Skip to content

Telegram Bot & Mini App Dev

Guides the agent through building Telegram bots, Mini Apps and clients using the Telegram APIs

Stars
23,127
Licence
MIT
Files
4 files

What it does

When installed, the agent gets a reference guide to the Telegram ecosystem: the Bot API (sending messages, polls, inline keyboards, webhooks, payments with Stars), Mini Apps (web apps that run inside Telegram, using the telegram-web-app JavaScript object), and the lower-level MTProto/TDLib route for building custom clients. When you ask for help with a Telegram project, it can produce starter Python bot code, Flask webhook code, keyboard and callback handling, and HTML/JS Mini App templates that follow these patterns. The skill's text is mostly in Chinese, and it is a guide rather than a tool that talks to Telegram itself.

Great for

  • Developers starting a new Telegram bot who want working boilerplate in Python
  • Front-end developers building a Telegram Mini App and needing the WebApp API reference
  • Teams planning a custom Telegram client who need an overview of Bot API, Mini Apps and TDLib

Skip it if

  • Non-developers expecting a finished bot with no coding: the output is code you must deploy and maintain yourself
  • Production bots handling payments or personal data without a security review: the examples hardcode tokens and skip input validation, webhook secret checks and error handling
  • Questions about Telegram features the guide does not cover in depth, such as the MTProto client API details, where the agent may give incomplete or outdated answers

Try asking

  • “Write a Python Telegram bot that echoes messages and replies with an inline keyboard”
  • “Set up a Flask webhook for my Telegram bot and explain the HTTPS requirements”
  • “Create a Telegram Mini App HTML page with a main button that sends data back to the bot”
  • “Explain the difference between Bot API, Mini Apps and TDLib for my project”
Step-by-step guide: how to use Telegram Bot & Mini App DevInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 4 original files, the MIT licence and an attribution note.

    telegram-dev.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip telegram-dev.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip telegram-dev.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Store the bot token in an environment variable or secrets manager rather than pasting it into code, since the examples hardcode it
  • Ask for webhook secret token verification and input validation before deploying anything public-facing
  • Name the exact Telegram feature (for example sendInvoice or Mini App initData checks) so the agent pulls the matching section of the reference files

What's inside

  • references/Dynamic_View_Alignment_Implementation_Document.md
  • references/index.md
  • references/Telegram_Bot_Button_and_Keyboard_Implementation_Template.md
  • SKILL.md

Redistributed unmodified from 2025Emma/vibe-coding-cn under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.