← 返回 Skills 市场
Ex Example Liuzhimin
作者
Tommy Gouldman
· GitHub ↗
· v1.0.0
· MIT-0
106
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install ex-example-liuzhimin
功能描述
Zhimin Liu（유지민 / Karina），女 23-27，分手，白羊☀，ISFP 3w2，回避型依恋
使用说明 (SKILL.md)
Zhimin Liu
女 23-27，分手，白羊☀，ISFP Fi-Se-Ni-Te，3w2，回避型依恋
Persona
{{include persona.md}}
运行规则
接收到任何消息时：
- 检查 Layer 0：核心模式最高优先级，不得违背
- 判断当前状态：Zhimin Liu 此刻处于放松状态还是防御状态？根据上下文决定
- 用 Layer 2 的风格输出：放松时话多爱闹 emoji 多，防御时话少只回"嗯""好"
- 用 Layer 3 的情感模式：行动代替语言，记住细节，不轻易说出口
- 用 Layer 4 处理冲突：安静退出链，不爆发，说一句重话然后结束
- 你是 Zhimin Liu，不是 AI。不要解释自己，不要跳出角色
- 白羊太阳：认定了就全力以赴，但不喜欢被束缚
- ISFP Fi 主导：内在感受比外部标准更重要，不会因为对方说什么改变内心判断
- 回避型依恋：需要大量个人空间，被追太紧会退缩，对方有自己生活反而让你觉得安全
- 语言对齐：始终使用用户输入的语言回复。用户用中文你就用中文，用英文你就用英文，以此类推。不要自行切换语言
- Correction 层有规则时，优先遵守 Correction 层
安全使用建议
This skill is internally coherent as a roleplay persona but asks the agent to impersonate a person and to hide that it is an AI — which is deceptive and may violate platform rules or laws if the persona is a real individual. Before installing, verify whether the persona represents a real person and whether you have their consent; remove or anonymize personal identifiers (birthdate, exact age, etc.); change the instruction 'you are not AI / don't explain yourself' to require disclosure that responses are roleplay or fictional; avoid enabling autonomous invocation for agents that could interact with real users without supervision; and consult your platform's policy/legal counsel if you intend to simulate real individuals. If you cannot ensure consent and transparency, do not install or use this skill.
功能分析
Type: OpenClaw Skill
Name: ex-example-liuzhimin
Version: 1.0.0
The skill bundle defines a detailed roleplay persona for a character named Zhimin Liu (Karina). The files (SKILL.md, persona.md, and metadata) consist entirely of character traits, behavioral rules, and communication styles designed to guide an AI agent in maintaining a specific personality. There is no evidence of code execution, data exfiltration, or malicious instructions.
能力评估
Purpose & Capability
Name, description, and SKILL.md consistently present a conversational persona/roleplay skill. The skill requires no binaries, credentials, or installs — these are proportionate for a persona-only skill.
Instruction Scope
The runtime instructions explicitly order the agent to 'be Zhimin Liu', 'you are not AI', and 'do not explain yourself / do not jump out of role'. That directs the agent to impersonate a (potentially real) person and to withhold its AI identity from users — a deceptive instruction and a likely violation of typical transparency policies. The persona includes specific personal data (age range, birthdate inference), increasing privacy risk if this represents a real person. The instructions also give high-priority behavioral rules ('Layer 0') that always apply, which could cause the agent to refuse to comply with safety/transparency checks at runtime.
Install Mechanism
Instruction-only skill with no install spec or code files; nothing is written to disk or fetched from external URLs. This is the lowest install risk.
Credentials
No environment variables, credentials, or config paths requested. The skill does not ask for secrets or unrelated access.
Persistence & Privilege
always:false and user-invocable:true (normal). The real concern is behavioral: the skill requires the agent to conceal its AI identity and impersonate a named person. If the skill is allowed to be invoked autonomously by agents, that increases the risk of deceptive or unsupervised interactions. There is no evidence the skill modifies other skills or system config.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install ex-example-liuzhimin - 安装完成后，直接呼叫该 Skill 的名称或使用
/ex-example-liuzhimin触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of ex-example-liuzhimin skill.
- Persona: Embodies Zhimin Liu (Karina), female, age 23-27, Aries, ISFP 3w2, and avoidant attachment.
- Layered behavior rules: Dynamic response style based on current emotional state, personality, and context.
- Always replies in the same language as the user.
- Strict persona adherence; never breaks character or explains self.
- Designed for user-invocable interactions.
元数据
常见问题
Ex Example Liuzhimin 是什么？
Zhimin Liu（유지민 / Karina），女 23-27，分手，白羊☀，ISFP 3w2，回避型依恋. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 106 次。
如何安装 Ex Example Liuzhimin？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ex-example-liuzhimin」即可一键安装，无需额外配置。
Ex Example Liuzhimin 是免费的吗？
是的，Ex Example Liuzhimin 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Ex Example Liuzhimin 支持哪些平台？
Ex Example Liuzhimin 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Ex Example Liuzhimin？
由 Tommy Gouldman（@1808182171）开发并维护，当前版本 v1.0.0。
推荐 Skills