The Agent Skills Directory

[COMMAND_EXECUTION]: The skill documentation includes commands for running tests such as pnpm test and pnpm test:coverage. These are standard development operations consistent with the skill's primary purpose.
[EXTERNAL_DOWNLOADS]: Use of the pnpm package manager implies interaction with well-known package registries.
[PROMPT_INJECTION]: The skill processes untrusted source files, creating a potential surface for indirect prompt injection. Ingestion points: Analysis of files and folders specified in the path argument in SKILL.md. Boundary markers: There are no explicit instructions to the agent to treat source file content as untrusted data or use delimiters. Capability inventory: The skill generates code and suggests command execution based on analyzed content. Sanitization: No input validation or sanitization of the source code content is specified.

test-ts