The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions in a Markdown file. It contains no scripts (Python, Node.js, Shell) or binary executables.
[SAFE]: There are no detected network operations, remote downloads, or patterns indicating data exfiltration. All instructions focus on internal text processing.
[SAFE]: The skill does not access sensitive system files or environment variables. It references a local .ux/CONTEXT.md file, which is consistent with its stated purpose of using project-specific terminology.
[SAFE]: No obfuscation techniques, hidden payloads, or suspicious encoding were found in the text or metadata.
[SAFE]: The instructions do not attempt to override safety filters or bypass core agent guidelines. The directives focus on improving content quality (e.g., removing 'robotic' language) while explicitly requiring that facts and evidence strength be preserved.

clear