The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes existing source code within the project directory to perform audits and refactors. This represents a potential surface for indirect prompt injection if the processed files contain adversarial instructions. However, this functionality is essential for the skill's primary purpose of code migration.
Ingestion points: Reads JavaScript and TypeScript files from the src/ directory, as well as configuration files like package.json and tsconfig.json.
Boundary markers: No explicit delimiters or boundary markers are defined for the ingested code content.
Capability inventory: The skill is capable of renaming files, writing code changes to disk, and executing shell commands for type-checking.
Sanitization: No specific sanitization or filtering of input code is described.
[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as pnpm exec tsc --noEmit and npx tsc --noEmit. These commands are standard for verifying TypeScript compilation and are consistent with the tool's intended use in a development environment.

typescript-refactor