The Agent Skills Directory

[SAFE]: The skill operates entirely on local project-specific files within the '.codestable/' and 'docs/' directories, with no network access or sensitive file exposure detected.
[SAFE]: Command execution is limited to the invocation of a local script (search-yaml.py) located within the project's own tools directory for metadata search purposes.
[SAFE]: All prompt instructions are task-oriented for documentation workflows and do not include patterns for prompt injection, safety bypass, or role-play-based restrictions removal.

cs-guide