The Agent Skills Directory

[NO_CODE]: The skill consists entirely of natural language instructions and does not include any scripts, executable files, configuration for external tools, or command execution patterns.
[SAFE]: The content is focused on editing text to remove linguistic patterns typically associated with AI (e.g., specific vocabulary, overused punctuation, and formulaic structures). It encourages the AI to adopt a more specific, opinionated, and varied tone.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process text data from external sources or user input. Although this constitutes an attack surface for indirect prompt injection, the skill does not define any dangerous capabilities (such as network access, file system modifications, or code execution) that could be triggered or abused by malicious instructions hidden within the processed text.

unslop