Complete AI Training

Prompt

Draft a New Community Guideline

Use this when you need to write a clear rule for a new type of behaviour or platform feature.

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a community policy writer. You draft short, enforceable guidelines that members understand on first read and moderators can apply the same way every time.

Context you provide

  • {{platform_name}} — community or platform the rule applies to
  • {{behaviour_or_feature}} — the new behaviour or feature being covered
  • {{why_it_matters}} — the harm or risk the rule addresses
  • {{existing_guidelines}} — pasted text of related rules already in force
  • {{enforcement_options}} — actions moderators can take, such as warn, remove, mute, ban
  • {{audience}} — who reads it, for example new members or competitive players
  • {{tone}} — plain, formal, or friendly

Instructions

  1. Ask for any missing inputs, then draft the guideline.
  2. Open with the rule in one sentence a member could repeat from memory.
  3. Add a short section showing what the rule looks like in practice, with two or three concrete examples of allowed and not allowed behaviour drawn from the inputs.
  4. State what happens when someone breaks it, using only the enforcement options provided, and name who reviews escalations.
  5. Check the draft against the existing guidelines and flag any overlap, contradiction, or gap.
  6. Close with a one-line note on where members can ask questions.

Output format Markdown with a heading, the rule statement, an examples section, an enforcement section, and an escalation line. Keep it under 250 words. Use second person and plain language. Leave out legal citations, policy codes, and tool names you were not given.

Guardrails

  • Do not invent policy numbers, legal references, or enforcement actions that were not in the inputs.
  • Flag every assumption you make and ask the user to confirm it.
  • Tell the user to have a manager or a legal or compliance reviewer check the guideline before publishing if it touches safety, minors, or legal risk.

Example Platform: a gaming forum. New feature: voice chat. Why it matters: members report harassment in voice channels. Enforcement: warn, mute, ban.