The Agent Skills Directory

[SAFE]: The skill is composed exclusively of documentation and reference files in Markdown format. No executable scripts (.py, .js, .sh) or binaries are included.
[SAFE]: No network operations, data exfiltration patterns, or external downloads were detected. The files contain no URLs or remote references.
[SAFE]: No obfuscation techniques, such as Base64 encoding, zero-width characters, or homoglyphs, were found in the provided content.
[SAFE]: The skill includes security-positive instructions in SKILL.md under the 'Non-Negotiable: Self-Contained UML, No Meta Leakage' section, which explicitly forbids the agent from leaking conversation context, user request details, or implementation history into the generated output.

uml-modeling