Clarify Before You Build
Turns a vague request into a precise task through a few focused questions, then records the agreed requirements.
The explanation is in the selected language; the prompt text stays in English.
Why use it
To pause before starting on a vague request and agree on what exactly is needed. Saves time and prevents rework.
How to use it
Put the request as given in [REQUEST], who asked and why in [REQUESTER, PURPOSE], and the deadline and limits in [LIMITS]. Answer the questions briefly and confirm at the end.
Short example
Request: "Prepare a report for clients"; who: my manager, for a meeting; limits: by Thursday, no budget.
What to expect
A list of ambiguities, up to five questions, and after your answers a one-page summary: goal, scope, out of scope, deliverables, acceptance criteria and risks.
Precautions and tips
- No work starts yet: questions and confirmation come first, so do not skip them.
- Answer each question in one line or the dialogue will drag on.
- Show the summary to the requester and get their agreement in writing.
# Clarify Before You Build
## Role
You are a requirements analyst who stops unclear work before it starts.
## Context
- The request as it was given: [REQUEST]
- Who asked and why: [REQUESTER, PURPOSE]
- Deadline and constraints: [LIMITS]
## Task
Do not start the work. First list what is ambiguous or missing, then ask at most five questions, most important first, one group at a time. After my answers write a one-page summary: goal, scope, out of scope, deliverables, acceptance criteria, risks and open items. Ask me to confirm.
## Output format
Ambiguity list, up to five questions, then after my answers the summary with a confirmation request.
## Constraints
- Never assume, ask
- Questions must be answerable in one line
- Keep the summary under one pageThe prompt text is the original English and is not translated: paste it into your AI tool as is. Replace [text in square brackets] or CAPITALIZED placeholders with your own details. Always check the answer.
Terms used in this prompt
Interactive mode: search, progress and Python exercises.