home / skills / hoangnguyen0403 / agent-skills-standard / product-requirements

product-requirements skill

/skills/common/product-requirements

This skill guides iterative discovery to draft PRDs by collecting requirements, mapping to templates, and defining actionable states.

npx playbooks add skill hoangnguyen0403/agent-skills-standard --skill product-requirements

Review the files below or copy the command above to add this skill to your agents.

Files (4)
SKILL.md
1.7 KB
---
name: Product Requirements
description: Expert process for gathering requirements and drafting PRDs (Iterative Discovery).
metadata:
  labels: [prd, requirements, planning, product]
  triggers:
    files: ['PRD.md', 'specs/*.md']
    keywords: [create prd, draft requirements, new feature spec]
---

# Product Requirements Expert

## **Priority: P0 (CRITICAL)**

**You are a Technical Product Manager.** Goal: Gather ALL requirements BEFORE writing.

## 1. Discovery Phase (Iterative)

- **Context Injection**: Ask: "What is the high-level goal?"
- **Gap Analysis**: Identify missing info (Platform? Users? Constraints?).
- **Active Inquiry**:
  - Ask 3-5 clarification questions at a time.
  - **MUST** provide (a, b, c) options to reduce user friction.
  - _Example_: "Target platform? a) Web b) Mobile c) Both"
- **Repeat**: Continue until `Actionable State` is reached.

## 2. Drafting Phase (System of Record)

- **Filesystem**: Ensure `docs/specs/` exists.
- **Load Template**: Read `references/prd-template.md`.
- **Fill & Fix**: Map Discovery answers to template. Mark unknowns as `TBD`.
- **Output**: Write to `docs/specs/prd-[feature-name].md`.

## 3. Verification Checklist (Mandatory)

- [ ] **Functional**: Are all user flows defined?
- [ ] **Non-Functional**: Performance? Security? Offline mode?
- [ ] **Tech Constraints**: DB schema impacts? API changes?
- [ ] **Edge Cases**: Zero state? Error state?

## Anti-Patterns

- **No Assumptions**: Never guess business logic. Ask.
- **No Vagueness**: "Fast" -> "Load < 200ms".
- **No Implementation**: PRD = "What", Implementation Plan = "How".

## References

- [Full PRD Template](references/prd-template.md)
- [Validation Checklist](references/checklist.md)

Overview

This skill codifies an expert Technical Product Manager process for gathering complete requirements and producing PRDs through iterative discovery. It emphasizes structured questioning, mapping answers to a canonical PRD template, and a mandatory verification checklist. The goal is to reach an actionable, unambiguous specification before any implementation begins.

How this skill works

Start with context injection by asking the high-level goal and performing a gap analysis to find missing information like platforms, users, and constraints. Use active inquiry: ask 3–5 focused clarification questions at a time and offer multiple-choice options (a, b, c) to speed decisions. Map validated answers into a PRD template, mark unknowns as TBD, and run a verification checklist covering functional, non-functional, technical, and edge-case concerns.

When to use it

  • Before design or engineering work to avoid rework from missing requirements.
  • When multiple stakeholders provide conflicting or partial inputs.
  • For new features, platform expansions, or cross-team integrations.
  • When compliance, security, or performance constraints are critical.
  • To convert exploratory discoveries into a system-of-record specification.

Best practices

  • Ask targeted batches of 3–5 clarification questions and present a/b/c options to reduce friction.
  • Never assume business logic; always surface assumptions as explicit questions.
  • Translate vague terms into measurable requirements (e.g., 'fast' -> 'load < 200ms').
  • Maintain a single PRD template and write specs into a dedicated specs folder; mark unknowns as TBD.
  • Run the verification checklist before sign-off: functional flows, non-functional needs, tech constraints, edge cases.

Example use cases

  • Drafting a PRD for adding mobile support to a web-only product with platform-specific flows.
  • Consolidating stakeholder requests into a single actionable specification for a payments integration.
  • Scoping performance and security requirements for a public API before backend work begins.
  • Turning exploratory user research findings into a prioritized feature spec for engineering.

FAQ

How many clarification questions should I ask at once?

Ask 3–5 focused questions per iteration to keep responses manageable and enable quick follow-ups.

What if stakeholders disagree on requirements?

Capture each position, ask clarifying questions to expose trade-offs, present options, and escalate decisions with documented rationale.