The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation providing guidelines for software architecture. It does not contain any executable scripts, network operations, or sensitive file access.
[NO_CODE]: No scripts, executables, or command-line operations are included in the skill. It functions as a set of reference documents for the agent.
[PROMPT_INJECTION]: The instructions use strong imperative language (e.g., 'MUST', 'OBEY'), but these are domain-specific architectural constraints intended to guide software design output, not to bypass safety filters or override core agent behavior.

clean-architecture