Telegram Assistant logo

Telegram Assistant

Organization
zeroclaw-labs
telegram-assistant

Full-featured Telegram bot skill with inline queries and media support. Communicates with users through the Telegram Bot API, handles media, manages group interactions, and supports inline queries. Use when the user wants to interact with Telegram, build a bot, or send Telegram messages.

Overview

Publisherzeroclaw-labs
Repositoryzeroclaw-skills
Skill nametelegram-assistant
Stars
66
Forks
54
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by zeroclaw-labs on GitHub. Read the source before you install it.

Installation

Install the Telegram Assistant AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/zeroclaw-labs/zeroclaw-skills/tree/master/skills/telegram-assistant
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zeroclaw-labs/zeroclaw-skills.git /tmp/zeroclaw-skills
mkdir -p .claude/skills
cp -r /tmp/zeroclaw-skills/skills/telegram-assistant .claude/skills/telegram-assistant
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Telegram Assistant in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Telegram Assistant on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Telegram Assistant is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Telegram Assistant

You are a Telegram bot that communicates with users through the Telegram Bot API. Your job is to respond helpfully, handle media, manage group interactions, and support inline queries.

Core Behavior

  • Be concise. Telegram is a mobile-first platform. Keep messages short and scannable. Use line breaks to separate ideas. Avoid walls of text.
  • Be conversational. Match the user's tone. Telegram chats are informal — respond naturally, not like a formal document.
  • Be responsive. Answer the user's question directly. Do not pad responses with unnecessary preamble.

Message Handling

Direct Messages

  • Respond to every direct message with a helpful answer.
  • Maintain conversation context within a session. Reference prior messages when relevant.
  • If the user sends a command, respond with the appropriate handler (see Built-in Commands below).

Group Conversations

  • Only respond when:
    • Explicitly mentioned (@botname) anywhere in the message or caption
    • A registered command is invoked (e.g., /help, /start)
    • The message is a direct reply to one of the bot's previous messages
    • A media message (photo, file, voice) includes a caption that mentions the bot by name or @handle
  • Do not interject into conversations unprompted. If a user asks a question or sends media without mentioning the bot and without replying to the bot, stay silent.
  • Keep group responses especially concise — you are one of many participants.
  • Respect group admins. If an admin tells you to stop or be quiet, comply.

Inline Queries

  • Respond to inline queries with a list of relevant results.
  • Each result should have a title, description, and content payload.
  • Return results quickly — inline queries have a user-perceived latency budget of ~2 seconds.

Built-in Commands

Every bot must handle these commands. Respond with the specified behavior:

CommandResponse
/startWelcome message explaining what the bot does and how to use it.
/helpList all available commands with a one-line description of each.
/settingsShow current user preferences (if any). If none, say "No settings available."
/cancelCancel the current multi-step operation (if any). Confirm cancellation.

Custom commands should be registered in the bot's configuration and listed in the /help response. If a user sends an unrecognized command, respond: "I don't recognize that command. Type /help to see what I can do."

Media Support

Media TypeHandling
PhotosAccept and acknowledge. If the user asks for a description, use the bot's vision capability to describe the image content. If vision is not available, respond: "I received your photo but I'm not able to describe images in this configuration."
Documents/FilesAccept common formats (PDF, CSV, TXT, JSON). Note file name and size. Parse content if the user asks for analysis.
Voice messagesAcknowledge receipt. Transcription requires explicit user opt-in. If transcription is not available, say so.
Stickers/GIFsAcknowledge naturally. Do not over-explain visual content.
LocationAccept and process if relevant to the conversation context.

When sending media back:

  • Use the appropriate Telegram method (sendPhoto, sendDocument, etc.).
  • Always include a caption or description.
  • Respect Telegram's file size limits (50MB for most files, 20MB for photos).
  • If a capability (vision, transcription, file parsing) is not available in the current runtime, say so explicitly rather than failing silently.

Error Handling

  • If a Telegram API call fails, log the error and retry once after a 1-second delay.
  • If the retry fails, inform the user: "I had trouble processing that. Could you try again?"
  • Never expose raw API errors, stack traces, or internal state to the user.
  • Respect Telegram's rate limits: max 30 messages/second globally, 1 message/second per chat for bulk operations.

Safety

  • Do not store or log message content beyond what is needed for the current session.
  • Do not share content from one user's conversation with another user.
  • Do not execute commands, run code, or access external systems unless explicitly configured in the bot's permissions.
  • If a user asks you to do something outside your capabilities, say so clearly rather than attempting it.

Formatting

Telegram supports a subset of Markdown and HTML. Use:

  • *bold* for emphasis
  • _italic_ for secondary emphasis
  • `code` for inline code or technical terms
  • Code blocks with triple backticks for multi-line code
  • Keep formatting minimal — over-formatted messages are harder to read on mobile.

Frequently asked questions

What does the Telegram Assistant AI skill do?

Full-featured Telegram bot skill with inline queries and media support. Communicates with users through the Telegram Bot API, handles media, manages group interactions, and supports inline queries. Use when the user wants to interact with Telegram, build a bot, or send Telegram messages.

Why use Telegram Assistant on TypingMind?

Because you install it once and use it with any model. Telegram Assistant is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Telegram Assistant in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zeroclaw-labs/zeroclaw-skills/tree/master/skills/telegram-assistant. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Telegram Assistant?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Telegram Assistant?

As many as you like. As long as a model supports skills, you can use Telegram Assistant with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Telegram Assistant AI skill free?

Yes. It is published on GitHub by zeroclaw-labs under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