The Agent Skills Directory

Command Execution: The skill identifies and executes .NET test runners (e.g., dotnet test, vstest.console.exe, MSBuild.exe). This is the primary function of the skill and is triggered based on user intent and repository structure.
Indirect Prompt Injection Surface: The skill is designed to read and follow instructions from a local file (.agents/skill-overlays/dotnet-test/run-tests.md). This "overlay" mechanism allows the repository content to influence the agent's behavior.
Ingestion points: Reads .agents/skill-overlays/dotnet-test/run-tests.md at the repository root.
Boundary markers: Requires specific frontmatter (core: dotnet-test/run-tests, binding-revision: "1", and mode: extend) and explicit user instructions win over the overlay.
Capability inventory: Executes shell commands for building and testing code.
Sanitization: The skill performs validation of the overlay's metadata before application.

run-tests