The Agent Skills Directory

[SAFE]: The skill focuses on transforming user prompts into high-quality, professional requests through decomposition, role framing, and precise terminology. All instructions are benign and aligned with its stated purpose.- [COMMAND_EXECUTION]: While the skill's metadata allows access to the Bash tool, the instructions themselves do not contain any logic to execute arbitrary commands or scripts automatically.
[DATA_EXFILTRATION]: There are no indicators of data exfiltration. The WebFetch and WebSearch tools are permitted in the frontmatter but are not used within the skill body to transmit data to external sources.- [PROMPT_INJECTION]: The skill does not attempt to override system prompts, bypass safety filters, or use 'jailbreak' techniques. It aims to improve the quality of a request without changing its original intent.

prompt-enhancer