PRD — Product requirements for a product or phase
A PRD answers what and why for a whole product or phase, with acceptance criteria someone can
check without asking the author. Features inside it get their own spec later (spec skill).
Before writing
- Read what exists: README,
docs/standards.md, previous PRDs in docs/prd/, the last gate report
in docs/gates/ (the last approved gate tells which phase comes next), research notes.
- Ask the user what you cannot infer (or, as a subagent, return the questions under Open
questions and stop; the caller asks the user): who the users are, the outcome that makes this
phase a success, hard constraints (deadline, budget, compliance, platforms), and what is
explicitly out. In the main conversation, use the
AskUserQuestion tool — multiple choice, the
recommended option first, free text always available. Follow the brainstorming skill when the
idea is still fuzzy.
Write docs/prd/<slug>.md (or docs/prd/PHASE-N.md for phased projects)
# PRD — <Product or phase name>
Status: draft | approved | implemented | superseded (by <link>) · Date: <YYYY-MM-DD> · Owner: <user>
## Problem and evidence
<Who has which problem today and how we know: data, support tickets, interviews, observed behavior.
If there is no evidence yet, say so — that is a value risk below.>
## Objective
<One sentence: the outcome this delivers.>
## Success metrics
| Metric | Baseline | Target | When measured |
|--------|----------|--------|---------------|
| <outcome, e.g. invoices paid within 30 days> | 61% | 75% | 60 days after release |
## Appetite
<How much time/effort this phase is worth (e.g. "2 weeks, one developer"). When the work outgrows
it, cut scope rather than extend the budget.>
## User stories
- As a <user>, I want <capability> so that <benefit>. (justification: <link or reason>)
## Acceptance criteria
| ID | Criterion | How to verify | Who verifies |
|----|-----------|---------------|--------------|
| C1 | <observable result with a number when it is about speed/size/quality> | <command, test, or written script step> | QA / user / automated |
## Out of scope
- <explicitly not in this phase, and where it goes instead>
## Rabbit holes and no-gos
- <tempting detail or edge case that would blow the appetite, and the decision taken to avoid it>
## Risks
- [value | usability | feasibility | viability] <risk> — early warning sign: <concrete signal> — mitigation: <…>
## Human test script
<Required when real users must validate the phase: step by step, what to observe, what to ask afterwards.>
## Blockers
- <decisions only the user can make; the PRD stays draft while this list is not empty>
Rules for criteria
- Every criterion is checkable by a command/test or by a written script someone can follow.
Words like "intuitive", "fast", "works well" need a number or a test, or they are not criteria.
- One behavior per criterion; IDs are stable so specs, tasks and gate reports can reference them.
- A phase PRD does not pull in deliverables from the next phase — note them under Out of scope.
- Success metrics are outcomes measured after release (adoption, conversion, time saved); acceptance
criteria are what the gate checks before release. Keep them apart, because shipping every criterion
does not prove the outcome happened.
- Tag each risk with its type — value (will they want it), usability (can they use it), feasibility
(can we build it), viability (does it work for the business: cost, legal, support) — so the
riskiest kind gets tested first.
After
Show the user the criteria table, the out-of-scope list and the blockers, and ask for approval (or,
as a subagent, return them under Open questions). When approved: set Status: approved
(verify later sets implemented; a replaced PRD becomes superseded), record significant
product/technical decisions with the adr skill, and hand the PRD to software-architect, which
writes contracts, ADRs and the feature list in docs/prd/<slug>-architecture.md. Every feature
then gets its own spec (spec skill; quick spec for small ones) — a PRD is never broken into tasks
directly.
