The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run the ls command on various local and system directories (such as ~/.claude/skills/, ~/.agent/skills/, and .agent/skills/) to identify which companion skills are currently installed. This is part of a companion check workflow triggered on first activation.
[EXTERNAL_DOWNLOADS]: The skill provides instructions for the agent to recommend installing additional components via the npx skills add command from the AbsolutelySkilled repository.
[PROMPT_INJECTION]: The skill is designed to analyze project structures and code provided by the user, creating a surface for potential indirect prompt injection.
Ingestion points: Processes user-supplied code and directory structure information through its architectural review and refactoring features in SKILL.md.
Boundary markers: Absent; there are no specific instructions to isolate user input from the agent's internal instructions.
Capability inventory: The skill utilizes file system listing capabilities (ls) as part of its automated dependency checking routine.
Sanitization: Absent; no mention of sanitizing or validating the user-provided data before processing.

clean-architecture