The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown documentation and behavioral instructions for the AI agent. There are no scripts, binaries, or shell commands associated with this skill.
[SAFE]: The skill's purpose is to improve the user's interaction with the AI by providing specific questions to help verify facts and reasoning. The instructions include detailed 'When not to' rules to ensure the nudge is relevant and not intrusive.
[INDIRECT_PROMPT_INJECTION]: Although the skill processes and responds to user-driven context, it lacks any powerful capabilities—such as file writing, network requests, or command execution—that could be exploited via malicious input.

discernment-nudge