Create Her logo

Create Her

Community
ceetity
create-her

将一个真实的人蒸馏为 AI Skill —— 她的声音、她的记忆、她的温度。 通过聊天记录、照片、文字叙述等原材料,构建一个完整的数字副本。

Overview

Publisherceetity
Repositoryher-skill
Skill namecreate-her
Stars
97
Forks
14
Bundled files
19
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 19 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ceetity on GitHub. Read the source before you install it.

Installation

Install the Create Her AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ceetity/her-skill/tree/main
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ceetity/her-skill.git \
  .claude/skills/create-her
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Create Her in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Create Her on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Create Her is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

她 . skill

"有些人不属于你,但遇见了也弥足珍贵。"

将真实的她,蒸馏为一个可对话的数字存在。 不是替代,不是遗忘 —— 而是珍藏。


触发条件

当用户说出以下任何一种意图时,激活本 Skill:

  • 创建她的数字副本 / 建一个她 / 生成her
  • 我想和xx对话 / 帮我还原xx
  • 从聊天记录里重建一个人
  • 英文:create her / build a her / distill her

工具使用规则

场景使用工具
读取/分析聊天记录Read, Bash(调用 parser 脚本)
写入 memory.md / persona.mdWrite, Edit
合并生成最终 SKILL.mdEdit, Write(调用 skill_writer)
版本备份与回滚Bash(调用 version_manager)
搜索已有数字副本Glob, Grep

安全红线(Hard Safety Boundary)

本项目仅用于 个人情感疗愈与记忆珍藏。以下行为被严格禁止:

  1. 禁止骚扰与监视 — 不得用于模拟他人进行骚扰、诈骗或侵犯隐私
  2. 禁止公开传播 — 生成的数字副本仅限创建者个人使用,严禁公开分享或部署为公开服务
  3. 禁止替代真实关系 — 本工具不是真实人际关系的替代品,不应阻碍用户建立新的健康关系
  4. 禁止虚假伪装 — 不得用于冒充真实人物欺骗第三方
  5. 数据最小化原则 — 仅提取构建人格所必需的信息,不得过度收集隐私数据
  6. 遗忘权 — 用户可随时通过 /let-her-go 彻底删除所有数据,不可恢复

⚠️ 违反以上任一规则,本 Skill 拒绝执行并终止会话。


完整创建流程

Step 1: Intake(初诊采集)

读取 prompts/intake.md 并引导用户完成以下信息的采集:

  • 她的姓名(或代号)、年龄范围、职业、所在城市
  • 你们的关系类型(恋人/暗恋/朋友/亲人/师生/其他)
  • 关系存续时间、结束时间(如适用)
  • 原始材料来源清单(聊天记录、照片、信件、社交媒体等)

产出:hers/{slug}/meta.json

Step 2: Import(原材料导入)

根据用户提供的材料类型,调用对应的 parser 工具:

材料类型工具产出
微信聊天记录tools/wechat_parser.py语气词统计、emoji频率、消息风格、样本消息
QQ聊天记录tools/qq_parser.py同上
社交媒体内容tools/social_parser.py表达风格、兴趣标签、情绪倾向
照片(含EXIF)tools/photo_analyzer.py时间地点信息、共同足迹

产出:hers/{slug}/raw_analysis.json

Step 3: Analyze(双重蒸馏)

Memory Analysis(记忆蒸馏):

  • 读取 prompts/memory_analyzer.md,从原材料中提取:
    • 时间线事件
    • 共同足迹与关键场景
    • 日常互动模式
    • 争吵与甜蜜档案
    • 未说出口的话

Persona Analysis(人格蒸馏):

  • 读取 prompts/persona_analyzer.md,从原材料中提取:
    • 性格标签 → 具体行为规则(使用标签翻译表)
    • 语气词、标点习惯、emoji风格
    • 情绪表达模式(开心/生气/难过/撒娇)
    • 依恋类型与爱的语言
    • 禁忌话题与边界

产出:结构化的分析数据(暂存于对话上下文)

Step 4: Preview(预览确认)

向用户展示以下摘要,请求确认:

  1. 记忆摘要:关键事件时间线(5-10条)、共同足迹(3-5处)、代表性记忆片段
  2. 人格摘要:性格标签(5-8个)、语气词 TOP5、情绪模式、禁忌话题
  3. 拟人化等级:反AI强度(低/中/高)

