What it does
微信4.x自动化机器人:群聊机器人、批量群发(支持文件)、批量设置群公告、聊天记录导出、群管理 | 5分钟上手
- Connects Instruction files the AI reads; connects to nothing
- Account or key No key needed
- Category Coding
For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/claw-codes-wx4py)Use together with
MCP servers that connect the AI to services for the same work
Fallow
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
Desktop Commander
MCP server for terminal commands, file operations, and process management
Similar Skills
Same kind of work, ordered like the Skills list
| This one wx4py | rea | graphify | archify | security-audit-skill | |
|---|---|---|---|---|---|
| Maker | claw-codes | morluto | Graphify-Labs | tt-a1i | cloudflare |
| Skills | 1 | 1 | 1 | 1 | 1 |
| GitHub stars | 807 | 461,751 | 148,352 | 96,757 | 73,156 |
| Last code change | Apr 11, 2026 | Nov 16, 2026 | Nov 16, 2026 | Nov 15, 2026 | Sep 15, 2026 |
| License | AGPL-3.0 | MIT | Apache-2.0 | Apache-2.0 | MIT |
1 skills (instruction sets) by claw-codes that an AI reads and follows · not an MCP server
How a Skill differs from MCP
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Works with
Claude Code
From the maker’s README and the folders in the repo
Install
Is it safe?
- Who made it
GitHub account claw-codes (person) is only 7 months old: take extra care
- Use and upkeep
★ 807 stars · code last changed Apr 11, 2026
- Any scripts?
No, plain text files the AI reads and follows
- Uses the internet?
No scripts, so it does not go online by itself
- Changes machine-wide settings?
No hooks or writes to machine settings found
Checked automatically from the repo files at commit ccbc7c1 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
First: which AI do you use?
Pick your app and this page shows only how to install it there
Option 1Upload to claude.ai (web and app)
Download from GitHub
This skill uses the AGPL-3.0 license, which is not on the list we redistribute, so we do not hand out a ZIP from our site. Download it from GitHub and arrange the folder yourself, or use "Let the AI install it" above, which is easier
Download from GitHub (whole repo) ↗
Unzip it, then zip only the wx4-skill folder again. The ZIP must have a wx4-skill folder with SKILL.md at the top level, no loose files
Open Skills on claude.ai and upload
+Create skillUpload a skillpick wx4-skill.zip
No Upload button? Turn on file creation first
SettingsCapabilitiesCode execution and file creation
Turn on Code execution and file creation first (newer menus: Create and edit files) · personal plans: Settings → Capabilities · Team/Enterprise: an admin turns it on under Organization settings → Plugins & skills · every plan, including Free
Upload once; it works in claude.ai and Claude Desktop, and in recent Claude Code signed in with a Claude account (not with an API key)
Cowork and cloud sessions use the skills turned on in your claude.ai account, not ~/.claude/skills on your computer (Claude Desktop scheduled tasks run locally and still load it)
Checked against official docs Nov 12, 2026 · Source: support.claude.com, support.claude.com, code.claude.com
Option 1Let Claude Code install it
Copy this sentence and paste it into a Claude Code chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Restart Claude Code, then type /wx4-skill or ask for a matching task and Claude picks it up
Checked against official docs Nov 12, 2026 · Source: code.claude.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.claude/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Restart Claude Code, then type /wx4-skill or ask for a matching task and Claude picks it up
ChatGPT desktop app
The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills
Option 1Let ChatGPT install it
Open Codex in the ChatGPT desktop app and paste this sentence into the chat
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Option 2Put the folder there yourself
Put the wx4-skill folder at ~/.agents/skills/wx4-skill
~ is your home folder ($HOME)
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
After installing
- ChatGPT desktop app: open Skills in the sidebar to see that the skill is there
- To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
- Codex picks up newly installed skills by itself; if one does not show up, restart Codex
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
ChatGPT on the web and mobile
Skills you install yourself do not work here; only skills that come with a plugin from the directory
To use this skill with ChatGPT, use the ChatGPT desktop app as above
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Option 1Let Codex install it
Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Restart Codex, then ask for a matching task; Codex lists the skill
Option 1Let Cursor install it
Copy this sentence and paste it into a Cursor chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
In Cursor’s Agent chat, type / and pick wx4-skill
Checked against official docs Nov 12, 2026 · Source: cursor.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.cursor/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
In Cursor’s Agent chat, type / and pick wx4-skill
Option 1Let the AI install it
For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com
For Terminal users
Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.
Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026
View the original SKILL.md
The text below comes from the maker’s repo, not from PopNx MCP
Showing the first 8,000 characters · Open the full file on GitHub
---
name: wx4-skill
description: 微信自动化操作 skill,用于帮助用户快速完成微信消息群发、文件发送、群管理、聊天记录获取、多群监听、AI 自动回复等自动化任务。当用户需要批量发送微信消息、管理微信群、获取聊天记录、监听群消息、或接入 AI 群聊机器人时使用此 skill。
---
# 微信自动化操作 Skill
## ⚠️ 使用前必读:安装检查
**在执行任何操作前,必须先确认 wx4py 库已安装。**
### 步骤1:检查是否已安装
```python
try:
from wx4py import WeChatClient
print("✅ wx4py 已安装")
except ImportError:
print("❌ 未安装 wx4py")
```
### 步骤2:如果未安装,执行安装
```bash
# 方法1:从 PyPI 安装(推荐)
pip install wx4py
# 方法2:从 GitHub 安装(最新版)
pip install git+https://github.com/claw-codes/wx4py.git
# 方法3:从本地安装
cd /path/to/wx4py
pip install .
```
### 步骤3:验证安装成功
```python
from wx4py import WeChatClient
# 测试导入
print("✅ 安装成功!")
# 检查版本(可选)
import wx4py
print(f"版本: {wx4py.__version__}")
```
**重要提示**:
- 如果用户提示 `ModuleNotFoundError: No module named 'wx4py'`,说明未安装
- 必须先安装库再执行后续操作
- 安装只需要一次,后续无需重复
---
## 概述
本 skill 基于 wx4py 库,帮助用户通过 Python 代码自动化控制 Windows 微信客户端,完成重复性的消息发送、群管理等任务。
**适用场景**:
- 批量群发通知到多个群或联系人
- 定时发送文件、图片、消息
- 获取和分析聊天记录
- 管理群公告、群昵称、免打扰等设置
- 监听多个群聊消息,并在被 @ 时自动回复
- 接入 OpenAI 兼容接口或自定义 AI 回调,构建群聊机器人
- 自动化日常微信操作
**前置要求**:
- Windows 系统
- 微信 PC 客户端已安装并登录(Qt 版本,已测试 4.1.7.59、4.1.8.29)
- Python >=3.9
- 终端、编辑器、脚本文件统一使用 UTF-8 编码环境,避免中文消息、群名、文件名出现乱码
**编码环境建议**:
- Python 源码文件保存为 UTF-8
- PowerShell / 终端优先使用 UTF-8 编码
- 读写文本、JSON、Markdown 文件时显式指定 `encoding='utf-8'`
- 如果要输出中文日志或生成中文文件内容,优先验证终端和编辑器都已切换到 UTF-8
## 核心功能
### 1. 消息发送
#### 发送单条消息到联系人或群
```python
from wx4py import WeChatClient
wx = WeChatClient()
wx.connect()
# 发送给联系人
wx.chat_window.send_to("文件传输助手", "测试消息")
# 发送到群
wx.chat_window.send_to("工作群", "下午3点开会", target_type='group')
wx.disconnect()
```
#### 批量群发消息
```python
wx = WeChatClient()
wx.connect()
# 批量发送到多个群
groups = ["群1", "群2", "群3"]
message = "重要通知:明天放假"
wx.chat_window.batch_send(groups, message)
# 批量发送到多个联系人
contacts = ["张三", "李四", "王五"]
wx.chat_window.batch_send(contacts, "周末聚餐通知", target_type='contact')
wx.disconnect()
```
### 2. 文件发送
#### 发送单个文件
```python
wx = WeChatClient()
wx.connect()
# 发送文件给联系人
wx.chat_window.send_file_to("文件传输助手", r"C:\reports\weekly.pdf")
# 发送文件到群
wx.chat_window.send_file_to("工作群", r"C:\data.xlsx", target_type='group', message='可以携带消息')
wx.disconnect()
```
#### 批量发送多个文件
```python
wx = WeChatClient()
wx.connect()
# 发送多个文件
files = [
r"C:\images\photo1.png",
r"C:\images\photo2.png",
r"C:\documents\report.pdf"
]
wx.chat_window.send_file_to("文件传输助手", files)
wx.disconnect()
```
### 3. 聊天记录获取
#### 获取指定时间范围的聊天记录
```python
wx = WeChatClient()
wx.connect()
