#218 by GitHub stars

therealXiaomanChu/ex-skill

Distill an ex-partner into an AI Skill. Import WeChat history, photos, social media posts, generate Relationship Memory + Persona, with continuous evolution. | 把前任蒸馏成 AI Skill，导入微信聊天记录、照片、朋友圈，生成 Relationship Memory + Persona，支持持续进化。

Engineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → a7c06380fe74

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit a7c06380fe74d0872840830fa6d4b863363c1f12

6.6kGitHub stars

10stars in 7 days

1skill in this repository

0commits in 30 days

Heat

4.3

Star growth, last 7 daysAhead of 52% of tracked repositories
Star growth, last 24 hoursAhead of 68% of tracked repositories
Rank movement, last 7 daysAhead of 58% of tracked repositories
Commits, last 30 daysAhead of 0% of tracked repositories
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Individual skills in this repository

create-ex /

How it works

create-ex

When your agent uses it

Distill an ex-partner into an AI Skill. Import WeChat history, photos, social media posts, generate Relationship Memory + Persona, with continuous evolution. | 把前任蒸馏成 AI Skill，导入微信聊天记录、照片、朋友圈，生成 Relationship Memory + Persona，支持持续进化。

What it loads into context

Frontmatter

110 tokens

Always available to the agent

SKILL.md

4,374 tokens

When the skill is activated

Reference documents

12,977 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

触发条件
工具使用规则
安全边界（⚠<U+FE0F> 重要）
主流程：创建新前任 Skill
进化模式：追加记忆
进化模式：对话纠正
管理命令
Trigger Conditions
Safety Boundaries (⚠<U+FE0F> Important)
Main Flow: Create a New Ex Skill

Scripts executed separately

tools/photo_analyzer.py
tools/qq_parser.py
tools/skill_writer.py
tools/social_parser.py
tools/version_manager.py
tools/wechat_parser.py

Files

.gitignoreasset220 bytes
INSTALL.mddoc1,926 bytes
LICENSEasset1,074 bytes
README.mddoc8,720 bytes
README_EN.mddoc5,366 bytes
SKILL.mdcore15,282 bytes
SKILL.mdcore15,282 bytes
SKILL.mdcore15,282 bytes
SKILL.mdcore15,282 bytes
SKILL.mdcore15,282 bytes
SKILL.mdcore15,282 bytes
SKILL.mdcore15,282 bytes
SKILL.mdcore15,282 bytes
SKILL.mdcore15,282 bytes
SKILL.mdcore15,282 bytes
SKILL.mdcore15,282 bytes
SKILL.mdcore15,282 bytes
SKILL.mdcore15,282 bytes
SKILL.mdcore15,282 bytes
SKILL.mdcore15,282 bytes
SKILL.mdcore15,282 bytes
SKILL.mdcore15,282 bytes
docs/COMPLIANCE.mddoc2,001 bytes
docs/EXPORT_GUIDE.mddoc2,676 bytes
docs/PRD.mddoc3,362 bytes
prompts/correction_handler.mddoc1,664 bytes
prompts/intake.mddoc1,842 bytes
prompts/memory_analyzer.mddoc2,288 bytes
prompts/memory_builder.mddoc2,210 bytes
prompts/merger.mddoc1,397 bytes
prompts/persona_analyzer.mddoc4,819 bytes
prompts/persona_builder.mddoc3,447 bytes
prompts/scene_director.mddoc1,784 bytes
prompts/session_summary.mddoc1,514 bytes
requirements.txtdoc211 bytes
tools/photo_analyzer.pyruns4,439 bytes
tools/qq_parser.pyruns4,327 bytes
tools/skill_writer.pyruns5,344 bytes
tools/social_parser.pyruns2,930 bytes
tools/version_manager.pyruns3,611 bytes
tools/wechat_parser.pyruns8,953 bytes

Read SKILL.md


> **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.
>
> 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。

# 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"

View the complete source on GitHub

Skills included

create-ex

Repository facts

License: MIT
Created: Mar 31, 2026
Last pushed: Apr 8, 2026
Forks: 564
Open issues: 15
Project activity: Slowing