1---2name: prd3description: "Writes a PRD in docs/prd/ with metrics, acceptance criteria, no-gos, risks and blockers. Use for level-3 work: a new system or product phase, or when the user asks for a PRD; feature-level work uses spec."4allowed-tools: Read Glob Grep Write Edit5metadata:6 source: https://skillmd.com/skills/jeffersonvalente/prd7---89# PRD — Product requirements for a product or phase1011A PRD answers *what* and *why* for a whole product or phase, with acceptance criteria someone can12check without asking the author. Features inside it get their own spec later (`spec` skill).1314## Before writing15161. Read what exists: README, `docs/standards.md`, previous PRDs in `docs/prd/`, the last gate report17 in `docs/gates/` (the last approved gate tells which phase comes next), research notes.182. Ask the user what you cannot infer (or, as a subagent, return the questions under **Open19 questions** and stop; the caller asks the user): who the users are, the outcome that makes this20 phase a success, hard constraints (deadline, budget, compliance, platforms), and what is21 explicitly out. In the main conversation, use the `AskUserQuestion` tool — multiple choice, the22 recommended option first, free text always available. Follow the `brainstorming` skill when the23 idea is still fuzzy.2425## Write `docs/prd/<slug>.md` (or `docs/prd/PHASE-N.md` for phased projects)2627```markdown28# PRD — <Product or phase name>2930Status: draft | approved | implemented | superseded (by <link>) · Date: <YYYY-MM-DD> · Owner: <user>3132## Problem and evidence33<Who has which problem today and how we know: data, support tickets, interviews, observed behavior.34If there is no evidence yet, say so — that is a value risk below.>3536## Objective37<One sentence: the outcome this delivers.>3839## Success metrics40| Metric | Baseline | Target | When measured |41|--------|----------|--------|---------------|42| <outcome, e.g. invoices paid within 30 days> | 61% | 75% | 60 days after release |4344## Appetite45<How much time/effort this phase is worth (e.g. "2 weeks, one developer"). When the work outgrows46it, cut scope rather than extend the budget.>4748## User stories49- As a <user>, I want <capability> so that <benefit>. (justification: <link or reason>)5051## Acceptance criteria52| ID | Criterion | How to verify | Who verifies |53|----|-----------|---------------|--------------|54| C1 | <observable result with a number when it is about speed/size/quality> | <command, test, or written script step> | QA / user / automated |5556## Out of scope57- <explicitly not in this phase, and where it goes instead>5859## Rabbit holes and no-gos60- <tempting detail or edge case that would blow the appetite, and the decision taken to avoid it>6162## Risks63- [value | usability | feasibility | viability] <risk> — early warning sign: <concrete signal> — mitigation: <…>6465## Human test script66<Required when real users must validate the phase: step by step, what to observe, what to ask afterwards.>6768## Blockers69- <decisions only the user can make; the PRD stays draft while this list is not empty>70```7172## Rules for criteria7374- Every criterion is checkable by a command/test or by a written script someone can follow.75 Words like "intuitive", "fast", "works well" need a number or a test, or they are not criteria.76- One behavior per criterion; IDs are stable so specs, tasks and gate reports can reference them.77- A phase PRD does not pull in deliverables from the next phase — note them under Out of scope.78- Success metrics are outcomes measured after release (adoption, conversion, time saved); acceptance79 criteria are what the gate checks before release. Keep them apart, because shipping every criterion80 does not prove the outcome happened.81- Tag each risk with its type — value (will they want it), usability (can they use it), feasibility82 (can we build it), viability (does it work for the business: cost, legal, support) — so the83 riskiest kind gets tested first.8485## After8687Show the user the criteria table, the out-of-scope list and the blockers, and ask for approval (or,88as a subagent, return them under **Open questions**). When approved: set `Status: approved`89(`verify` later sets `implemented`; a replaced PRD becomes `superseded`), record significant90product/technical decisions with the `adr` skill, and hand the PRD to `software-architect`, which91writes contracts, ADRs and the feature list in `docs/prd/<slug>-architecture.md`. Every feature92then gets its own spec (`spec` skill; quick spec for small ones) — a PRD is never broken into tasks93directly.