The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @total-typescript/shoehorn package from the NPM registry. This is a well-known utility library in the TypeScript ecosystem used for creating type-safe partial objects in tests.
[COMMAND_EXECUTION]: The skill utilizes the grep command to recursively search for TypeScript type assertions (as Type) within test files. This is a standard and benign use of shell tooling for code analysis.
[INDIRECT_PROMPT_INJECTION]: The skill reads and processes the content of local test files (*.test.ts, *.spec.ts). This creates a potential surface for indirect prompt injection if the files being refactored contain malicious instructions, though this is a necessary part of its refactoring functionality.
Ingestion points: Local files matched by the grep search in the SKILL.md workflow.
Boundary markers: The skill does not explicitly define delimiters for the code it processes.
Capability inventory: The skill performs package installation via npm, searches files using grep, and performs text replacement.
Sanitization: No specific sanitization or filtering of the ingested file content is mentioned.

migrate-to-shoehorn