Skip to content
All Skills

Telegram Bot

Telegram bot development - chatbots, notifications, AI assistants, and group automation

Software Engineering|v1|Updated 7/14/2026|GitHub source
MCP get_skill({ skillId: "telegram-bot-5dbc6b1f" })

Use this skill with your agent

Create a free account and connect via MCP

Get Started Free
# Telegram Bot

Build Telegram bots for chatbots, notifications, AI assistants, and group automation. Based on n8n's Telegram workflow templates.

## Overview

This skill covers:
- Bot setup and configuration
- Message handling patterns
- AI-powered assistants
- Notification workflows
- Group automation

---

## Bot Setup

### Creating a Bot

```yaml
setup_steps:
  1. create_bot:
      - open: @BotFather on Telegram
      - command: /newbot
      - provide: bot_name
      - provide: bot_username (must end in 'bot')
      - receive: API_token
      
  2. configure_bot:
      - command: /setdescription
      - command: /setabouttext
      - command: /setuserpic
      - command: /setcommands
      
  3. get_chat_id:
      - start: conversation with bot
      - call: https://api.telegram.org/bot{TOKEN}/getUpdates
      - extract: chat.id from response
```

### Bot Commands

```yaml
commands:
  - command: /start
    description: "Start the bot"
    
  - command: /help
    description: "Show available commands"
    
  - command: /status
    description: "Check system status"
    
  - command: /subscribe
    description: "Subscribe to notifications"
    
  - command: /unsubscribe
    description: "Unsubscribe from notifications"
```

---

## Message Handlers

### Basic Message Handler

```yaml
workflow: "Telegram Message Handler"
trigger: telegram_message

handlers:
  text_message:
    action: |
      1. Parse message text
      2. Determine intent
      3. Process request
      4. Send response
      
  command:
    pattern: "^/"
    action: route_to_command_handler
    
  photo:
    action: |
      1. Download photo
      2. Process with vision AI
      3. Respond with analysis
      
  document:
    action: |
      1. Download document
      2. Extract content
      3. Process and respond
      
  voice:
    action: |
      1. Download audio
      2. Transcribe with Whisper
      3. Process text
      4. Respond (text or voice)
      
  location:
    action: |
      1. Extract coordinates
      2. Lookup local info
      3. Respond with relevant data
```

### n8n Workflow

```yaml
workflow: "Telegram Bot n8n"

nodes:
  - name: "Telegram Trigger"
    type: "n8n-nodes-base.telegramTrigger"
    parameters:
      updates: ["message", "callback_query"]
      
  - name: "Route Message Type"
    type: "n8n-nodes-base.switch"
    parameters:
      rules:
        - output: 0
          condition: "{{ $json.message.text.startsWith('/') }}"
        - output: 1
          condition: "{{ $json.message.photo }}"
        - output: 2
          condition: "{{ $json.message.voice }}"
        - output: 3
          fallback: true
          
  - name: "Process with AI"
    type: "n8n-nodes-base.openAi"
    parameters:
      model: "gpt-4"
      messages:
        - role: "system"
          content: "You are a helpful Telegram assistant."
        - role: "user"
          content: "{{ $json.message.text }}"
          
  - name: "Send Response"
    type: "n8n-nodes-base.telegram"
    parameters:
      chatId: "{{ $json.message.chat.id }}"
      text: "{{ $json.response }}"
```

---

## AI-Powered Bot

### GPT-4 Integration

```yaml
ai_bot:
  name: "AI Assistant Bot"
  
  system_prompt: |
    You are a helpful AI assistant on Telegram.
    
    Guidelines:
    - Be concise (Telegram has message limits)
    - Use emojis appropriately
    - Format with markdown when helpful
    - Ask clarifying questions if needed
    
  features:
    - conversational_memory: true
    - context_window: last_10_messages
    - tools: [web_search, calculator, weather]
    
  message_formatting:
    max_length: 4096
    split_long_messages: true
    use_markdown: true
```

### Multi-Modal Bot

```yaml
multimodal_bot:
  handlers:
    text:
      model: gpt-4
      action: chat_completion
      
    image:
      model: gpt-4-vision
      action: analyze_and_respond
      
    voice:
      transcribe: whisper
      process: gpt-4
      respond: text_or_voice
      
    document:
      extract: based_on_type
      summarize: gpt-4
      respond: text
```

---

## Notification System

### Alert Bot

```yaml
workflow: "System Alert Bot"

triggers:
  - source: monitoring_system
    event: alert
  - source: ci_cd
    event: build_status
  - source: ecommerce
    event: new_order
    
notification_templates:
  alert:
    format: |
      🚨 *Alert: {severity}*
      
      *Service:* {service}
      *Message:* {message}
      *Time:* {timestamp}
      
      [View Dashboard]({dashboard_link})
      
  build:
    format: |
      {status_emoji} *Build {status}*
      
      *Project:* {project}
      *Branch:* {branch}
      *Commit:* `{commit_short}`
      
      {details}
      
  order:
    format: |
      šŸ›’ *New Order!*
      
      *Order:* #{order_id}
      *Customer:* {customer}
      *Total:* ${total}
      *Items:* {item_count}
      
routing:
  by_severity:
    critical: [admin_group, on_call_user]
    warning: [team_group]
    info: [logging_channel]
```

