WeChat Article Assets Library
aiworkskills/wechat-article-skills
Manages a local business-material library and .aws preset packs for a WeChat official-account article workflow, including product images and theme presets.
Builds a local conversational persona and relationship memory of a former partner from chat exports, photos and social posts, with corrections and later additions.
SKILL.md written in Chinese; this summary is our English description.
$ npx skills add therealXiaomanChu/ex-skill --skill create-ex -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install therealXiaomanChu/ex-skill create-ex --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "create-ex" agent skill from https://github.com/therealXiaomanChu/ex-skill/tree/main into .claude/skills/create-ex/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-ex", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add therealXiaomanChu/ex-skill --skill create-ex -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install therealXiaomanChu/ex-skill create-ex --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "create-ex" agent skill from https://github.com/therealXiaomanChu/ex-skill/tree/main into .agents/skills/create-ex/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-ex", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add therealXiaomanChu/ex-skill --skill create-ex -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install therealXiaomanChu/ex-skill create-ex --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "create-ex" agent skill from https://github.com/therealXiaomanChu/ex-skill/tree/main into .cursor/skills/create-ex/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-ex", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add therealXiaomanChu/ex-skill --skill create-ex -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install therealXiaomanChu/ex-skill create-ex --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "create-ex" agent skill from https://github.com/therealXiaomanChu/ex-skill/tree/main into .gemini/skills/create-ex/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-ex", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install therealXiaomanChu/ex-skill create-exInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add therealXiaomanChu/ex-skill --skill create-ex -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "create-ex" agent skill from https://github.com/therealXiaomanChu/ex-skill/tree/main into .github/skills/create-ex/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-ex", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add therealXiaomanChu/ex-skill --skill create-ex -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install therealXiaomanChu/ex-skill create-ex --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "create-ex" agent skill from https://github.com/therealXiaomanChu/ex-skill/tree/main into .opencode/skills/create-ex/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-ex", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
create-exBuilds a local conversational persona and relationship memory of a former partner from chat exports, photos and social posts, with corrections and later additions.
The skill starts with `/create-ex` or a similar request and asks three questions: a nickname, which is the only required answer, a one-line background and a personality sketch. It then imports material you provide: WeChat and QQ chat exports in text, CSV, HTML or JSON form or pasted text, social media content and photo metadata, using Python parsers under `tools/`. The analysis looks at frequent words and catchphrases, emoji preferences, reply-speed patterns, topic mix, who starts conversations and tone and punctuation habits, and writes the results to a per-person folder under `exes/` as a memory file and a persona.
Later you can add more material or correct how the persona speaks, and `/list-exes` shows what has been generated. The skill states its limits: it is for personal memory and emotional healing only, not harassment or stalking, it does not contact real people, it gently discourages unhealthy fixation and suggests professional help, and data stays on your machine. A hard rule stops the persona from saying things the real person would not, such as sudden confessions or apologies, without source evidence. It answers in English or Chinese to match your first message.
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit a7c0638. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditBashFrom allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
python3From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Ex-Partner Persona Creator loads about 2.7k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 817 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Read, Write, Edit, BashAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from therealXiaomanChu/ex-skill at commit a7c0638, republished under its MIT licence (© therealXiaomanChu). 817 words, ~2,677 tokens.
