The Agent Skills Directory

[SAFE]: The skill operates entirely within its stated purpose of diagram generation, utilizing a structured approach to manage user requirements and technical output.
[SAFE]: No network operations are performed. The skill's file access is limited to reading and writing .drawio (XML) files as required for its primary functionality.
[SAFE]: Security and quality are reinforced through a mandatory 9-check validation phase (references/validation-checks.md) that verifies XML integrity, ID uniqueness, edge bindings, and semantic completeness before files are written to disk.
[SAFE]: The sub-agent architecture (Generator, Validator, Fixer) follows modular design principles with clear, task-specific instructions that do not attempt to bypass agent safety filters or override system prompts.
[SAFE]: Metadata and author information are consistent with the vendor's known patterns, and all installation references point to official repositories without signs of typosquatting or impersonation.

drawio-generator