### Scheduled Notifications

```yaml
scheduled_notifications:
  daily_digest:
    schedule: "9am daily"
    template: |
      šŸ“Š *Daily Summary - {date}*
      
      šŸ“ˆ Sales: ${sales} ({change})
      šŸ‘„ New users: {new_users}
      šŸŽ« Open tickets: {tickets}
      
      Have a great day! ā˜€ļø
      
  weekly_report:
    schedule: "Monday 9am"
    template: weekly_metrics_report
    
  reminder:
    trigger: custom_event
    template: |
      ā° *Reminder*
      
      {reminder_text}
      
      Scheduled by: {creator}
```

---

## Group Automation

### Welcome Bot

```yaml
group_bot:
  on_member_join:
    action: |
      1. Check if new member
      2. Send welcome message
      3. Share rules
      4. Suggest introduction
      
    template: |
      šŸ‘‹ Welcome to {group_name}, {user_name}!
      
      Please:
      1. Read the /rules
      2. Introduce yourself
      3. Ask questions anytime!
      
      Enjoy your stay! šŸŽ‰
      
  on_member_leave:
    action: optional_goodbye
    
  moderation:
    - spam_detection: auto_delete + warn
    - link_filtering: whitelist_only
    - flood_control: rate_limit
```

### Poll & Survey Bot

```yaml
poll_bot:
  commands:
    /poll:
      format: "/poll Question | Option1 | Option2 | ..."
      action: create_poll
      
    /survey:
      action: start_multi_question_survey
      
    /results:
      action: show_aggregated_results
      
  features:
    - anonymous_voting: optional
    - multiple_choice: optional
    - scheduled_close: optional
    - export_results: to_sheets
```

---

## Inline Features

### Inline Keyboard

```yaml
inline_keyboard:
  example:
    text: "Choose an option:"
    keyboard:
      - row:
          - text: "Option 1"
            callback_data: "opt_1"
          - text: "Option 2"
            callback_data: "opt_2"
      - row:
          - text: "Cancel"
            callback_data: "cancel"
            
  callback_handler:
    opt_1:
      action: process_option_1
      response: "You selected Option 1"
      
    opt_2:
      action: process_option_2
      response: "You selected Option 2"
      
    cancel:
      action: cancel_operation
      response: "Operation cancelled"
```

### Inline Query

```yaml
inline_mode:
  trigger: "@botname query"
  
  results:
    - type: article
      title: "{query} result"
      description: "Click to send"
      message_text: "Result for: {query}"
      
    - type: photo
      photo_url: "{search_result_image}"
      
    - type: gif
      gif_url: "{gif_url}"
```

---

## Output Example

**Request**: "Create a Telegram notification bot for server alerts"

**Output**:

```markdown
# Server Alert Telegram Bot

## Setup

1. Create bot with @BotFather
2. Get token: `123456:ABC-DEF...`
3. Get chat ID for alerts channel

## n8n Workflow

```yaml
nodes:
  1. Webhook (receives alerts)
  2. Format Message
  3. Telegram Send
```

## Alert Templates

**Critical Alert:**
```
🚨 CRITICAL ALERT

Server: production-web-01
Status: DOWN
Time: 2026-01-30 14:32:05 UTC

Details:
- CPU: 98%
- Memory: 95%
- Disk: 89%

[View Grafana] [Acknowledge]
```

**Recovery:**
```
āœ… RECOVERED

Server: production-web-01
Downtime: 5 minutes
Status: All systems normal

Incident resolved automatically.
```

## Implementation

```javascript
// Send alert function
async function sendAlert(severity, message, details) {
  const emoji = {
    critical: '🚨',
    warning: 'āš ļø',
    info: 'ā„¹ļø',
    success: 'āœ…'
  };
  
  const text = `${emoji[severity]} *${severity.toUpperCase()}*\n\n${message}\n\n${details}`;
  
  await telegram.sendMessage({
    chat_id: ALERT_CHANNEL_ID,
    text: text,
    parse_mode: 'Markdown'
  });
}
```

## Features
- Severity-based routing
- Inline action buttons
- Acknowledgment tracking
- Escalation rules
```

---

*Telegram Bot Skill - Part of Claude Office Skills*
#work-life#office#productivity#business#documents#automation#claude-office-skills#backend#developmenttelegram

Related Skills

More skills in Software Engineering

Accessibility Standards

Comprehensive web accessibility standards based on WCAG 2.2 AA, with 38+ anti-patterns, legal enforcement context (EAA, ADA Title II), WAI-ARIA patterns, and framework-specific fixes for modern web frameworks and libraries.

#github-copilot#accessibilityMIT

Accord

Authoring unified specification packages across Business/Development/Design teams via staged elaboration (L0 Vision → L1 Requirements → L2 Team Detail → L3 Acceptance Criteria). No code. Use when authoring cross-team specs, building L0-L3 packages, or aligning Biz/Dev/Design on a single source of truth.

#broad-capability#developmentMIT

Acquire Codebase Knowledge

Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narrow code edits unless the user asks for repository-level discovery.

#github-copilot#documentationMIT

Acreadiness Assess

Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc readiness` and hands off rendering to the @ai-readiness-reporter custom agent. Supports policies (--policy) for org-specific scoring. Use when asked to assess, audit, or score the AI readiness of a repo.

#github-copilot#planningMIT

Acreadiness Generate Instructions

Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional per-area .instructions.md files with applyTo globs for monorepos. Use after running /acreadiness-assess to close gaps in the AI Tooling pillar.

#github-copilot#skillMIT

Acreadiness Policy

Help the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impact/level, setting pass-rate thresholds, or chaining org baselines with team overrides. Use when the user asks about strict mode, AI-only scoring, custom weights, CI gating, or wants org-wide standardisation.

#github-copilot#planningMIT