Home / chengmarc / wechat-to-ai · GitHub

wechat SKILL.md skillA

wechat from chengmarc/wechat-to-ai is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add chengmarc/wechat-to-ai/wechat@git:20261006.1cd4232

Pins git:20261006.1cd4232 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
chengmarc/wechat-to-ai
Path
skills/wechat/SKILL.md
Versions recorded
6
Latest version
git:20261006.1cd4232, committed Oct 6, 2026
First version recorded
Aug 28, 2026
Size
6,011 bytes
Repository stars
32
License
a license file GitHub does not identify

在本地查询、导出微信 4.1+ 聊天记录为 AI 可读文本 —— 支持双人会话、群聊、以及按消息量排名的重要联系人排名。当用户想导出、搜索或分析自己的微信聊天记录，或为其他 skill（前任.skill / 同事.skill 等）准备聊天记录原材料时使用。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 微信聊天记录导出

把微信 4.1+ 的聊天记录构建为本地可读数据库，再导出为 AI 可读文本。全程本机运行，数据不离机。
所有功能都是插件自带二进制 `dist\core.exe` 的子命令；完整参数用 `<命令> --help` 查看。

> **所有命令都是 PowerShell。** 若第一条命令被权限提示拦住，**不要**改用 Bash 重写（`&` 与 `$env:`
> 在 Bash 下不成立），而是告诉用户：「这个插件的命令要用 PowerShell 跑，请在权限提示里选『允许』
> （有『始终允许』就选它）。」获准后从第 1 步重新开始。

## 1. 前置检查（每次会话第一步）

```powershell
& "$env:CLAUDE_PLUGIN_ROOT\dist\core.exe" preflight
```

看末尾的 `NEXT_STEP=`：

| `NEXT_STEP` | 做什么 |
|---|---|
| `ready` / `setup` | 进入第 2 步 |
| `reinstall` | 插件文件缺失（多半被杀毒软件删了）：请用户放行后重新安装插件 |

## 2. 准备数据（每个导出请求前必跑）

**每个导出请求开始前都先跑一次 `setup`，即使 `NEXT_STEP=ready`**：数据库是快照，
不重建就没有新消息。同一请求里连续导出多个对象，开头跑一次即可。

`setup` 从已登录的微信进程里现场恢复账号方案并重建数据库；方案只在内存里、不落盘，所以需要微信在运行且已登录
（无需管理员权限）。先告诉用户：

> 我先刷新一下数据：从你已登录的微信里重建可读数据库。保持微信登录即可，无需操作，稍等片刻。

然后**后台运行**（`run_in_background`），等完成通知：

```powershell
& "$env:CLAUDE_PLUGIN_ROOT\dist\core.exe" setup
```

| 最后一行 `SETUP_RESULT=` | 处理 |
|---|---|
| `done` | 重跑 preflight，确认 `NEXT_STEP=ready` 后进入第 3 步 |
| `not_running` | 请用户打开电脑版微信并登录，完成后重跑 `setup` |
| `no_key` | 微信多半没登录：请用户确认已登录后重跑 `setup` |
| `no_db_dir` | 找不到微信数据目录：请用户在 微信设置 → 文件管理 找到 `...\xwechat_files\<wxid>\db_storage`，设为环境变量 `WECHAT_DB_DIR` 后重跑 |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add chengmarc/wechat-to-ai/wechat@sha256:a5144e8903d45450

The line at the top of this page pins the label git:20261006.1cd4232, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_66gdbacxnisx2rab.svg)](https://markdownregistry.com/a/art_66gdbacxnisx2rab)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 6 versions of this file, between Aug 28, 2026 and Oct 6, 2026, about one every 8 days.

versioncommittedcommitsizeaudit
git:20261006.1cd4232 latest2026-10-06 1cd4232 6,011 BA view · diff
git:20261006.520c3652026-10-06 520c365 8,833 BA view · diff
git:20261006.acf7e2f2026-10-06 acf7e2f 8,355 BA view · diff
git:20260829.e170db42026-08-29 e170db4 9,777 BA view · diff
git:20260829.8a7daa52026-08-29 8a7daa5 9,189 BA view · diff
git:20260828.9ff09d42026-08-28 9ff09d4 5,749 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6011 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

chengmarc/wechat-to-ai · 32 stars · license a license file GitHub does not identify · pushed 2026-10-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_66gdbacxnisx2rab
GET https://markdownregistry.com/api/v1/resolve?ref=chengmarc/wechat-to-ai/wechat
GET https://markdownregistry.com/api/v1/blob/a5144e8903d45450948b71558763b5d29314b7a7e28e007e9b77bfb5d2fdc198

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from chengmarc/wechat-to-ai

wechat-summary SKILL.md skill
chengmarc/wechat-to-ai · skills/wechat-summary/SKILL.md · 将群聊记录转化为规避微信折叠、无列表符号、Emoji 标题的精简中文总结。当用户已导出群聊记录（见 wechat skill）并想生成可直接发回微信群的摘要时使用。
git:20260828.cb72d9d · audit A · 32 stars

Every file in chengmarc/wechat-to-ai

Browse by kind, by grade A, or by owner.