telegram-bot-factory
Skill0 starsChanged 5 months agoMITView on GitHub
Use when Christian wants to create or modify a Telegram persona bot. Triggers on 'new telegram bot', 'add a bot', 'another persona bot', 'wire up a bot with Groq'. Scaffolds an end-to-end persona bot the way his existing 3 are built: BotFather token steps, persona system prompt, Groq wiring, launchd plist for autostart, and logging.
In this repository9 other files it gives its agents.
- ai-brainSkill
- assumption-checkSkill
- cover-letter-loopSkill
- design-inspoSkill
- luno-osSkill
- memory-hygieneSkill
- research-to-vaultSkill
- skill-routerSkill
- vault-librarianSkill
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
- Very specific: line 22
Script: create the bot script following the existing bots' structure (reuse, don't reinvent — find the existing bot files first via the …
- Very specific: line 23
Autostart: write a launchd plist (Label, ProgramArguments → python + script, RunAtLoad, KeepAlive, StandardOut/Error log paths).
- Distinctive: line 29
Keep the full-access Claude bridge locked to the authorized chat ID only.
- Distinctive: line 30
Don't commit tokens or the Groq key to git.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
Telegram Bot Factory
Reproduces the pattern behind Christian's 3 existing bots (Business / Learning / General) so the next one takes minutes.
Stack (match existing)
- Telegram Bot API token from BotFather.
- Groq for the LLM persona responses.
- Python bot script per persona.
- launchd
.plistin~/Library/LaunchAgents/for autostart + keepalive. - Log file per bot.
Procedure
- Define persona: name, purpose, tone, system prompt. Keep prompts short and specific.
- Token: walk him through BotFather (
/newbot, name, username ending inbot) and capture the token. Note: brand-new Telegram accounts have a cooldown before new bots. - Script: create the bot script following the existing bots' structure (reuse, don't reinvent — find the existing bot files first via the Claude Index /
~/Documents/Codes). Wire the Groq key and persona prompt. - Autostart: write a launchd plist (Label, ProgramArguments → python + script, RunAtLoad, KeepAlive, StandardOut/Error log paths).
launchctl loadit. - Logo (optional): Claude-themed icon → BotFather
/setuserpic. - Verify: send a test message, confirm a Groq-backed reply and that the log is writing.
Guardrails
- Reuse the existing bots' code structure; locate them before writing new code.
- Keep the full-access Claude bridge locked to the authorized chat ID only.
- Don't commit tokens or the Groq key to git.
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
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.