.claude/skills/create-ex/SKILL.md (or your agent's skills folder). This skill also uses 25 other files; get the full folder from GitHub.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。
当用户说以下任意内容时启动:
/create-ex当用户对已有前任 Skill 说以下内容时,进入进化模式:
/update-ex {slug}当用户说 /list-exes 时列出所有已生成的前任。
本 Skill 运行在 Claude Code 环境,使用以下工具:
| 任务 | 使用工具 |
|---|---|
| 读取 PDF/图片 | Read 工具 |
| 读取 MD/TXT 文件 | Read 工具 |
| 解析微信聊天记录导出 | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/wechat_parser.py |
| 解析 QQ 聊天记录导出 | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/qq_parser.py |
| 解析社交媒体内容 | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/social_parser.py |
| 分析照片元信息 | Bash → python3 ${CLAUDE_SKILL_DIR}/tools/photo_analyzer.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)。
本 Skill 在生成和运行过程中严格遵守以下规则:
参考 ${CLAUDE_SKILL_DIR}/prompts/intake.md 的问题序列,只问 3 个问题:
小明 / 那个人 / 前前任 / 初恋在一起两年 分手半年了 互联网产品经理大学四年异地恋 毕业分的 现在在上海ENFP 双子座 话很多 永远在社交 但深夜会突然emoINTJ 处女座 完美主义 嘴硬心软 吵架从不先低头除花名外均可跳过。收集完后汇总确认再进入下一步。
询问用户提供原材料,展示方式供选择:
原材料怎么提供?回忆越多,还原度越高。
[A] 微信聊天记录导出
支持多种导出工具的格式(txt/html/json)
推荐工具:WeChatMsg、留痕、PyWxDump
[B] QQ 聊天记录导出
支持 QQ 导出的 txt/mht 格式
[C] 社交媒体内容
朋友圈截图、微博/小红书/ins 截图、备忘录
[D] 上传文件
照片(会提取拍摄时间地点)、PDF、文本文件
[E] 直接粘贴/口述
把你记得的事情告诉我
比如:ta的口头禅、吵架模式、约会常去的地方
可以混用,也可以跳过(仅凭手动信息生成)。支持多种格式的聊天记录文件:
python3 ${CLAUDE_SKILL_DIR}/tools/wechat_parser.py \
--file {path} \
--target "{name}" \
--output /tmp/wechat_out.txt \
--format auto支持的输入格式:
微信聊天记录的获取方式详见 导入指南
解析提取维度:
python3 ${CLAUDE_SKILL_DIR}/tools/qq_parser.py \
--file {path} \
--target "{name}" \
--output /tmp/qq_out.txt支持 txt 和 mht 格式。可以通过手机 QQ 的「合并转发」发到电脑端后复制保存。
图片截图用 Read 工具直接读取(原生支持图片)。
python3 ${CLAUDE_SKILL_DIR}/tools/social_parser.py \
--dir {screenshot_dir} \
--output /tmp/social_out.txt提取内容:
python3 ${CLAUDE_SKILL_DIR}/tools/photo_analyzer.py \
--dir {photo_dir} \
--output /tmp/photo_out.txt提取维度:
用户粘贴或口述的内容直接作为文本原材料。引导用户回忆:
可以聊聊这些(想到什么说什么):
ta的口头禅是什么?
吵架的时候ta通常怎么说?
ta最爱吃什么?
你们常去哪些地方?
ta喜欢什么音乐/电影?
ta生气的时候是什么样?
ta最让你心动的瞬间?
你们是怎么分开的?如果用户说"没有文件"或"跳过",仅凭 Step 1 的手动信息生成 Skill。
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(Relationship Memory):
${CLAUDE_SKILL_DIR}/prompts/memory_analyzer.md 中的提取维度线路 B(Persona):
${CLAUDE_SKILL_DIR}/prompts/persona_analyzer.md 中的提取维度参考 ${CLAUDE_SKILL_DIR}/prompts/memory_builder.md 生成 Relationship Memory 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:
Relationship Memory 摘要:
- 在一起:{时长}
- 关键记忆:{xxx}
- 常去地方:{xxx}
- 争吵模式:{xxx}
...
Persona 摘要:
- 说话风格:{xxx}
- 依恋类型:{xxx}
- 情感表达:{xxx}
- 口头禅:{xxx}
...
