The Agent Skills Directory

Standard Command Execution: The skill involves executing common development commands like dotnet build, pytest --collect-only, and mvn test-compile to validate changes and discover tests. These operations are performed as part of a typical development workflow to ensure project integrity.
Automated Source Editing: The skill includes functionality to automatically modify source files by adding framework-specific attributes (e.g., [TestCategory], @pytest.mark). This direct interaction with codebase files is necessary for its primary function of tagging tests.
Indirect Prompt Injection Surface: The skill analyzes user-provided source code (method names, assertions, comments) to classify tests. This processing of external, untrusted content represents a surface where specifically crafted code could theoretically influence the classification logic, although the use of a fixed taxonomy serves as a mitigation.
Ingestion points: Reads test files and project configuration to detect language, framework, and test methods (Step 1, Step 2).
Boundary markers: None explicitly defined for the ingested code content.
Capability inventory: Modifies source files (auto-edit) and executes shell commands for project validation (Validation section).
Sanitization: Relies on specific heuristics and a predefined taxonomy to determine appropriate tags.

test-tagging