Product requirements document drafter from problem notes
Drafts a lean PRD from your problem notes and constraints: problem, goals and non-goals, users, requirements with priorities, success metrics, risks and open questions. Unknowns are marked, not filled with guesses.
Prompt in Product by AISkillHub Library
What it does
A PRD is useful when it makes the problem and the boundaries clear enough for design and engineering to make good decisions without you in the room. This prompt drafts that document from whatever you have: support data, customer quotes, a Slack thread, a strategy note. It keeps the document lean and makes every unknown visible.
**Use it when** you have a problem worth solving and need a first draft to review with engineering and design, rather than starting from a blank template.
**What you get** A PRD with these sections: 1. Problem, with the evidence and its source 2. Goals and non-goals 3. Users and the situations they are in 4. Requirements as numbered user-facing behaviours, each marked must, should or could 5. Success metrics with baseline, target and how each is measured 6. Scope and constraints 7. Risks and dependencies 8. Rollout and launch notes 9. Open questions, with the evidence available so far
**What it will not do** - It will not invent baselines, targets, research findings or user numbers. Missing values appear as `[needs: ...]`. - It will not prescribe implementation (database design, architecture). Requirements describe behaviour; engineering decides how. - It will not inflate scope. If the notes suggest more than the stated constraints allow, it moves the extra items to "could" or to a later phase and says why.
**Example** From notes about support handling about 40 invoice-export tickets a month and a three-week, one-engineer constraint, the prompt drafts a PRD for bulk invoice download by date range, lists CSV export and automatic sending to accountants as open questions, and marks the success target as `[needs: target agreed with support lead]`. See the example file.
How to use it
## How to use
1. Open `prompts/prd-drafter.md` and copy everything below the title line. 2. Replace each `{{variable}}` with your own content. Paste long material (notes, transcripts, tables) directly in place of the variable; keep the surrounding tags so the model can tell inputs apart. 3. Start a new chat in ChatGPT, Claude or Gemini and paste the filled prompt as your first message. 4. Read the output against the quality checks at the end of the prompt before you use or send it.
## Variables
- `{{problem_notes}}`: everything you know about the problem: data, quotes, tickets, observations, with sources where possible. - `{{product_context}}`: what exists today in the relevant area of the product, and relevant roles or permissions. - `{{constraints}}`: time, people, technical or business constraints. - `{{audience}}`: who will read the PRD, e.g. `engineering, design, support lead`.
If you do not have a value for an optional variable, write `none` rather than deleting it, so the prompt still reads correctly.
## Example
`prompts/prd-drafter.example.md` shows the prompt with every variable filled and a trimmed sample of the output, so you can see the expected shape before you run it on real material.
## Reusing it
To reuse it often, save the prompt (with the variables left in) as the instructions of a Claude Project, a custom GPT or a Gemini Gem, then paste only the inputs in each new chat.
Files
Save each file at the path shown, relative to your project root.