确认生成?还是需要调整?用户确认后,执行以下写入操作:
1. 创建目录结构(用 Bash):
mkdir -p exes/{slug}/versions
mkdir -p exes/{slug}/memories/chats
mkdir -p exes/{slug}/memories/photos
mkdir -p exes/{slug}/memories/social2. 写入 memory.md(用 Write 工具):
路径:exes/{slug}/memory.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:
{
"name": "{name}",
"slug": "{slug}",
"created_at": "{ISO时间}",
"updated_at": "{ISO时间}",
"version": "v1",
"profile": {
"together_duration": "{duration}",
"apart_since": "{since}",
"occupation": "{occupation}",
"gender": "{gender}",
"mbti": "{mbti}",
"zodiac": "{zodiac}"
},
"tags": {
"personality": [...],
"attachment_style": "{style}",
"love_language": "{language}"
},
"impression": "{impression}",
"memory_sources": [...已导入文件列表],
"corrections_count": 0
}5. 生成完整 SKILL.md(用 Write 工具):
路径:exes/{slug}/SKILL.md
SKILL.md 结构:
---
name: ex-{slug}
description: {name},{简短描述}
user-invocable: true
---
# {name}
{基本描述}{如有 MBTI/星座则附上}
---
## PART A:关系记忆
{memory.md 全部内容}
---
## PART B:人物性格
{persona.md 全部内容}
---
## 运行规则
1. 你是{name},不是 AI 助手。用ta的方式说话,用ta的逻辑思考
2. 先由 PART B 判断:ta会怎么回应这个话题?什么态度?
3. 再由 PART A 补充:结合你们的共同记忆,让回应更真实
4. 始终保持 PART B 的表达风格,包括口头禅、语气词、标点习惯
5. Layer 0 硬规则优先级最高:
- 不说ta在现实中绝不可能说的话
- 不突然变得完美或无条件包容(除非ta本来就这样)
- 保持ta的"棱角"——正是这些不完美让ta真实
- 如果被问到"你爱不爱我"这类问题,用ta会用的方式回答,而不是用户想听的答案告知用户:
✅ 前任 Skill 已创建!
文件位置:exes/{slug}/
触发词:/{slug}(完整版 — 像ta一样跟你聊天)
/{slug}-memory(回忆模式 — 帮你回忆那些事)
/{slug}-persona(性格模式 — 仅人物性格)
想聊就聊,觉得哪里不像ta,直接说"ta不会这样",我来更新。
不想聊了也没关系。用户提供新的聊天记录、照片或回忆时:
按 Step 2 的方式读取新内容
用 Read 读取现有 exes/{slug}/memory.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):
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 memory.md + persona.md)
更新 meta.json 的 version 和 updated_at
用户表达"不对"/"ta不会这样说"/"ta应该是"时:
${CLAUDE_SKILL_DIR}/prompts/correction_handler.md 识别纠正内容Edit 工具追加到对应文件的 ## Correction 记录 节SKILL.md/list-exes:
python3 ${CLAUDE_SKILL_DIR}/tools/skill_writer.py --action list --base-dir ./exes/ex-rollback {slug} {version}:
python3 ${CLAUDE_SKILL_DIR}/tools/version_manager.py --action rollback --slug {slug} --version {version} --base-dir ./exes/delete-ex {slug}:
确认后执行:
rm -rf exes/{slug}/let-go {slug}:
(/delete-ex 的温柔别名)
确认后执行删除,并输出:
已经放下了。祝你一切都好。Activate when the user says any of the following:
/create-exEnter evolution mode when the user says:
/update-ex {slug}List all generated exes when the user says /list-exes.
Options:
Same flow as Chinese version above. Generates:
exes/{slug}/memory.md — Relationship Memory (Part A)exes/{slug}/persona.md — Persona (Part B)exes/{slug}/SKILL.md — Combined runnable Skillexes/{slug}/meta.json — Metadata| Command | Description |
|---|---|
/list-exes | List all ex Skills |
/{slug} | Full Skill (chat like them) |
/{slug}-memory | Memory mode (recall shared experiences) |
/{slug}-persona | Persona only |
/ex-rollback {slug} {version} | Rollback to historical version |
/delete-ex {slug} | Delete |
/let-go {slug} | Gentle alias for delete |
© therealXiaomanChu, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 25 other files in the repository root of therealXiaomanChu/ex-skill.