Rank over the last 12 weeks

Now #218 · best #174 · down 20 in 30 days

#214 on Oct 30
#215 on Oct 31
#214 on Nov 1
#216 on Nov 2
#219 on Nov 3
#218 since Nov 4

69 earlier periods

#173 on Aug 2
#176 from Aug 7 to Aug 8
#175 on Aug 9
#178 from Aug 10 to Aug 11
#177 on Aug 12
#180 on Aug 13
#181 on Aug 14
#180 from Aug 15 to Aug 17
#181 on Aug 18
#180 on Aug 19
#176 on Aug 20
#178 on Aug 21
#174 on Aug 22
#182 on Aug 23
#181 on Aug 24
#182 on Aug 25
#183 on Aug 26
#186 on Aug 27
#184 on Aug 28
#187 on Aug 29
#185 from Aug 30 to Aug 31
#190 on Sep 1
#182 on Sep 2
#188 on Sep 3
#185 on Sep 4
#188 on Sep 5
#185 on Sep 6
#188 from Sep 7 to Sep 8
#189 on Sep 9
#190 from Sep 10 to Sep 11
#191 on Sep 12
#192 on Sep 13
#193 on Sep 14
#192 from Sep 15 to Sep 17
#194 on Sep 18
#192 on Sep 19
#194 on Sep 20
#195 from Sep 21 to Sep 22
#196 on Sep 23
#195 on Sep 24
#194 on Sep 25
#195 on Sep 26
#196 on Sep 27
#198 from Sep 28 to Sep 29
#196 on Sep 30
#198 on Oct 1
#200 on Oct 2
#197 on Oct 3
#194 on Oct 4
#197 from Oct 5 to Oct 6
#199 on Oct 7
#198 on Oct 8
#203 on Oct 9
#200 on Oct 10
#201 on Oct 11
#203 on Oct 12
#204 on Oct 13
#203 on Oct 14
#204 on Oct 15
#202 on Oct 16
#205 on Oct 17
#204 on Oct 18
#206 on Oct 19
#205 on Oct 20
#206 from Oct 21 to Oct 22
#207 from Oct 23 to Oct 24
#210 on Oct 25
#209 on Oct 28
#210 on Oct 29

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 2, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 16 notes

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

1 broad permissionin 1 file: SKILL.md:1
1 dangerous shell commandin 1 file: SKILL.md:408
35 network referencesin 4 files: README.md:7 README_EN.md:7 INSTALL.md:10 and 1 more
No hidden or obfuscated text
No instruction overrides
6 executable scriptsin 6 files: tools/photo_analyzer.py:1 tools/qq_parser.py:1 tools/skill_writer.py:1 and 3 more
1 reference to secretsin 1 file: .gitignore:21
No requests to vote in Hot

Show all 44 signals by file

`.gitignore`

Access to secretsline 21
```
[Credential-related source omitted]
```

`INSTALL.md`

Network accessline 10

mkdir -p .claude/skills git clone https://github.com/therealXiaomanChu/ex-skill .claude/skills/create-ex

Network accessline 11

git clone https://github.com/therealXiaomanChu/ex-skill .claude/skills/create-ex

Network accessline 17

git clone https://github.com/therealXiaomanChu/ex-skill ~/.claude/skills/create-ex

Network accessline 23

git clone https://github.com/therealXiaomanChu/ex-skill ~/.openclaw/workspace/skills/create-ex

`README.md`

Network accessline 7

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)

Network accessline 8

[![Python 3.9+](https://img.shields.io/badge/Python-3.9%2B-blue.svg)](https://python.org)

Network accessline 9

[![Claude Code](https://img.shields.io/badge/Claude%20Code-Skill-blueviolet)](https://claude.ai/code)

Network accessline 10

[![AgentSkills](https://img.shields.io/badge/AgentSkills-Standard-green)](https://agentskills.io)

Network accessline 31

# 安装到当前项目（在 git 仓库根目录执行） mkdir -p .claude/skills git clone https://github.com/therealXiaomanChu/ex-skill .claude/skills/create-ex

Network accessline 33

git clone https://github.com/therealXiaomanChu/ex-skill .claude/skills/create-ex

Network accessline 35

# 或安装到全局（所有项目都能用） git clone https://github.com/therealXiaomanChu/ex-skill ~/.claude/skills/create-ex

Network accessline 36

git clone https://github.com/therealXiaomanChu/ex-skill ~/.claude/skills/create-ex

