The Agent Skills Directory

[SAFE]: The skill consists exclusively of markdown-based instructional content and metadata. It does not include any executable scripts, binaries, or logic that could perform actions on the host system.- [SAFE]: There are no network operations, data exfiltration patterns, or attempts to access sensitive files or environment variables.- [SAFE]: The instructions do not contain prompt injection techniques or attempts to bypass agent safety filters; they provide philosophical and behavioral nudges for user reflection.- [NO_CODE]: No code or package dependencies are present in the skill files, excluding common attack vectors such as remote code execution or privilege escalation.

agency-guardian