The Agent Skills Directory

[SAFE]: The skill's primary function is structured document generation based on interactive user input.
[SAFE]: No network operations, external downloads, or remote code execution patterns were identified. All operations are local to the agent's environment.
[SAFE]: File system access is limited to writing a Markdown file within a predictable project subdirectory (.specs/). The skill includes logic to sanitize user-provided feature names into safe URL-style slugs for directory naming.
[SAFE]: No sensitive file access (e.g., credentials, SSH keys, environment variables) is requested or performed by the skill.
[SAFE]: The instructions do not contain prompt injection patterns or attempts to bypass safety guardrails.

create-tdd