The Agent Skills Directory

SAFE (SAFE): The provided files are purely documentation (Markdown) outlining structural and metadata standards for agent skills. No active code, scripts, or network exfiltration patterns were detected inside the repository.
REMOTE_CODE_EXECUTION (LOW): The specification mentions a validation command npx skills-ref. While npx can be used to execute remote code, it is cited as a developer utility for local validation and is not triggered automatically by the skill's instructions.

skill-creation