agentleFS
Sign inStart free
daniilganievdaniilganiev/telegram-dev/skills/new-bot/SKILL.md

new-bot

Skill0 starsChanged 36 days agoMITView on GitHub

Scaffold a Telegram bot backend in TypeScript (grammY) or Python (aiogram), webhook-ready, with optional Mini App button and Stars payments. Arguments are the project name and optionally ts or py.

  • Reads credentials

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. Bossmann007/cursor-kit★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository11 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check the runtime: node --version (22+) for ts, python --version (3.10+) for py.

    line 13
  2. Distinctive:

    Ask only two things: what the bot does in one sentence, and whether it opens a Mini App and/or takes payments.

    line 14
  3. Distinctive:

    Create the project from the framework's current docs, not from memory.

    line 16
  4. Very specific:

    Run the typecheck (tsc --noEmit) or python -m compileall plus a linter if present.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

New Telegram bot

Arguments: $ARGUMENTS. The first word is the project name (kebab-case; ask if missing). The second is the language: ts (grammY, default) or py (aiogram 3). If the current folder already has package.json or pyproject.toml, follow it instead.

  1. Check the runtime: node --version (22+) for ts, python --version (3.10+) for py. Ask only two things: what the bot does in one sentence, and whether it opens a Mini App and/or takes payments.
  2. Create the project from the framework's current docs, not from memory.
    • ts: src/bot.ts (handlers), src/server.ts (webhook with secret-token check), src/dev.ts (long polling for local runs), strict tsconfig.
    • py: app/bot.py (routers), app/server.py (aiohttp or FastAPI webhook with secret-token check), app/dev.py (polling), pyproject.toml, virtual env instructions.
  3. .gitignore with .env, node_modules, .venv, __pycache__; .env.example with BOT_TOKEN=, WEBHOOK_SECRET=, WEBAPP_URL=.
  4. /start that handles missing and unknown parameters, /help, and, if requested, a button that opens the Mini App via web_app.
  5. Payments requested: add the Stars handlers from telegram-payments with idempotent fulfilment.
  6. Run the typecheck (tsc --noEmit) or python -m compileall plus a linter if present. Start it only if the user has put their own token in .env; never ask for the token in chat.
  7. Finish with what the user does by hand: /newbot in @BotFather, token into .env, choose hosting, setWebhook with the secret, commands, menu button.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free