The Agent Skills Directory

[DATA_EXPOSURE]: The skill reads local project metadata and source code files (e.g., .csproj, .sln, Dockerfile, global.json) to assess technology usage and identify applicable breaking changes. This data access is essential for its primary function of project migration.
[COMMAND_EXECUTION]: The workflow involves running standard .NET CLI commands such as dotnet build, dotnet test, and dotnet restore to establish a baseline and verify the integrity of the migrated project.
[EXTERNAL_DOWNLOADS]: The skill references configuration and documentation from well-known and official sources, including Microsoft's documentation and the Microsoft Container Registry (mcr.microsoft.com) for Docker base images.
[INDIRECT_PROMPT_INJECTION]: The skill has the surface area for indirect injection as it processes untrusted local source code and project configuration files.
Ingestion points: Local repository files including source code, project files (.csproj), and configuration files (.json, .props).
Boundary markers: The instructions explicitly direct the agent to treat the provided reference documents as the authoritative source for migration logic, mitigating risks from instructions embedded in user data.
Capability inventory: The skill has the capability to read/write files and execute shell commands via the .NET CLI.
Sanitization: No explicit sanitization of project content is mentioned; the skill relies on the standard operation of the .NET SDK and the structured migration workflow.

migrate-dotnet10-to-dotnet11