The Agent Skills Directory

[SAFE] (SAFE): The skill consists entirely of markdown-based instructional content. It defines templates, structures, and quality standards for documentation without utilizing any scripts, command-line executions, or system-level access.
[Indirect Prompt Injection] (SAFE): The skill is designed to process technical artifacts such as code and schemas. While this constitutes an ingestion surface for untrusted data, the skill possesses no tools or capabilities (like code execution or network exfiltration) that could be leveraged maliciously if a payload were encountered in the processed code. It acts as a static formatting and summarization guide.

reference-builder