Home/Blog/How to Write Telegram Channel Rules and a Welcome Pack
Blog

How to Write Telegram Channel Rules and a Welcome Pack

P
promptstudio
How to Write Telegram Channel Rules and a Welcome Pack

Telegram packs slide into captions. Rules and welcome only. Not WhatsApp. Not Discord.

The matching generator is the Telegram Channel Rules and Welcome Pack from a Community Brief (Not Captions) (Telegram Channel Rules And Welcome Pack From A Community Brief Not Captions) prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).

Rules from the community brief

Write Telegram channel rules, welcome message, and pin text from a community brief. Not captions, not WhatsApp community rules, not Discord rules. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.

Paste these fields before you hit run:

Community brief (purpose, audience, hard lines): [Brief]
Rule count max: [N or 8]
Welcome length max (chars): [WMax or 500]
Pin length max (chars): [PMax or 300]
Moderator contacts I allow (or UNKNOWN): [Mods]
Words I must not use: [Banned]
What I must never invent: [Never]
Output format: [Format]
Language: [Lang]
Chat languages allowed: [ChatLang]

That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.

Welcome and pin as separate blocks

Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.

Walk the Generate list in order:

  1. Honesty ledger: Brief, N, WMax, PMax, Mods, ChatLang, Lang.
  2. Purpose one-liner from Brief.
  3. Up to N numbered rules with short examples.
  4. Welcome message under WMax; print char count.
  5. Pin text under PMax; print char count. Mods or MOD UNKNOWN.
  6. ChatLang line.
  7. Refuse: caption packs, WhatsApp rules, Discord AutoMod invent, inventing phone numbers.
  8. Compliance pass: Banned and Never. Format as Format. Gaps list of five.

If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.

Leave ads policy UNKNOWN if blank

Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.

Honor the constraints as hard stops, not vibes:

  • Telegram channel rules and welcome from Brief. Not captions.
  • Never invent contacts or legal claims.
  • Char caps are hard; print counts.
  • No emojis.

When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.

Refuse hashtag and caption engines

Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.

Tags on the card (telegram channel rules, telegram welcome pack, not a caption engine) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.

Fill the card, then run

Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.