signalbeam-edge

Verify hexagonal architecture layer rules, Result pattern usage, and coding conventions. Use as a quick local check during development — fast and focused on architecture rules only. For full security + quality review, use /code-review instead.

Review code changes for security, architecture, and quality issues. Use for deep PR-level review — checks OWASP vulnerabilities, hexagonal architecture violations, code smells, and test gaps. For a quick architecture-only check, use /check-architecture instead.

Complete current task with all quality gates, code review, QA check, and submit PR. Use when implementation is done and you want to run the full verification pipeline (build, lint, tests, review, QA) and create the pull request.

Complete infrastructure task — lint, validate, review, and submit PR. Use when an infrastructure-only branch is ready for submission — runs Terraform/Helm validation and creates the PR, skipping .NET/frontend checks.

Scaffold a new frontend feature module with page, components, API service, and hooks. Use whenever the user wants to add a new page, dashboard section, UI module, or frontend feature to the React app.

Capture a screenshot of a URL or route with one command. Use whenever the user wants to take a screenshot, capture a page, see what a route looks like, or visually verify a page. Supports mobile viewport with --mobile and unauthenticated mode with --no-auth.

Smoke test the running frontend and API by navigating key routes with Playwright, checking for console errors and broken pages. Use after /run-local or to verify the app works before creating a PR.

Auto-detect changed frontend routes, navigate them with Playwright, take screenshots, and check for console/network errors. Use after implementing a frontend feature to verify it works visually — auto-detects routes from git changes or accepts a route argument. Supports --responsive for mobile testing and --interactive for click testing.

Run .NET tests with smart change detection — auto-detects changed files via git diff and runs only affected test projects. Use whenever the user wants to run tests, verify changes, check if tests pass, run unit tests, integration tests, or test a specific service. Supports service names (e.g., "device-manager", "edge-agent") and aliases (dm, ea, bo, tp, im).

Break down a feature into a structured plan with acceptance criteria, affected services, and implementation tasks. Use for simple features that don't need a full PRD — or when the user describes what they want to build and needs a task breakdown. For complex features needing full requirements, success metrics, and technical planning, use /prd instead.

Generate a Product Requirements Document through guided discovery questions and codebase analysis. Use for complex features that need structured requirements, success metrics, and technical planning before implementation.

QA check to verify implementation matches GitHub issue requirements. Use to validate that all acceptance criteria from the linked issue are met before creating a PR.

Scaffold a new CQRS command with handler, validator, and POST endpoint following project conventions. Use whenever the user wants to add a write operation, mutation, POST/PUT/DELETE endpoint, or any state-changing action to a microservice.

Scaffold a new domain entity with value object ID, aggregate root, factory method, and domain event. Use whenever the user wants to add a new domain concept, database table, persisted object, or aggregate root to the system.

Scaffold a WolverineFx event handler for domain events or integration events. Use whenever the user wants to react to domain events, publish to NATS, send notifications, update read models, or add async side effects.

Scaffold a new Helm chart with standard templates and values. Use when deploying a new microservice or component to Kubernetes and it needs its own chart.

Create an EF Core migration for a specific microservice. Use after adding or modifying entities, DbSets, or entity configurations — migration creation is mandatory for any schema change.

Scaffold a new CQRS query with handler and GET endpoint following project conventions. Use whenever the user wants to add a read endpoint, GET route, list/detail view, or search/filter capability to a microservice.

Scaffold a new Terraform module with variables, main, and outputs. Use when provisioning a new Azure resource (database, cache, storage, etc.) that needs its own Terraform module and Terragrunt wiring.

Create a pull request with a structured description linking to the GitHub issue. Use when ready to push and open a PR — auto-detects changed services/layers and generates a structured PR body with test plan.

Run all linters and formatters — dotnet format, ESLint, helm lint, and terraform validate. Use to verify formatting before a PR. Note that hooks auto-fix on save/commit; this skill is for explicit verification across the full codebase. For infrastructure-only changes, use /infra-lint instead.

Create a feature branch from a GitHub issue and set up the working context. Use whenever starting implementation on a new issue — creates the branch, fetches requirements, and begins building automatically.

Create GitHub issues from a feature plan or PRD — automatically determines single issue vs epic + task issues. Use after /prd or /plan-feature to push tasks to GitHub, or whenever the user wants to create structured issue(s) for a feature.

Investigate and diagnose problems using structured evidence gathering and hypothesis testing. Use whenever something is broken, failing, or behaving unexpectedly — build errors, test failures, runtime exceptions, deployment issues, or performance problems.

Generate or update project documentation from code — API docs, service docs, architecture docs, or runbooks. Use after adding endpoints, entities, events, or infrastructure changes, or when documentation may be stale.

Start the local development environment using .NET Aspire AppHost. Use to spin up all services locally for manual testing — runs PostgreSQL, NATS, Valkey, and all microservices via Aspire.

Run terraform plan for review and optionally apply infrastructure changes. Use when the user wants to preview or deploy infrastructure — always shows the plan before any apply.

Lint Terraform, Terragrunt, and Helm charts only — skips .NET and frontend. Use for infrastructure-only changes when /lint would be overkill.

Plan infrastructure changes — Terraform modules, Helm charts, CI/CD pipelines. Use when the user wants to add or modify cloud infrastructure, Kubernetes resources, or deployment pipelines.