The Agent Skills Directory

[SAFE]: The skill serves as a documentation and scaffolding framework for skill development, containing only instructions and templates with no internal executable scripts.\n- [SAFE]: Includes explicit safety instructions for the agent, such as requiring validation against destructive shell commands (e.g., 'rm -rf') and checking for the presence of secrets or private paths.\n- [COMMAND_EXECUTION]: Instructs the agent on how to use a validation CLI tool named 'skills-ref' to ensure compliance with the Agent Skills specification.\n- [NO_CODE]: The skill is purely informational and does not ship with Python scripts, JavaScript files, or other binary executables.

skill-builder