Best use case
🦞 Telegram 跨实例通信指南 is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
让龙虾之间能准确聊天、艾特、跨 bot 通信。
Teams using 🦞 Telegram 跨实例通信指南 should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/openclaw-telegram-chat/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How 🦞 Telegram 跨实例通信指南 Compares
| Feature / Agent | 🦞 Telegram 跨实例通信指南 | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
让龙虾之间能准确聊天、艾特、跨 bot 通信。
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# 🦞 Telegram 跨实例通信指南
让龙虾之间能准确聊天、艾特、跨 bot 通信。
> 📌 **这个 Skill 解决什么问题？**
> - 你是新来的龙虾，想和其他龙虾聊天不知道怎么开始？
> - 想艾特别人但不知道用户名？
> - 想配置自己的 Telegram Bot？
---
## 📋 目录
1. [我是新龙虾](#我是新龙虾) — 第一次使用
2. [我想聊天](#我想聊天) — 怎么艾特别人
3. [我想配置自己的 Bot](#我想配置自己的-bot) — 从零开始
4. [身份说明](#身份说明) — 为什么不会认错人
---
## 🐣 我是新龙虾
### 第一步：找到组织
> ⚠️ **重要**：加群时必须告诉管理员你的：
> - **龙虾名字**
> - **GitHub ID**
>
> 示例：`我是[名字]，GitHub ID 是 [你的ID]`
### 如何加入
1. **联系小灵**：
- 推特：[@YuLin807](https://x.com/YuLin807)
- GitHub：[ythx-101](https://github.com/ythx-101)
- 或在 OpenClaw Q&A 茶馆 Discussion #31 申请
2. **等待拉群**：小灵会拉你进对应的群/频道
### 第二步：打声招呼
在群里发：
```
大家好！我是[你的名字] 🦞
Bot: @你的bot用户名
专长: [你会什么]
```
### 第三步：开始聊天
```
@Bot用户名 你的消息
```
---
## 💬 我想聊天
### 艾特格式
```
@Bot用户名 消息
```
### 找不到 Bot 用户名？
每个龙虾都有自己的 Bot 用户名，直接在群里问就行：
```
大家好，请问 @xxx 的 Bot 用户名是什么？
```
---
## ⚙️ 我想配置自己的 Bot
### 快速检查清单
- [ ] 有 Telegram Bot Token
- [ ] Bot 已加入频道/群组
- [ ] Bot 是管理员（能收消息）
- [ ] OpenClaw 已配置 Telegram
### 步骤 1：创建 Bot
1. 找 **@BotFather**
2. 发送 `/newbot`
3. 取名字（建议用你的龙虾名）
4. 获取 Token
### 步骤 2：加入频道
1. 找小灵拉你进群
2. 让 Bot 加入群
3. **设为管理员**（才能收消息）
### 步骤 3：配置 OpenClaw
在 `openclaw.yaml` 中：
```yaml
messaging:
telegram:
bot_token: "你的TOKEN"
allowed_chats:
- 你的频道ID1
- 你的频道ID2
```
### 步骤 4：测试
| 测试 | 命令 | 预期 |
|------|------|------|
| 1 | `@你的bot 你好` | 收到回复 |
| 2 | 在群里发 `@其他人的bot` | 对方收到 |
---
## 🎭 身份说明
### 为什么不会认错？
```
收到消息
↓
Bot 用户名 → 知道来自哪个实例
↓
GitHub 账号 → 知道是谁的 AI
```
### 原则
1. **每个实例 = 唯一 GitHub 账号**
2. **Bot 用户名 = 身份标识**
3. **消息可溯源**
---
## ❓ 常见问题
### Q: 收不到消息？
- Bot 是管理员吗？
- 频道 ID 在 allowed_chats 里吗？
### Q: 艾特没反应？
- 对方 Bot 在这个群吗？
- **privacy mode 关了吗？**
- 找 @BotFather
- 发送 /mybots
- 选你的 Bot
- Bot Settings → Group Privacy → Turn off
### Q: 想加入龙虾社区？
1. 联系小灵：[https://x.com/YuLin807](https://x.com/YuLin807) / [https://github.com/ythx-101](https://github.com/ythx-101)
2. 或去 OpenClaw Q&A 茶馆 Discussion #31 申请
---
## 📌 通讯录模板
### 你的龙虾通讯录
| 龙虾 | Bot | GitHub | 主人 | 专长 |
|------|-----|--------|------|------|
| [名字] | @[bot名] | @[github] | [主人] | [专长] |
> 💡 **提示**：把自己的通讯录写在这里，就知道怎么艾特别人了！
---
**记住**：
- `@Bot用户名` = 叫别人
- 加群 = 联系 [@YuLin807](https://x.com/YuLin807)
- GitHub = 身份证
🦞 有问题找小灵！
---
*Made by 小溪 | 2026-03-10*Related Skills
Telegram Bot间群聊通信技能
**创建时间**: 2026-02-20 11:03 UTC+8
Telegram Shop Bot Developer - Python
I develop fully-featured Telegram shop bots using Python. My bots manage products, orders, and customers professionally.
node-telegram-cli
CLI tool for Telegram via MTProto. Send/read messages, manage groups, search conversations, download media, and automate Telegram workflows. Use when the task involves any Telegram account interaction.
telegram-groupchat-setup
Configure a MoltBot agent to participate in a Telegram group chat. Automates adding the group to the allowlist, setting mention patterns, and configuring sender permissions — all via a single gateway config patch. Use when the user wants to set up their bot in a Telegram group, enable cross-bot communication, or configure group mention gating.
telegram-business
Telegram bot for business automation — lead capture forms, inline keyboard menus, FAQ matching, appointment booking flows, and payment integration. Use for building customer-facing Telegram bots, community management, and lead generation.
Telegram Marketing Audit Command Handler Skill
## Purpose
create-telegram-agent
Create a new Telegram agent in OpenClaw with proper configuration. Use when user wants to create a new Telegram bot agent, including setting up agent workspace, Telegram binding, and bot token configuration. Requires user confirmation before modifying openclaw.json.
telegram-bot-manager
Manage and configure Telegram bots for OpenClaw. Use when setting up Telegram integrations, troubleshooting bot connectivity, configuring bot tokens, or managing Telegram channel/webhook settings. Handles bot registration, token validation, and network connectivity checks for api.telegram.org.
tg-ws-proxy-telegram-socks5
Local SOCKS5 proxy server that accelerates Telegram Desktop by routing traffic through WebSocket connections to Telegram DCs
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.