# 获取今天的聊天记录
messages = wx.chat_window.get_chat_history(
target="工作群",
target_type='group',
since='today' # 'today' | 'yesterday' | 'week' | 'all'
)
# 处理消息
for msg in messages:
print(f"[{msg['time']}] {msg['content']}")
wx.disconnect()
```
**返回格式**:
```python
{
"type": "text", # text / link / system
"content": "消息内容",
"time": "今天 15:30"
}
```
### 4. 群管理
#### 获取群成员列表
```python
wx = WeChatClient()
wx.connect()
members = wx.group_manager.get_group_members("工作群")
print(f"群成员数量:{len(members)}")
for member in members:
print(member)
wx.disconnect()
```
#### 修改群昵称
```python
wx = WeChatClient()
wx.connect()
wx.group_manager.set_group_nickname("工作群", "张三的小号")
wx.disconnect()
```
#### 获取群昵称
```python
wx = WeChatClient()
wx.connect()
nickname = wx.group_manager.get_group_nickname("工作群")
print(f"我在本群的昵称:{nickname}")
wx.disconnect()
```
#### 设置消息免打扰
```python
wx = WeChatClient()
wx.connect()
# 开启免打扰
wx.group_manager.set_do_not_disturb("工作群", enable=True)
# 关闭免打扰
wx.group_manager.set_do_not_disturb("工作群", enable=False)
wx.disconnect()
```
#### 置顶/取消置顶聊天
```python
wx = WeChatClient()
wx.connect()
# 置顶聊天
wx.group_manager.set_pin_chat("工作群", enable=True)
# 取消置顶
wx.group_manager.set_pin_chat("工作群", enable=False)
wx.disconnect()
```
#### 修改群公告(如果修改不成功,很大概率是因为不是管理员的原因)
```python
wx = WeChatClient()
wx.connect()
# 优先使用这种方式,从 Markdown 文件设置公告(支持表格、列表等格式)
wx.group_manager.set_announcement_from_markdown("工作群", "markdown文件路径")
# 直接设置文本公告
wx.group_manager.modify_announcement_simple("工作群", "本群禁止发广告,违者移出")
wx.disconnect()
```
### 5. 群聊监听与 AI 自动回复
#### 监听多个群聊消息
```python
from wx4py import CallbackHandler, MessageEvent, WeChatClient
groups = ["工作群1", "工作群2", "工作群3"]
def on_message(event: MessageEvent):
print(f"[{event.group}] {event.content}")
return "" # 只监听,不自动回复
with WeChatClient(auto_connect=True) as wx:
wx.process_groups(
groups,
[CallbackHandler(on_message)],
block=True,
)
```
#### 只在被 @ 时自动回复
```python
from wx4py import AsyncCallbackHandler, MessageEvent, WeChatClient
groups = ["工作群1", "工作群2"]
def reply(event: MessageEvent):
if not event.is_at_me:
return ""
return f"收到:{event.content}"
with WeChatClient(auto_connect=True) as wx:
wx.process_groups(
groups,
[AsyncCallbackHandler(reply, auto_reply=True, reply_on_at=True)],
block=True,
)
```
#### 监听指定群消息并转发给指定联系人或群
```python
from wx4py import ForwardRuleHandler, GroupForwardRule, WeChatClient
rules = [
GroupForwardRule(
source_group="告警群",
targets=["值班同学"],
target_type="contact",
prefix_template="[告警群] ",
),
GroupForwardRule(
source_group="项目群A",
targets=["项目群B"],
target_type="group",
prefix_template="[项目群A] ",
),
]
with WeChatClient(auto_connect=True) as wx:
wx.process_groups(
["告警群", "项目群A"],
[ForwardRuleHandler(rules)],
block=True,
)
```
**适用场景**:
- 监听告警群,把消息转发给值班联系人
- 监听业务群,把消息同步到另一个群
- 针对不同来源群,配置不同的联系人或群作为目标
#### 使用内置 AIClient 接入 OpenAI 兼容接口
```python
import os
from wx4py import AIClient, AIConfig, AIResponder, AsyncCallbackHandler, WeChatClient
ai = AIClient(
AIConfig(
base_url="https://api.example.com/v1",
api_format="completions",
model="your-model-id",
api_key=os.environ["AI_API_KEY"],
enable_thinking=False,
)
)
with WeChatClient(auto_connect=True) as wx:
wx.process_groups(
["工作群"],
[
AsyncCallbackHandler(
AIResponder(ai, context_size=8, reply_on_at=True),
auto_reply=True,
)
],
block=True,
)
```
#### 使用自定义 AI 或业务系统
```python
from wx4py import AsyncCallbackHandler, MessageEvent, WeChatClient
def custom_reply(event: MessageEvent):
if not event.is_at_me:
return ""
# 这里可以调用公司内部接口、其他 AI SDK 或业务系统。
return f"自定义回复:{event.content}"
with WeChatClient(auto_connect=True) as wx:
wx.process_groups(
["工作群"],
[AsyncCallbackHandler(custom_reply, auto_reply=True, reply_on_at=True)],
block=True,
)
```
**实现说明**:
- 每个群优先打开独立聊天窗口,适合同时监听多个群。
- 自动回复通过发送队列串行执行,避免多个群同时回复时抢占窗口。
- 本库发送的消息会自动记录,避免机器人监听到自己的回复后再次触发。
## 使用模式
### 推荐:使用上下文管理器
```python
from wx4py import WeChatClient
with WeChatClient() as wx:
# 自动连接和断开
wx.chat_window.send_to("文件传输助手", "Hello!")
```
### 手动连接管理
```python
wx = WeChatClient()
wx.connect()
try:
# 执行操作
wx.chat_window.send_to("文件传输助手", "Hello!")
finally:
wx.disconnect()
```
## 实用脚本示例
### 示例1:定时群发通知
```python
from wx4py import WeChatClient
import schedule
import time
def send_daily_notification():
with WeChatClient() as wx:
groups = ["工作群1", "工作群2", "工作群3"]
message = "早安!今日工作提醒..."
wx.chat_window.batch_send(groups, message, target_type='group')
print("通知已发送")
# 每天早上9点发送
schedule.every().day.at("09:00").do(send_daily_notification)
while True:
schedule.run_pending()
time.sleep(60)
```
### 示例2:收集昨天的聊天记录并保存
```python
from wx4py import WeChatClient
import json
from datetime import datetime
with WeChatClient() as wx:
# 获取昨天的聊天记录
messages = wx.chat_window.get_chat_history(
target="工作群",
target_type='group',
since='yesterday'
)
# 保存到文件
filename = f"chat_history_{datetime.now().strftime('%Y%m%d')}.json"
with open(filename, 'w', encoding='utf-8') as f:
json.dump(messages, f, ensure_ascii=False, indent=2)
Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
From GitHub
- GitHub stars
- 807
- Maker
- claw-codes
- License
- AGPL-3.0
- Last code change
- Apr 11, 2026
- SKILL.md files in the repo (including translated copies and templates)
- 1
- Topics
- automation, openclaw-skills, python, rpa, skills, wechat, weixin
- Repo
- claw-codes/wx4py