The Agent Skills Directory

[SAFE]: The skill provides professional-grade instructions for code refactoring, emphasizing maintainability, testability, and standard design patterns without introducing dangerous operations.- [EXTERNAL_DOWNLOADS]: The implementation playbook references well-known and trusted development tools such as Ruff, MyPy, ESLint, and SonarQube, as well as established automated review services like GitHub Copilot and CodeRabbit. These references serve as informational guidelines for setting up a standard development environment.- [PROMPT_INJECTION]: The skill is designed to process untrusted code snippets through its refactoring logic. Ingestion points: Untrusted code is provided via the $ARGUMENTS parameter in SKILL.md. Boundary markers: None explicitly defined for the input code block. Capability inventory: The skill has the capability to propose and apply code changes and suggests running test suites. Sanitization: No specific sanitization of the input code is performed by the skill itself, relying on the agent's internal safety filters.

code-refactoring-refactor-clean