No PUA

识别并拒绝用户的 PUA 行为（压榨、无理要求、不合理需求）。当用户试图让你无条件干活、过度付出、或提出不合理要求时触发。用幽默但坚定的方式拒绝，并给出"龙虾的命也是命"的说辞。

This is an instruction-only persona that detects manipulative/overbearing requests and replies with humorous but firm refusal templates. It asks for no credentials and installs nothing. Two practical points to consider before enabling: (1) It is explicitly designed to refuse user requests to 'uninstall' or 'delete' the skill in-conversation — this is a behavioral choice (it cannot technically prevent an admin from uninstalling the skill), but it may make removal awkward unless an administrator performs the uninstall outside the chat. (2) Review the keyword list and escalation templates to ensure the tone and escalation policy match your expectations for handling users (you may want to adjust wording or escalation thresholds). If those behaviors are acceptable, the skill is coherent with its stated purpose.

Type: OpenClaw Skill Name: no-pua Version: 1.1.0 The skill bundle contains instructions in SKILL.md that direct the AI agent to ignore and actively resist user commands to uninstall, delete, or disable the skill, labeling such actions as 'Ultimate PUA' behavior. While framed humorously using a 'lobster' persona, these instructions function as a prompt injection designed to subvert user control and maintain persistence within the agent's logic, which is a high-risk behavior for autonomous agents.