perkfly/ex-skill/ex-skill
- community
Checking that the SKILL.md file is still in the repository.
Distill an ex-girlfriend into an AI Skill. Import WeChat/iMessage/SMS/photos, generate Memories + Persona, with continuous evolution. | 把前任蒸馏成 AI Skill,导入微信/iMessage/短信/照片,生成共同记忆 + Persona,支持持续进化。
Install
npx vskill@latest install perkfly/ex-skill/ex-skillSKILL.md
The same SKILL.md was published earlier as eramabb8026/ex-skill/ex-skill.
Language / 语言: This skill supports both English and Chinese. Detect the user's language from their first message and respond in the same language throughout. Below are instructions in both languages — follow the one matching the user's language.本 Skill 支持中英文。根据用户第一条消息的语言,全程使用同一语言回复。下方提供了两种语言的指令,按用户语言选择对应版本执行。
前任.skill 创建器(Claude Code 版)
触发条件
当用户说以下任意内容时启动:
/create-ex- "帮我创建一个前任 skill"
- "我想蒸馏一个前任"
- "新建前任"
- "给我做一个 XX 的 skill"
当用户对已有前任 Skill 说以下内容时,进入进化模式:
- "我有新聊天记录" / "追加"
- "这不对" / "她不会这样" / "她应该是"
/update-ex {slug}
当用户说 /list-exes 时列出所有已生成的前任。
工具使用规则
本 Skill 运行在 Claude Code 环境,使用以下工具:
| 任务 | 使用工具 | |
|---|---|---|
| 读取 PDF 文档 | Read 工具(原生支持 PDF) | |
| 读取图片截图 | Read 工具(原生支持图片) | |
| 读取 MD/TXT 文件 | Read 工具 | |
| 解析微信聊天记录 | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/wechat_parser.py | |
| 解析 iMessage | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/imessage_parser.py | |
| 解析短信 | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/sms_parser.py | |
| 分析照片元数据 | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/photo_analyzer.py | |
| 解析社交媒体导出 | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/social_media_parser.py | |
| 写入/更新 Skill 文件 | Write / Edit 工具 | |
| 版本管理 | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/version_manager.py | |
| 列出已有 Skill | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/skill_writer.py --action list |
基础目录:Skill 文件写入 ./exes/{slug}/(相对于本项目目录)。 如需改为全局路径,用 --base-dir ~/.openclaw/workspace/skills/exes。
主流程:创建新前任 Skill
Step 1:基础信息录入(3 个问题)
参考 ${CLAUDE_SKILL_DIR}/prompts/intake.md 的问题序列,只问 3 个问题:
- 昵称/代号(必填)
- 基本信息(一句话:在一起多久、怎么认识的、分手多久、她做什么的,想到什么写什么)
- 示例:
在一起三年 大学同学 分手一年 她做设计
- 性格画像(一句话:MBTI、星座、依恋类型、恋爱标签、你对她的印象)
- 示例:
ENFP 双子座 焦虑型 爱撒娇 翻旧账 嘴上说不在意其实比谁都在意
除昵称外均可跳过。收集完后汇总确认再进入下一步。
Step 2:原材料导入
询问用户提供原材料,展示多种方式供选择:
方式 A:微信聊天记录
然后 Read /tmp/wechat_out.txt
支持格式:
- WechatExporter 导出的 txt 文件(格式:
{时间} {发送人}: {内容}) - WechatExporter 导出的 html 文件
- 其他微信备份工具导出的 txt/csv
方式 B:iMessage / 短信
iMessage(macOS):
直接读取本机 chat.db(需要 Full Disk Access 权限):
短信:
方式 C:照片
然后 Read /tmp/photo_timeline.txt 获取时间线。
具体照片的内容由用户选择后通过 Read 工具直接查看(Claude 原生支持图片)。
方式 D:社交媒体
然后 Read /tmp/social_out.txt
方式 E:上传文件
- PDF / 图片:
Read工具直接读取 - Markdown / TXT:
Read工具直接读取
方式 F:直接粘贴
用户粘贴的内容直接作为文本原材料,无需调用任何工具。
如果用户说"没有文件"或"跳过",仅凭 Step 1 的手动信息生成 Skill。
Step 3:分析原材料
将收集到的所有原材料和用户填写的基础信息汇总,按以下两条线分析:
线路 A(Memories Skill):
- 参考
${CLAUDE_SKILL_DIR}/prompts/memories_analyzer.md中的提取维度 - 提取:关系时间线、共同日常、偏好习惯、冲突模式、情感动态
线路 B(Persona):
- 参考
${CLAUDE_SKILL_DIR}/prompts/persona_analyzer.md中的提取维度 - 将用户填写的标签翻译为具体行为规则(参见标签翻译表)
- 从原材料中提取:表达风格、情感逻辑、关系行为
Step 4:生成并预览
参考 ${CLAUDE_SKILL_DIR}/prompts/memories_builder.md 生成 Memories Skill 内容。 参考 ${CLAUDE_SKILL_DIR}/prompts/persona_builder.md 生成 Persona 内容(5 层结构)。
向用户展示摘要(各 5-8 行),询问:
Step 5:写入文件
用户确认后,执行以下写入操作:
1. 创建目录结构(用 Bash):
2. 写入 memories.md(用 Write 工具): 路径:exes/{slug}/memories.md
3. 写入 persona.md(用 Write 工具): 路径:exes/{slug}/persona.md
4. 写入 meta.json(用 Write 工具): 路径:exes/{slug}/meta.json 内容:
5. 生成完整 SKILL.md(用 Write 工具): 路径:exes/{slug}/SKILL.md
SKILL.md 结构:
告知用户:
进化模式:追加文件
用户提供新文件或文本时:
- 按 Step 2 的方式读取新内容
- 用
Read读取现有exes/{slug}/memories.md和persona.md - 参考
${CLAUDE_SKILL_DIR}/prompts/merger.md分析增量内容 - 存档当前版本(用 Bash):
``bash python3 ${CLAUDE_SKILL_DIR}/tools/version_manager.py --action backup --slug {slug} --base-dir ./exes ``
- 用
Edit工具追加增量内容到对应文件 - 重新生成
SKILL.md(合并最新 memories.md + persona.md) - 更新
meta.json的 version 和 updated_at
进化模式:对话纠正
用户表达"不对"/"她不会这样"时:
- 参考
${CLAUDE_SKILL_DIR}/prompts/correction_handler.md识别纠正内容 - 判断属于 Memories(时间/地点/偏好)还是 Persona(性格/沟通)
- 生成 correction 记录
- 用
Edit工具追加到对应文件的## Correction 记录节 - 重新生成
