Telegram Connection logo

Telegram Connection

Organization
rejot-dev
telegram-connection

Configure and automate the Backoffice Telegram bot capability. Use when setting up Telegram, handling events with source "telegram" and eventType "message.received", sending chat replies, downloading Telegram files, or debugging Telegram hooks and runtime tools.

Overview

Publisherrejot-dev
Repositoryfragno
Skill nametelegram-connection
Stars
62
Forks
6
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 rejot-dev on GitHub. Read the source before you install it.

Installation

Install the Telegram Connection 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.
  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/rejot-dev/fragno.git /tmp/fragno
mkdir -p .claude/skills
cp -r /tmp/fragno/apps/backoffice/content/static/skills/telegram-connection .claude/skills/telegram-connection
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Telegram Connection 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 Connection 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 Connection 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 Connection

Use this skill for the organization-scoped Telegram bot integration: bot setup details, inbound message semantics, Telegram hook scope, and Telegram-specific runtime tool purposes.

Telegram configuration

User-supplied configuration fields:

  • botToken: Telegram BotFather token. Secret.
  • botUsername: optional bot username, with or without @.
  • apiBaseUrl: optional Telegram API base URL override.

Backoffice generates the webhook secret during configuration.

Setup procedure:

  1. Tell the user how to register a bot with Telegram:
    • Open a chat with the verified @BotFather account in Telegram.
    • Send /newbot and follow the prompts to choose a display name and a unique username.
    • Copy the bot token BotFather returns and enter it in the Backoffice Telegram connection.
    • Treat the bot token like a password and regenerate it in BotFather if it is exposed.
  2. Save the connection configuration. Backoffice generates a cryptographically secure webhook secret, derives the organization-scoped webhook URL, and registers both with Telegram.

The stored secret must match the X-Telegram-Bot-Api-Secret-Token header Telegram sends to the webhook.

Telegram events

Message received

Fires when the Telegram webhook receives a bot message for the organization.

Catalog identity:

  • source: telegram
  • eventType: message.received

Before parsing payloads, inspect the catalog schema with codemode:

js
const descriptor = await events.catalogGet({ source: "telegram", eventType: "message.received" });

Payload fields:

  • messageId: Telegram message id as a string.
  • chatId: Telegram chat id as a string. Use this with Telegram chat tools.
  • fromUserId: Telegram user id when available, otherwise null.
  • text: message text when available, otherwise null.
  • attachments: optional attachment metadata. Voice notes and files are represented here, not as raw Telegram message.voice fields.

When reading a queued ingest hook through internal.hooksGet({ fragment: "automations", hookId }), the normalized Telegram payload is inside the event envelope:

js
const entry = await internal.hooksGet({ fragment: "automations", hookId });
const payload = entry?.payload?.payload;
const attachments = payload?.attachments ?? [];

Actor:

  • scope: external
  • source: telegram
  • type: chat
  • id: the Telegram chat id

Common automation pattern: filter on event.source === "telegram" and event.eventType === "message.received", then route slash commands, plain text, or attachments.

Capability configured

Fires after Telegram is configured for an organization for the first time. Use it to bootstrap Telegram-specific automation state.

Catalog identity:

  • source: telegram
  • eventType: capability.configured

Hook scope: telegram.

Telegram tools

Telegram tools can:

  • send chat messages;
  • send typing indicators;
  • edit existing messages;
  • resolve Telegram file metadata;
  • download Telegram files.

Use codemode first. The telegram provider methods are sendMessage, sendChatAction, editMessage, getFile, and downloadFile.

Example:

js
await telegram.sendMessage({ chatId, text: "Hello", parseMode: "Markdown" });

Frequently asked questions

What does the Telegram Connection AI skill do?

Configure and automate the Backoffice Telegram bot capability. Use when setting up Telegram, handling events with source "telegram" and eventType "message.received", sending chat replies, downloading Telegram files, or debugging Telegram hooks and runtime tools.

Why use Telegram Connection on TypingMind?

Because you install it once and use it with any model. Telegram Connection 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 Connection in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/rejot-dev/fragno/tree/main/apps/backoffice/content/static/skills/telegram-connection. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Telegram Connection?

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 Connection?

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

Is the Telegram Connection AI skill free?

Yes. It is published on GitHub by rejot-dev 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 👇