The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown instructions and examples for a decision-making framework. There is no code, shell scripts, or executable logic included within the files.- [DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or data exfiltration mechanisms were detected.- [REMOTE_CODE_EXECUTION]: The skill does not perform any network operations, package installations, or remote script execution. All external references are to standard academic sources and official vendor repositories.- [PROMPT_INJECTION]: The instructions are focused on guiding the user through a specific philosophical process and do not contain any patterns intended to bypass AI safety guardrails or override system instructions.

middle-way