The Agent Skills Directory

[SAFE]: The skill consists entirely of behavioral instructions and natural language prompts. It does not include any scripts, executable files, or tool configurations that could pose a security risk.
[NO_CODE]: No code or scripts were detected in the skill. The instructions focus on establishing a logical framework for human-AI interaction during troubleshooting tasks.
[PROMPT_INJECTION]: The skill uses authoritative language to define the agent's behavior (e.g., 'Recite verbatim', 'Operating rules'), but these instructions are limited to the debugging workflow and do not attempt to bypass safety filters, extract system prompts, or override platform security constraints.

debug-mantra