使い方
- インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
- 必要なツール、認証情報、対応環境を原文で確認します。
- 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/aroyburman-codes/pm-skills --skill prd-writer開始前の確認
- 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
- スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。
PRD Writer Skill
Generate a complete, structured PRD from a feature idea, problem statement, or brief description.
When to Use
- User needs to write a PRD for a new feature
- User has an idea and wants it turned into a structured spec
- User says
/prd-writerfollowed by a feature description - Any time a product requirement needs to be documented
Framework: PRD Structure
1. Overview
- Feature name: Clear, descriptive name
- Author: [to be filled]
- Date: Current date
- Status: Draft / In Review / Approved
- One-liner: What this feature does in one sentence
2. Problem Statement
- What problem are we solving? Describe the user pain point or business need
- Who has this problem? Primary user segment
- How big is this problem? Estimated impact (users affected, frequency, severity)
- Why solve it now? Urgency, strategic alignment, competitive pressure
3. Goals & Non-Goals
Goals:
- 3-5 specific, measurable goals this feature should achieve
- Each goal maps to a user need or business objective
Non-Goals:
- Explicitly list what this feature will NOT do
- Prevents scope creep and sets expectations
4. User Stories
Write 3-5 user stories in the format:
As a [user type], I want to [action] so that [benefit].
Include acceptance criteria for each:
- Given [context], when [action], then [expected result]
5. Detailed Requirements
Functional Requirements:
| ID | Requirement | Priority (P0/P1/P2) | Notes |
|---|---|---|---|
| FR-1 | |||
| FR-2 |
Non-Functional Requirements:
- Performance: Latency, throughput, scalability targets
- Security: Auth, data handling, compliance
- Accessibility: WCAG level, screen reader support
- Reliability: Uptime, error handling, graceful degradation
For AI/ML features, also include:
- Model requirements: Accuracy, latency, cost per inference
- Data requirements: Training data, eval data, data pipeline
- Safety requirements: Content policy, guardrails, fallback behavior
- Eval criteria: How model quality will be measured
6. UX & Design
- User flow: Step-by-step walkthrough of the primary flow
- Key screens/states: Describe the main UI states (loading, empty, error, success)
- Edge cases: What happens when things go wrong?
- Design references: Links to mockups/wireframes (placeholder)
7. Technical Approach
- Architecture: High-level system design
- Dependencies: APIs, services, teams needed
- Data model: Key entities and relationships
- Migration: Any data migration or backward compatibility concerns
8. Success Metrics
- Primary metric: The one number that tells us this feature worked
- Secondary metrics (3-4): Supporting indicators
- Guardrail metrics (2-3): What must NOT regress
- Measurement plan: How and when to measure
9. Launch Plan
- Rollout strategy: Feature flag → internal → beta → GA
- Launch criteria: What must be true before each stage
- Rollback plan: How to revert if something goes wrong
- Communication: Who needs to know and when
10. Open Questions
- List unresolved questions that need stakeholder input
- Include who should answer each question
Output Format
Generate as clean markdown, ready to paste into Notion, Confluence, Google Docs, or any doc tool. Use tables for requirements. Be specific and actionable — avoid vague language.
Research-First Workflow
- Research — Search for comparable features from competitors, best practices, and relevant technical approaches.
- Generate the complete PRD following the structure above.
- Flag open questions and assumptions that need validation.

