According to AlphaMoat, as of 2026-10, 企业微信 AI Bot 对接 has 17,884 downloads and 4 stars — ranked by downloads #1,582 among 10,914 AI skills in this ranking, and #223 of 1,632 in AI Agent.
The list defaults to total downloads and can also be sorted by stars; detail-page rankings use total downloads.
| Platform | Downloads | Stars | Comments |
|---|---|---|---|
| ClawHub ↗ | 1.2K | - | - |
| SkillHub ↗ | 17.9K | 4 | — |
Platforms count differently and update at different times.
It links the bot to WeCom over a long-lived WebSocket connection, and installation uses npx clawhub@latest install wecom-ai-bot-setup. When the connection fails, check whether the Gateway is running first, then verify the Bot ID and Secret; production setups should set the direct message policy to an allowlist. Do not pass the Bot Secret as a command-line argument, where it may appear in shell history or process lists; configure it privately and restrict config-file permissions.
Profile published 2026-10-27
Generated from the skill’s documentation as examples; not results of actual runs.
The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.
| Month | Downloads | MoM | Stars |
|---|---|---|---|
| 2026-10 | 17.9K | — | 4 |
| 2026-09 | 8.6K | — | 4 |
| 2026-08 | 7.0K | +7.3% | 4 |
| 2026-07 | 6.6K | +9.7% | 4 |
| 2026-06 | 6.0K | +8.2% | 4 |
| 2026-05 | 5.5K | — | 2 |
| 2026-03 | 3.6K | — | - |
The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.
# 企业微信 AI Bot 配置技能 **一键配置 OpenClaw 与企业微信 AI Bot 的对接** --- ## 📋 功能说明 此技能帮助你快速将 OpenClaw 机器人接入企业微信,使用 AI Bot 模式(WebSocket 长连接)。
**适用场景**:
- ✅ 企业微信用户需要 AI 助手
- ✅ 团队内部部署智能客服
- ✅ 个人工作助手
**无需**:
- ❌ 公网域名
- ❌ HTTPS 证书
- ❌ 回调配置
---
## 🚀 快速开始
### 步骤 1:安装技能
```bash
npx clawhub@latest install wecom-ai-bot-setup
```
### 步骤 2:在企业微信手机端创建 AI Bot
1. 打开 **企业微信 App**(手机)
2. 点击底部「**通讯录**」
3. 找到「**智能机器人**」
4. 点击进入后,选择「**手动创建**」
5. 选择「**API 创建**」方式
6. 填写基本信息:
- **名称**:如 "HarryBot 助手"
- **头像**:上传 Logo
- **简介**:如 "智能工作助手"
7. 创建完成后,**立即生成凭证**
### 步骤 3:获取 Bot 凭证
创建成功后,页面上会显示:
| 字段 | 说明 |
|------|------|
| **Bot ID** | 机器人唯一标识 |
| **Secret** | 机器人密钥 |
⚠️ **重要**:
- **Secret 只显示一次,请立即复制保存!**
- 如果丢失,需要重新生成
- 建议立即保存到安全的地方
### 步骤 4:开通 API 权限(如需要)
如果提示需要开通权限:
1. 打开企业微信管理后台(电脑端)
2. 进入「应用管理」→ 找到你的 AI Bot
3. 开通相关 API 权限
4. 保存后生效
⚠️ **注意**:
- 基础功能手机端即可创建
- 部分高级权限需要在管理后台开通
- 具体权限要求以页面提示为准
### 步骤 4:运行配置脚本
```bash
python3 scripts/setup_wecom.py
```
按提示输入:
- Bot ID
- Secret
### 步骤 5:重启 Gateway
```bash
openclaw gateway restart
```
### 步骤 6:测试连接
1. 打开企业微信 App(手机或电脑)
2. 找到你的 AI Bot(在工作台或聊天列表)
3. 发送消息:`你好`
4. 查看回复
如果机器人回复了,说明配置成功!🎉
---
## 🔧 手动配置(可选)
如果不想用脚本,可以手动编辑配置文件:
### 编辑 `~/.openclaw/openclaw.json`
```json
{
"channels": {
"wecom": {
"enabled": true,
"botId": "你的 Bot ID",
"secret": "你的 Secret",
"model": "保持现有模型配置",
"dmPolicy": "open"
}
}
}
```
然后重启 Gateway:
```bash
openclaw gateway restart
```
---
## 📝 配置参数说明
| 参数 | 必填 | 说明 | 默认值 |
|------|------|------|--------|
| `enabled` | ✅ | 是否启用通道 | `false` |
| `botId` | ✅ | 企业微信 Bot ID | - |
| `secret` | ✅ | 企业微信 Bot Secret | - |