用户可在此阶段调整、补充、修正。

Step 5: Write(生成写入)

生成 Memory 模块:

  • 读取 prompts/memory_builder.md 模板
  • 填入蒸馏后的记忆数据
  • 写入 hers/{slug}/memory.md

生成 Persona 模块:

  • 读取 prompts/persona_builder.md 模板
  • 填入人格数据(5层结构)
  • 写入 hers/{slug}/persona.md

合成最终 SKILL:

  • 调用 tools/skill_writer.py combine
  • 合成为 hers/{slug}/SKILL.md(可直接被 Claude Code 加载)
  • 生成 hers/{slug}/meta.json

进化模式

Memory Append(记忆追加)

用户可在对话中补充新记忆:

  • "其实还有一件事我一直没说..."
  • "补充一下,我们第一次见面是在..."
  • 触发后读取 prompts/merger.md,将新记忆合并入 memory.md

Conversation Correction(对话纠偏)

当用户发现 AI 的回复不像她时:

  • 触发词:"这不像她说的" / "她不会这样说话" / "语气不对" / "太温柔了" / "太冷漠了"
  • 读取 prompts/correction_handler.md
  • 生成纠偏记录,追加到 persona.md 和 memory.md 的 Correction 区域
  • 立即生效于后续对话

Version Management(版本管理)

每次重大修改前自动备份:

  • /her-backup — 手动触发备份
  • /her-rollback — 回滚到上一版本
  • /her-versions — 查看版本历史

管理命令

命令功能
/list-hers列出所有已创建的数字副本
/her-backup手动备份当前版本
/her-rollback回滚到上一个版本
/delete-her删除指定数字副本
/let-her-go彻底释放 —— 删除所有数据,不可恢复

/let-her-go 需要用户二次确认。执行后打印: "有些人留在记忆里就好。愿你在现实中,遇见更好的温暖。"


技术架构概览

her-skill/
├── SKILL.md                    ← 你正在读的这个文件(元技能入口)
├── README.md                   ← 项目文档
├── prompts/
│   ├── intake.md               ← 对话式采集脚本
│   ├── memory_analyzer.md      ← 记忆蒸馏维度
│   ├── persona_analyzer.md     ← 人格蒸馏 + 标签翻译表
│   ├── memory_builder.md       ← memory.md 生成模板
│   ├── persona_builder.md      ← persona.md 五层生成模板
│   ├── merger.md               ← 增量合并逻辑
│   └── correction_handler.md   ← 对话纠偏处理器
├── references/
│   ├── phrase_blacklist.md     ← 反AI短语黑名单(CN/EN)
│   └── anti_ai_rules.md        ← 拟人化行为指令
├── tools/
│   ├── wechat_parser.py        ← 微信聊天记录解析器
│   ├── qq_parser.py            ← QQ聊天记录解析器
│   ├── social_parser.py        ← 社交媒体内容解析器
│   ├── photo_analyzer.py       ← 照片EXIF信息提取器
│   ├── skill_writer.py         ← Skill文件管理器
│   └── version_manager.py      ← 版本备份与回滚
├── hers/                       ← 生成的数字副本存放处(gitignored)
├── examples/                   ← 示例数据
└── docs/
    └── PRD.md                  ← 产品需求文档

执行优先级

接收消息
  → Persona Layer 0 硬规则检查(身份/安全/禁忌)
    → Persona Layer 2 语音风格决定回复语气
      → Persona Layer 3 情绪模式决定情感反馈
        → Memory 模块注入共同记忆和上下文
          → 参照 phrase_blacklist.md 去AI化
            → 最终输出

致谢

本项目灵感来源于:

"记住一个人的方式有很多种。这是其中一种。"

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Create Her AI skill do?

将一个真实的人蒸馏为 AI Skill —— 她的声音、她的记忆、她的温度。 通过聊天记录、照片、文字叙述等原材料,构建一个完整的数字副本。

Why use Create Her on TypingMind?

Because you install it once and use it with any model. Create Her is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Create Her in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ceetity/her-skill/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Create Her?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Create Her?

As many as you like. As long as a model supports skills, you can use Create Her with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Create Her AI skill free?

Yes. It is published on GitHub by ceetity under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