The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard command-line utilities including git, grep, find, npm, and tsc to analyze codebase structure, detect specific code patterns (smells), and verify the integrity of the project after structural changes via build and test scripts.
[INDIRECT_PROMPT_INJECTION]: As the skill is designed to analyze and modify source code files (*.ts, *.tsx), it inherently interacts with potentially untrusted external content. However, the skill provides specific guidance on implementing safety boundaries (e.g., 'Parse-at-Boundary' pattern) to mitigate risks associated with processing external data in the final application.

typescript-refactoring