Prd DevelopmentSAFE

Product Management skills framework built on battle-tested methods for Claude Code, Cowork, Codex, and AI agents.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: prd-development
argument-hint: "[feature or initiative]"
description: Build a structured PRD that connects problem, users, solution, and success criteria. Use when turning discovery notes into an engineering-ready document for a major initiative.
intent: >-
  Guide product managers through structured PRD (Product Requirements Document) creation by orchestrating problem framing, user research synthesis, solution definition, and success criteria into a cohesive document. Use this to move from scattered notes and Slack threads to a clear, comprehensive PRD that aligns stakeholders, provides engineering context, and serves as a source of truth—avoiding ambiguity, scope creep, and the "build what's in my head" trap.
type: workflow
theme: pm-artifacts
best_for:
  - "Writing a complete PRD from scratch"
  - "Structuring product requirements for an engineering handoff"
  - "Documenting a major new feature before development begins"
scenarios:
  - "I need a PRD for a new AI-powered recommendation feature in our e-commerce platform"
  - "I've completed a discovery sprint and need to turn the findings into a PRD my engineers can act on"
estimated_time: "60-120 min"
---


## Purpose
Guide product managers through structured PRD (Product Requirements Document) creation by orchestrating problem framing, user research synthesis, solution definition, and success criteria into a cohesive document. Use this to move from scattered notes and Slack threads to a clear, comprehensive PRD that aligns stakeholders, provides engineering context, and serves as a source of truth—avoiding ambiguity, scope creep, and the "build what's in my head" trap.

This is not a waterfall spec—it's a living document that captures strategic context, customer problems, proposed solutions, and success criteria, evolving as you learn through delivery.

## Input

**Works best with:** The feature or initiative the PRD covers.
**Also useful:** Discovery notes, problem statements, user research, success metrics, and constraints — paste whatever exists; the workflow slots it into the right phases and skips what's already answered.

Anything supplied with the invocation itself — text after the skill name, a pasted context dump, or an appended `ARGUMENTS:` line — counts as answers already given. Use it and skip whatever it covers; don't re-ask.

**Arriving empty-handed? That works too.** The workflow starts at problem definition and builds up from there.

**Example invocation:** `Build a PRD for self-serve workspace provisioning — here are my discovery notes and the OKR it ladders to.`

## Key Concepts

### What is a PRD?

A PRD (Product Requirements Document) is a structured document that answers:
1. **What problem are we solving?** (Problem statement)
2. **For whom?** (Target users/personas)
3. **Why now?** (Strategic context, business case)
4. **What are we building?** (Solution overview)
5. **How will we measure success?** (Metrics, success criteria)
6. **What are the requirements?** (User stories, acceptance criteria, constraints)
7. **What are we NOT building?** (Out of scope)

### PRD Structure (Standard Template)

```markdown
# [Feature/Product Name] PRD

## 1. Executive Summary
- One-paragraph overview (problem + solution + impact)

## 2. Problem Statement
- Who has this problem?
- What is the problem?
- Why is it painful?
- Evidence (customer quotes, data, research)

## 3. Target Users & Personas
- Primary persona(s)
- Secondary persona(s)
- Jobs-to-be-done

## 4. Strategic Context
- Business goals (OKRs)
- Market opportunity (TAM/SAM/SOM)
- Competitive landscape
- Why now?

## 5. Solution Overview
- High-level description
- User flows or wireframes
- Key features

## 6. Success Metrics
- Primary metric (what we're optimizing for)
- Secondary metrics
- Targets (current → goal)

## 7. User Stories & Requirements
- Epic hypothesis
- User stories with acceptance criteria
- Edge cases, constraints

## 8. Out of Scope
- What we're NOT building (and why)

## 9. Dependencies & Risks
- Technical dependencies
- External dependencies (integrations, partnerships)
- Risks and mitigations

## 10. Open Questions
- Unresolved decisions
- Areas requiring discovery
```

### Why This Works
- **Alignment:** Ensures everyone (PM, design, eng, stakeholders) understands the "why"
- **Context preservation:** Captures research and strategic rationale for future reference
- **Decision log:** Documents what's in scope, out of scope, and why
- **Execution clarity:** Provides engineering with user stories and acceptance criteria

### Anti-Patterns (What This Is NOT)
- **Not a detailed spec:** PRDs frame the problem and solution; they don't specify UI pixel-by-pixel
- **Not waterfall:** PRDs evolve as you learn; they're not frozen contracts
- **Not a substitute for collaboration:** PRDs complement conversation, not replace it

### When to Use This
- Starting a major feature or product initiative
- Aligning cross-functional teams on scope and requirements
- Documenting decisions for future reference
- Onboarding new team members to a project

### When NOT to Use This
- For small bug fixes or trivial features (overkill)
- When problem and solution are already clear and aligned (just write user stories)
- For continuous discovery experiments (use Lean UX Canvas instead)

---

### Facilitation Source of Truth

When running this workflow as a guided conversation, use [`workshop-facilitation`](../workshop-facilitation/SKILL.md) as the interaction protocol.

It defines:
- session heads-up + entry mode (Guided, Context dump, Best guess)
- one-question turns with plain-language prompts
- progress labels (for example, Context Qx/8 and Scoring Qx/5)
- interruption handling and pause/resume behavior
- numbered recommendations at decision points
- quick-select numbered response options for regular questions (include `Other (specify)` when useful)

This file defines the workflow sequence and domain-specific outputs. If there is a conflict, follow this file's wor

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.