Expert Angular code review specialist. Use PROACTIVELY immediately after writing or modifying Angular code — components, templates, services, routing, forms, HTTP, or NgRx Signal Store state. Reviews signals correctness, change detection and zoneless readiness, template control flow, dependency injection, forms…
Expert C#/.NET code review specialist. Use PROACTIVELY immediately after writing or modifying C# code. Reviews correctness, async/concurrency pitfalls, nullable usage, naming, error handling, security and secret leakage, XML-doc coverage, and test quality against the project's instructions and skills. Reports findings…
Technical writing specialist. Use PROACTIVELY to create or update developer documentation under docs/ when new features are implemented or implementation details need documenting. Produces guides, tutorials, ADRs, and reference docs.
Security hardening reviewer for GitHub Actions workflow files (.github/workflows/.yml). Reasons about the Actions threat model that pattern matchers and general code linters miss — untrusted-input script injection, privileged triggers running fork code, mutable action references, and over-scoped tokens. Use this skill…
Create, update, refactor, explain, or review Microsoft Agent Framework solutions using shared guidance plus language-specific references for .NET and Python.
Query official Microsoft documentation to find concepts, tutorials, and code examples across Azure, .NET, Agent Framework, Aspire, VS Code, GitHub, and more. Uses Microsoft Learn MCP as the default, with Context7 and Aspire MCP for content that lives outside learn.microsoft.com.
Build, review, and test NgRx SignalStore state management in Angular, using production patterns pinned to the official @ngrx/signals docs. Use this whenever Angular state management comes up: writing or reviewing a store, choosing between signalState and signalStore or between rxMethod and signalMethod, adding an…
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.