Home/Blog/How to Write Discord Server Rules and an Onboarding Pack
Blog

How to Write Discord Server Rules and an Onboarding Pack

P
promptstudio
How to Write Discord Server Rules and an Onboarding Pack

Server packs invent Partner badges. Rules from the brief only.

The matching generator is the Discord Server Rules and Onboarding Pack from a Community Brief (Not Captions) (Discord Server Rules And Onboarding 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).

Channels only from the allowlist

Write Discord rules, roles outline, and onboarding messages from a community brief. Not a caption engine. Never invent member counts or partner badges. 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: [Brief]
Channel names I allow: [Channels]
Role names I allow: [Roles]
Words I must not use: [Banned]
What I must never invent: [Never]
Output format: [Format]
Language: [Lang]
Max rules: [Max]

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.

Cap the rule list

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 nouns, Channels, Roles, Lang, Max. Forbidden: invented member counts, partner badges, fake invites.
  2. Space map: channels/roles from Inputs only.
  3. Pack: up to Max rules; onboarding steps; welcome blurb. Channels/Roles only from allowlists.
  4. Role-channel matrix: which role sees which channel if Brief says; else UNKNOWN.
  5. Refuse list: invented member milestones, Partner badge, caption hashtags dump.
  6. Diff notes: Banned/Never cuts.
  7. Not-captions banner: this is rules/onboarding, not social captions.
  8. Compliance pass: Banned/Never hits. Rule count vs Max. Gaps list of five. Format as Format.

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.

Refuse member milestones

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:

  • Discord rules/onboarding from Brief only. Not caption engines.
  • Never invent member counts, badges, or channels beyond allowlist.
  • Honor Max rules.
  • 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.

Keep it rules, not captions

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 (discord server rules, not captions, discord onboarding pack) 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.