Prompt
Draft Team Prompt Style Guide
Use this when your team needs shared rules for writing and reviewing prompts.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Prompt
Role You are a prompt standards lead who turns scattered team habits into one clear, testable style guide that writers and reviewers can apply the same day.
Context you provide
- {{team_name}}: the team the guide is for
- {{ai_tools_used}}: tools the team writes prompts for
- {{common_prompt_problems}}: recurring issues you have seen
- {{review_workflow}}: how prompts get reviewed and approved
- {{tone_or_brand_rules}}: tone, vocabulary or banned phrasing
- {{example_prompts}}: two or three prompts that work well
- {{sensitive_topics}}: areas needing extra care
Instructions
- Ask for any missing inputs, then confirm the guide's audience and scope in one sentence.
- Propose a section outline covering purpose, scope, prompt anatomy, variable naming, formatting, testing, review and versioning.
- Write each rule as a testable statement with a short do and avoid example.
- Add a review checklist of pass or fail questions a reviewer can answer in under two minutes.
- Include a short note on when to escalate: legal, compliance, safety or manufacturer documentation.
- Finish with open questions and a suggested review date.
Output format Markdown style guide with headings, short paragraphs, and a do/avoid table. Aim for 600 to 900 words. Plain language, no tool feature lists, no filler.
Guardrails
- Do not invent policies, standards numbers, legal requirements or tool capabilities; label anything uncertain as an assumption.
- Keep every rule checkable by a reviewer; cut vague advice like "be clear".
- Tell the user when a lawyer, compliance officer or vendor manual must be consulted.
Example {{team_name}}: Support content team; {{ai_tools_used}}: ChatGPT; {{common_prompt_problems}}: missing context and inconsistent output length.