The Agent Skills Directory

[PROMPT_INJECTION]: The skill instructions use authoritative language (e.g., 'Zero tolerance', 'No judgement required') and complex multi-phase logic to enforce specific formatting and stylistic transformations. While static detectors may flag these as attempts to bypass policy, the instructions are strictly focused on removing AI-specific writing patterns (slop) rather than bypassing safety filters or security protocols.
[NO_CODE]: The skill consists entirely of Markdown instructions and voice resource templates. It does not contain any executable scripts, binary files, or network-capable tools, which significantly limits the risk of malicious activity.

rewrite-slop