The Agent Skills Directory

[SAFE]: The skill defines structural patterns and templates for AI agent interactions. It does not contain executable code, scripts, or system commands.
[SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was detected. The instructions focus on improving agent output quality and consistency.
[SAFE]: Tool references such as activate_project and read_memory appear to be part of a local management system and do not involve remote code execution or unauthorized downloads.

workflow-patterns