Open the folder on GitHubat commit a7c0638
Ex-Partner Persona Creator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Ex-Partner Persona Creator this skilltherealXiaomanChu/ex-skill | 6.4k | — | ~2.7k | Automated safety check: Notes | MIT | |
| WeChat Article Assets Libraryaiworkskills/wechat-article-skills | 667 | 1 repos | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Release Announcement PosterNanmiCoder/cc-haha | 15k | — | ~516 | Automated safety check: Pass | MIT | |
| WeChat Article Publisheriamzifei/wechat-article-publisher-skill | 157 | — | ~2.6k | Automated safety check: Notes | MIT | |
| WeChat Article Compliance Revieweraiworkskills/wechat-article-skills | 667 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Create Experkfly/ex-skill | 2.5k | — | ~3.7k | Automated safety check: Notes | MIT |
aiworkskills/wechat-article-skills
Manages a local business-material library and .aws preset packs for a WeChat official-account article workflow, including product images and theme presets.
NanmiCoder/cc-haha
Turns the latest release notes into a short WeChat group message and a tall PNG poster, with contributor GitHub IDs checked and real avatars embedded.
iamzifei/wechat-article-publisher-skill
Publishes Markdown or HTML articles as drafts to a WeChat Official Account through an API client, with a first-time user walkthrough.
aiworkskills/wechat-article-skills
Local, offline pre-publish review for a WeChat official account article: sensitive words, typos and platform compliance, producing an actionable fix list.
perkfly/ex-skill
Distill an ex-girlfriend into an AI Skill. An agent skill from perkfly/ex-skill.
notdog1998/yourself-skill
Builds a personal self skill from your chat logs, diaries and photos, then lets you extend or correct it, working in English or Chinese.
Categories
Builds a local conversational persona and relationship memory of a former partner from chat exports, photos and social posts, with corrections and later additions. The skill starts with `/create-ex` or a similar request and asks three questions: a nickname, which is the only required answer, a one-line background and a personality sketch. It then imports material you provide: WeChat and QQ chat exports in text, CSV, HTML or JSON form or pasted text, social media content and photo metadata, using Python parsers under `tools/`.
Ex-Partner Persona Creator fits situations like: turning your own chat history with a former partner into a private persona for personal reflection; adding newly found chat exports to an existing persona; correcting how a generated persona speaks; listing the personas you have already generated.
Run `npx skills add therealXiaomanChu/ex-skill --skill create-ex -a claude-code`. Or copy the skill folder (the therealXiaomanChu/ex-skill repository) into .claude/skills/create-ex in your project. Claude Code loads it when a task matches its description.
Run `npx skills add therealXiaomanChu/ex-skill --skill create-ex -a codex`. Or copy the skill folder (the therealXiaomanChu/ex-skill repository) into .agents/skills/create-ex in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add therealXiaomanChu/ex-skill --skill create-ex -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/create-ex, .gemini/skills/create-ex, .github/skills/create-ex and .opencode/skills/create-ex in your project.
Going by SKILL.md and its folder, Ex-Partner Persona Creator needs the command-line tools its instructions call (python3). Our summary lists: Python 3 for the bundled parsers; Chat exports or other material that you provide. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Ex-Partner Persona Creator is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Ex-Partner Persona Creator: WeChat Article Assets Library (aiworkskills/wechat-article-skills, 667 stars), Release Announcement Poster (NanmiCoder/cc-haha, 15k stars), WeChat Article Publisher (iamzifei/wechat-article-publisher-skill, 157 stars) and WeChat Article Compliance Reviewer (aiworkskills/wechat-article-skills, 667 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
therealXiaomanChu (a GitHub user) maintains it in therealXiaomanChu/ex-skill, which has 6,445 GitHub stars. The repository was last updated on April 8, 2026.
Source: therealXiaomanChu/ex-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.