The Agent Skills Directory

[SAFE]: The skill consists solely of natural language instructions within a markdown file. It contains no executable code, scripts, or external dependencies.
[SAFE]: No network operations, sensitive file access patterns, or credential harvesting attempts were detected.
[SAFE]: The 'self-firing' instructions directed at the agent are functional quality-control heuristics intended to trigger task self-correction. They do not attempt to bypass safety filters, jailbreak the model, or exfiltrate data.
[NO_CODE]: The skill does not provide or call any tools or scripts; it functions as a conceptual framework for the agent to follow during its reasoning process.

thebar