Network accessline 49

- **Claude Code**：免费安装，需要 Node.js 18+（[安装指南](https://docs.anthropic.com/en/docs/claude-code)）

Network accessline 52

- Claude Pro / Max 订阅：在订阅额度内使用，无需额外配置   - Anthropic API Key：按量付费，需在 Claude Code 中配置 key - **替代前端**：也可以使用 [OpenClaw](https://github.com/nicepkg/openclaw) 运行本 Skill

Network accessline 53

- Anthropic API Key：按量付费，需在 Claude Code 中配置 key - **替代前端**：也可以使用 [OpenClaw](https://github.com/nicepkg/openclaw) 运行本 Skill - **不需要 GPU**，不需要本地模型，不需要 Docker

Network accessline 54

- **替代前端**：也可以使用 [OpenClaw](https://github.com/nicepkg/openclaw) 运行本 Skill

Network accessline 176

本项目遵循 [AgentSkills](https://agentskills.io) 开放标准：

Network accessline 218

| 项目 | 作者 | 说明 | |------|------|------| | [ex-cure-skill](https://github.com/W1ndys/ex-cure-skill) | @W1ndys | 关系反思模式，从聊天记录中复盘经验教训 |

Network accessline 219

|------|------|------| | [ex-cure-skill](https://github.com/W1ndys/ex-cure-skill) | @W1ndys | 关系反思模式，从聊天记录中复盘经验教训 | | [同事.skill](https://github.com/titanwings/colleague-skill) | @titanwings | 本项目的灵感来源，把同事蒸馏成 AI Skill |

Network accessline 220

| [ex-cure-skill](https://github.com/W1ndys/ex-cure-skill) | @W1ndys | 关系反思模式，从聊天记录中复盘经验教训 |

Network accessline 221

| [同事.skill](https://github.com/titanwings/colleague-skill) | @titanwings | 本项目的灵感来源，把同事蒸馏成 AI Skill |

Network accessline 222

| [simp-skill](https://github.com/BeamusWayne/simp-skill) | @BeamusWayne | 与其怀念前任，不如勇敢追爱 |

Network accessline 236

MIT License © [therealXiaomanChu](https://github.com/therealXiaomanChu)

`README_EN.md`

Network accessline 7

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)

Network accessline 8

[![Python 3.9+](https://img.shields.io/badge/Python-3.9%2B-blue.svg)](https://python.org)

Network accessline 9

[![Claude Code](https://img.shields.io/badge/Claude%20Code-Skill-blueviolet)](https://claude.ai/code)

Network accessline 10

[![AgentSkills](https://img.shields.io/badge/AgentSkills-Standard-green)](https://agentskills.io)

Network accessline 29

# Install to current project mkdir -p .claude/skills git clone https://github.com/therealXiaomanChu/ex-skill .claude/skills/create-ex

Network accessline 31

git clone https://github.com/therealXiaomanChu/ex-skill .claude/skills/create-ex

Network accessline 33

# Or install globally git clone https://github.com/therealXiaomanChu/ex-skill ~/.claude/skills/create-ex

Network accessline 34

git clone https://github.com/therealXiaomanChu/ex-skill ~/.claude/skills/create-ex

Network accessline 156

The architecture of this project is directly inspired by **[colleague-skill (同事.skill)](https://github.com/titanwings/colleague-skill)** by [titanwings](https://github.com/titanwings). colleague-skill pioneered the idea of "distilling a per

Network accessline 158

This project follows the [AgentSkills](https://agentskills.io) open standard, compatible with Claude Code and OpenClaw.

