pulumi commands, Pulumi stacks, infrastructure as code in TypeScript/Python/Go/C#, or deploying with pulumi up.
Inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API. Perform read-only queries with the bundled script. Requires SENTRYAUTHTOKEN. Use when investigating production errors, checking Sentry issues, or reviewing error trends.
Convert data into Standard.site AT Protocol lexicon records and validate them against official schemas. Use when creating or verifying site.standard.publication, site.standard.document, site.standard.graph.subscription, site.standard.graph.recommend, or site.standard.theme.basic records — even if the user doesn't name…
Plan, apply, and manage infrastructure with Terraform. Use when tasks mention terraform commands, HCL configuration, provider setup, state management, or workspace operations.