The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes project-specific test files which act as an untrusted data ingestion surface.
Ingestion points: The agent reads and searches through *.test.ts and *.spec.ts files using grep.
Boundary markers: There are no explicit delimiters or instructions for the agent to ignore instructions embedded within the codebase being modified.
Capability inventory: The skill requires execution of shell commands (npm, grep) and performs file system writes to update assertions.
Sanitization: No validation or sanitization is performed on the content read from the external test files.
[EXTERNAL_DOWNLOADS]: The skill installs the @total-typescript/shoehorn package from the NPM registry. This is a well-known utility library from a reputable source.
[COMMAND_EXECUTION]: The workflow utilizes standard shell commands, including npm install and grep, to discover type assertions and manage project dependencies.

migrate-to-shoehorn