The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional content formatted in Markdown. It defines a high-level approach for an AI agent to follow when refactoring or extending existing codebases to maintain design cleanliness.
[NO_CODE]: There are no scripts, executables, or command-line instructions provided within the skill. All guidance is delivered via natural language instructions.
[INDIRECT_PROMPT_INJECTION]: While the skill is intended to process external code provided by a user, it does not define any executable capabilities (such as network access or file system writes) that could be leveraged for an injection attack. The primary function is to influence the agent's logic for code generation.

strategic-change