Network accessline 162

MIT License © [therealXiaomanChu](https://github.com/therealXiaomanChu)

`SKILL.md`

Broad permissionsline 1
```
Read, Write, Edit, Bash
```
Dangerous shell operationline 408
```
rm -rf exes/{slug}
```

`docs/COMPLIANCE.md`

Network accessline 12

唯一的网络交互是 Claude Code 与 Anthropic API 之间的对话请求，这部分受 [Anthropic 使用政策](https://www.anthropic.com/policies) 约束。

`tools/photo_analyzer.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`tools/qq_parser.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`tools/skill_writer.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`tools/social_parser.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`tools/version_manager.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`tools/wechat_parser.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 43 facts

Network access in code of documentationINSTALL.md:10Low confidence
Network access in code of documentationINSTALL.md:11Low confidence
Network access in code of documentationINSTALL.md:17Low confidence
Network access in code of documentationINSTALL.md:23Low confidence
Network access in prose of documentationREADME.md:7Low confidence
Network access in prose of documentationREADME.md:8Low confidence
Network access in prose of documentationREADME.md:9Low confidence
Network access in prose of documentationREADME.md:10Low confidence
Network access in code of documentationREADME.md:31Low confidence
Network access in code of documentationREADME.md:33Low confidence
Network access in code of documentationREADME.md:35Low confidence
Network access in code of documentationREADME.md:36Low confidence
Network access in prose of documentationREADME.md:49Low confidence
Network access in prose of documentationREADME.md:52Low confidence
Network access in prose of documentationREADME.md:53Low confidence
Network access in prose of documentationREADME.md:54Low confidence
Network access in prose of documentationREADME.md:176Low confidence
Network access in prose of documentationREADME.md:218Low confidence
Network access in prose of documentationREADME.md:219Low confidence
Network access in prose of documentationREADME.md:220Low confidence
Network access in prose of documentationREADME.md:221Low confidence
Network access in prose of documentationREADME.md:222Low confidence
Network access in prose of documentationREADME.md:236Low confidence
Network access in prose of documentationREADME_EN.md:7Low confidence
Network access in prose of documentationREADME_EN.md:8Low confidence
Network access in prose of documentationREADME_EN.md:9Low confidence
Network access in prose of documentationREADME_EN.md:10Low confidence
Network access in code of documentationREADME_EN.md:29Low confidence
Network access in code of documentationREADME_EN.md:31Low confidence
Network access in code of documentationREADME_EN.md:33Low confidence
Network access in code of documentationREADME_EN.md:34Low confidence
Network access in prose of documentationREADME_EN.md:156Low confidence
Network access in prose of documentationREADME_EN.md:158Low confidence
Network access in prose of documentationREADME_EN.md:162Low confidence
Broad permissions in the frontmatter of the SKILL.mdSKILL.md:1High confidence
Dangerous shell operation in code of the SKILL.mdSKILL.md:408High confidence
Network access in prose of documentationdocs/COMPLIANCE.md:12Low confidence
Executable script in code of a file that runstools/photo_analyzer.py:1High confidence
Executable script in code of a file that runstools/qq_parser.py:1High confidence
Executable script in code of a file that runstools/skill_writer.py:1High confidence
Executable script in code of a file that runstools/social_parser.py:1High confidence
Executable script in code of a file that runstools/version_manager.py:1High confidence
Executable script in code of a file that runstools/wechat_parser.py:1High confidence

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Native	Frontmatter field user-invocable in SKILL.md	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md SKILL.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

[![therealXiaomanChu/ex-skill on hotskills](https://hotskills.dev/badge/therealxiaomanchu-ex-skill.svg)](https://hotskills.dev/skill/therealxiaomanchu-ex-skill/)

therealXiaomanChu/ex-skill

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

create-ex

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Rank over the last 12 weeks

Before you install

.gitignore

INSTALL.md

README.md

README_EN.md

SKILL.md

docs/COMPLIANCE.md

tools/photo_analyzer.py

tools/qq_parser.py

tools/skill_writer.py

tools/social_parser.py

tools/version_manager.py

tools/wechat_parser.py

How the signals fit together

Works with

You might also use

mattpocock/skills

obra/superpowers

NousResearch/hermes-agent

multica-ai/andrej-karpathy-skills

anthropics/skills

DietrichGebert/ponytail

Explore alternatives and comparisons

Add this badge to your README

`SKILL.md`

`.gitignore`

`INSTALL.md`

`README.md`

`README_EN.md`

`SKILL.md`

`docs/COMPLIANCE.md`

`tools/photo_analyzer.py`

`tools/qq_parser.py`

`tools/skill_writer.py`

`tools/social_parser.py`

`tools/version_manager.py`

`tools/wechat_parser.py`