The Agent Skills Directory

[SAFE]: The skill's instructions are focused solely on refactoring local C# source code for readability. The stated purpose matches the implementation, and there are no attempts to override agent safety protocols, exfiltrate credentials, or establish persistence.
[COMMAND_EXECUTION]: The skill directs the agent to use the dotnet CLI for building and testing the project. These are standard operations for a C# development environment intended to ensure the formatting changes do not introduce syntax errors or regressions.
[INDIRECT_PROMPT_INJECTION]: The skill reads and processes user-controlled source code files, which constitutes a potential attack surface. However, the instructions constrain the agent to identifying specific structural syntax (method and delegate declarations), which mitigates the risk of the agent following instructions embedded in code comments or string literals.
Ingestion points: All non-generated .cs files in the repository.
Boundary markers: No specific delimiters or safety warnings are instructed for the ingested file content.
Capability inventory: The agent is authorized to modify files on disk and execute dotnet build/test commands.
Sanitization: No explicit sanitization or filtering of file content is specified beyond identifying declaration patterns.

format-params