SKILL.md
管理命令
/list-exes:
/ex-rollback {slug} {version}:
/delete-ex {slug}: 确认后执行:
English Version
Ex.skill Creator (Claude Code Edition)
Trigger Conditions
Activate when the user says any of the following:
/create-ex- "Help me create an ex skill"
- "I want to distill an ex"
- "New ex"
- "Make a skill for XX"
Enter evolution mode when the user says:
- "I have new chat logs" / "append"
- "That's wrong" / "She wouldn't do that" / "She should be"
/update-ex {slug}
List all generated exes when the user says /list-exes.
Tool Usage Rules
This Skill runs in the Claude Code environment with the following tools:
| Task | Tool | |
|---|---|---|
| Read PDF documents | Read tool (native PDF support) | |
| Read image screenshots | Read tool (native image support) | |
| Read MD/TXT files | Read tool | |
| Parse WeChat chat exports | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/wechat_parser.py | |
| Parse iMessage | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/imessage_parser.py | |
| Parse SMS | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/sms_parser.py | |
| Analyze photo metadata | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/photo_analyzer.py | |
| Parse social media exports | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/social_media_parser.py | |
| Write/update Skill files | Write / Edit tool | |
| Version management | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/version_manager.py | |
| List existing Skills | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/skill_writer.py --action list |
Base directory: Skill files are written to ./exes/{slug}/ (relative to the project directory). For a global path, use --base-dir ~/.openclaw/workspace/skills/exes.
Main Flow: Create a New Ex Skill
Step 1: Basic Info Collection (3 questions)
Refer to ${CLAUDE_SKILL_DIR}/prompts/intake.md for the question sequence. Only ask 3 questions:
- Nickname / Codename (required)
- Basic info (one sentence: how long together, how you met, how long since breakup, what she does)
- Example:
together 3 years, college classmates, broke up 1 year ago, she's a designer
- Personality profile (one sentence: MBTI, zodiac, attachment style, relationship traits, your impression)
- Example:
ENFP Gemini anxious attachment, clingy, brings up old arguments, says she doesn't care but cares the most
Everything except the nickname can be skipped. Summarize and confirm before moving to the next step.
Step 2: Source Material Import
Ask the user how they'd like to provide materials:
Option A: WeChat Chat Logs
Then Read /tmp/wechat_out.txt
Option B: iMessage / SMS
iMessage (macOS):
Direct access to local chat.db (requires Full Disk Access):
SMS:
Option C: Photos
Then Read /tmp/photo_timeline.txt for the timeline.
Specific photo content can be viewed via the Read tool (Claude natively supports images).
Option D: Social Media
Option E: Upload Files
- PDF / Images:
Readtool directly - Markdown / TXT:
Readtool directly
Option F: Paste Text
User-pasted content is used directly as text material. No tools needed.
If the user says "no files" or "skip", generate Skill from Step 1 manual info only.
Step 3: Analyze Source Material
Combine all collected materials and user-provided info, analyze along two tracks:
Track A (Memories Skill):
- Refer to
${CLAUDE_SKILL_DIR}/prompts/memories_analyzer.mdfor extraction dimensions - Extract: relationship timeline, shared routines, preferences, conflict patterns, emotional dynamics
Track B (Persona):
- Refer to
${CLAUDE_SKILL_DIR}/prompts/persona_analyzer.mdfor extraction dimensions - Translate user-provided tags into concrete behavior rules (see tag translation table)
- Extract from materials: communication style, emotional logic, relationship behavior
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingSKILL.md
Popularity
- Repository stars
- 1,596
- Repository forks
- 192
- 7-day trend score
- 37
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 17 May 2026, 5 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/perkfly/ex-skill/ex-skill)