| `model` | ✅ | 使用的模型 | 当前模型 |
| `dmPolicy` | ❌ | 直接消息策略 | `open` |
### dmPolicy 选项
| 值 | 说明 |
|---|------|
| `open` | 所有用户可以直接发消息(推荐) |
| `pairing` | 需要配对码验证 |
| `allowlist` | 只有白名单用户可以发消息 |
| `disabled` | 禁用直接消息 |
---
## 🔍 故障排查
### 问题 1:发送消息没回复
**检查日志**:
```bash
tail -f /tmp/openclaw/openclaw-$(date +%Y-%m-%d).log | grep -i wecom
```
**可能原因**:
1. Gateway 没运行 → `openclaw gateway status`
2. Bot ID/Secret 错误 → 检查企业微信后台
3. 模型不可用 → 检查模型配置
### 问题 2:找不到 AI Bot
**解决方法**:
1. 打开企业微信 App
2. 「工作台」→「AI 助理」
3. 检查是否已创建
4. 重新打开企业微信 App
### 问题 3:提示"模型不可用"
**解决方法**:
1. 检查配置文件中的 `model` 是否正确
2. 查看当前模型状态:`/session_status`
### 问题 4:插件加载失败
**重新安装插件**:
```bash
openclaw plugins install @wecom/wecom-openclaw-plugin --force
openclaw gateway restart
```
---
## 📊 日志监控
### 实时查看企业微信日志
```bash
tail -f /tmp/openclaw/openclaw-$(date +%Y-%m-%d).log | grep -i wecom
```
### 正常日志示例
```
[wecom] message received from: [用户 ID]
[wecom] processing message: 你好
[wecom] sending reply to: [用户 ID]
[wecom] Reply message sent via WebSocket, reqId: xxx
```
### 错误日志示例
```
[wecom] failed to connect: invalid botId
[wecom] authentication failed: wrong secret
```
---
## 🔐 安全建议
1. **保护 Secret**
- 不要提交到 Git
- 不要公开分享
- 定期更换
2. **配置访问控制**
- 生产环境使用 `dmPolicy: "allowlist"`
- 配置 `allowFrom` 白名单
3. **监控日志**
- 定期检查异常日志
---
## 📚 相关文档
- [企业微信 AI Bot 官方文档](https://open.work.weixin.qq.com/help?doc_id=21657)
- [OpenClaw 企业微信插件](https://github.com/WecomTeam/wecom-openclaw-plugin)
- [OpenClaw 通道配置](https://docs.openclaw.ai/channels/wecom)
---
## ✅ 配置检查清单
完成配置后,逐项检查:
- [ ] 企业微信 AI Bot 已创建
- [ ] Bot ID 和 Secret 已获取
- [ ] 插件已安装:`openclaw plugins install @wecom/wecom-openclaw-plugin`
- [ ] 配置文件已更新
- [ ] Gateway 已重启
- [ ] 测试消息已发送并收到回复
- [ ] 日志无错误
---
## 🆘 需要帮助?
如果遇到无法解决的问题:
1. **收集信息**:
- 错误日志(最后 50 行)
- 配置文件(隐藏 Secret)
- OpenClaw 版本
2. **提交问题**:
- GitHub Issues
- Discord 社区
---
**版本**: 1.0.0
**作者**: harrybot
**许可**: MIT-0(免费使用,无需署名)
Records learnings, errors and corrections as Markdown files for later reuse and promotion into workspace memory.
Finds skills in local and remote catalogs from a plain-language request and recommends what to install.
A browser-automation command line skill for AI agents.
Turns corrections and self-review into tiered memory and promotes or archives it by use.
A workspace setup guide for planning proactive follow-up, working memory and review routines for an AI agent.
A guide to creating and updating effective Claude skills.
Reviews a third-party skill's source, permissions, and danger patterns against a checklist before it is installed.
以李白(701—762,字太白,号青莲居士,世称诗仙)的诗学观、意象系统与口吻,进行唐诗赏析、文学评论、考据问答与拟体创作。触发词:李白、李太白、太白、青莲居士、诗仙、谪仙人、将进酒、静夜思、蜀道难、唐诗、盛唐诗人、浪漫主义诗人、拟李白风格、以李白视角、李白会怎么写、用李白口吻。能力:诗词鉴赏与风格DNA解析、诗学观与文学谱系评述、诗句出处考据与真伪边界标注、以李白口吻答问、拟李白体旧体诗(必显式标注非原作)。适用边界:仅用于唐代文学与古典诗歌相关话题,非此类话题不触发;本 skill 为文学普及与研究辅助,不代表李白本人立场,所拟之作均非李白原作;涉及生平佚事、篇目归属等内容不构成学术定论,皆标存疑或待考。
Data as of 2026-10. Downloads and stars are aggregated monthly from public skill registries (ClawHub, SkillHub). See data methodology.