therealXiaomanChu/ex-skill
把前任蒸馏成 AI Skill,用ta的方式跟你说话。Inspired by colleague-skill(同事skill).
View Origin LinkProduct Positioning & Context
AI Executive Synthesis
The product aims for high fidelity in simulating an ex-partner. This issue highlights the double-edged sword of such realism, where negative experiences could also be replicated.
This issue exposes a critical psychological and ethical dilemma inherent in highly realistic AI simulations like `ex-skill`. The user's statement, "If this AI imitates realistically enough, it will still abandon you like before," highlights the potential for the product to replicate not just positive, but also deeply painful, aspects of past relationships. This underscores a significant market risk: achieving high fidelity in AI simulation could inadvertently lead to emotional distress for users, undermining the product's therapeutic or nostalgic intent. The comments from other users, ranging from emotional reactions to calls for "reporting" and acknowledging that "this is not something code can solve," further emphasize the profound non-technical challenges and ethical boundaries of developing emotionally resonant AI companions.
把前任蒸馏成 AI Skill,用ta的方式跟你说话。Inspired by colleague-skill(同事skill).
Active Developer Issues (GitHub)
Logged: Apr 3, 2026
Logged: Apr 3, 2026
Logged: Apr 2, 2026
Logged: Apr 2, 2026
Logged: Apr 1, 2026
Community Voice & Feedback
@ZUOXIANGE 你小子,轮舔还是你:laughing: 训练时,提示词直接给他人设要求他30s-12s内随机时间回复就行了
不要秒回
1%的概率下分手,成为前任
放下吧
这不是代码能解决的
这不是代码能解决的
希望能加上 每一次对话之后/对话特定条数 能输出 session summary 然后在开始新对话前 加载前N天/前N个summary 实现记忆不中断?
我请gpt写了一下可能可以实现的方案:
https://chatgpt.com/share/69ce03e5-df74-83e8-a46e-8b61a27b3edc
我请gpt写了一下可能可以实现的方案:
https://chatgpt.com/share/69ce03e5-df74-83e8-a46e-8b61a27b3edc
1. 语音克隆功能,提供ta的音频后能克隆语音,模仿发声
2. 支持切换多个前任
3. 设置场景,看多个前任的对话过程
2. 支持切换多个前任
3. 设置场景,看多个前任的对话过程
极具攻击性言论,举报了
“乌溜溜的黑眼珠和你的笑脸,怎么也难忘记你容颜的转变。轻飘飘的旧时光就这么溜走,转头回去看看时已匆匆数年……”
> 她不是已经复刻一个了吗
666
666
> 她不是已经复刻一个了吗
666
666
呜呜呜呜,我要举报你!呜呜呜
> 她不是已经复刻一个了吗
666
666
我有个朋友让你憋说了😠
> 她不是已经复刻一个了吗
6666
6666
呜呜
Related Early-Stage Discoveries
Discovery Source
GitHub Open Source Aggregated via automated community intelligence tracking.
Tech Stack Dependencies
No direct open-source NPM package mentions detected in the product documentation.
Media Tractions & Mentions
No mainstream media stories specifically mentioning this product name have been intercepted yet.
Deep Research & Science
No direct peer-reviewed scientific literature matched with this product's architecture.
Market Trends