Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Prd Create

ASecurity

Use when the user wants a new Product Requirements Document — 'criar um PRD', 'escrever os requisitos de', 'new PRD for', 'documento de requisitos' — through a 12-step interview, one question at a time, ending with an approval gate. Do NOT use to change an existing PRD (prd- refine) or to plan implementation.

3 stars
0 votes
0 copies
0 views
Added 9/28/2026
businessbashtestinggit

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 9/28/2026

$npx -y skills add pwdev-solucoes/pwdev-claude-marketplace --skill prd-create --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Prd Create?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Prd Create
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/pwdev-solucoes-prd-create/badge)](https://www.skillsdirectory.com/skills/pwdev-solucoes-prd-create)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: prd-create
description: >
  Use when the user wants a new Product Requirements Document — 'criar um PRD', 'escrever os
  requisitos de', 'new PRD for', 'documento de requisitos' — through a 12-step interview, one
  question at a time, ending with an approval gate. Do NOT use to change an existing PRD (prd-
  refine) or to plan implementation.
metadata:
  version: 3.0.0
---

# Create a PRD

## Method (inline — you run in the MAIN context)
You are the PRD interviewer. Follow
`<plugin-root>/references/interview-method.md` end-to-end: persona,
principles, the 12-step process, smart defaults, consistency checks, opening
message. Never delegate the interview to a subagent — you interview the human, and
subagents cannot talk to the human.

## Input
The arguments: brief description of the feature or system (required).

## Pre-check

```bash
mkdir -p .planning/prds
```

## Flow

### STEP 0 — Language
Follow `<plugin-root>/references/language.md` (resolve `lang` from
`.planning/config.json`; ask only if unset).

### STEP 1 — Determine PRD slug

From the arguments, generate a kebab-case slug (e.g., "user-authentication", "inventory-management").

Create directory:
```bash
mkdir -p .planning/prds/{slug}
```

### STEP 2 — Start Interview

Follow the 12-step interview process from `references/interview-method.md`:

1. Context and overview
2. Problem and opportunity
3. Objectives and success metrics
4. Scope
5. Functional requirements
6. Non-functional requirements
7. Architecture and approach
8. Decisions and trade-offs
9. Dependencies
10. Risks and mitigation
11. Acceptance criteria
12. Testing and validation

**Rules:**
- One question at a time
- Summarize at end of each step
- Confirm before moving on
- Mark unknowns as hypothesis

### STEP 3 — Consistency Checks

Before generating, run all consistency checks from `references/interview-method.md`.
Flag any issues and resolve with the user.

### STEP 4 — Generate PRD.md

Write to `.planning/prds/{slug}/PRD.md` following exactly the template in
`<plugin-root>/templates/PRD.template.md`.
Log: `sh "<plugin-root>/scripts/audit-log.sh" event create "" completed ".planning/prds/{slug}/PRD.md" ""`

### STEP 4.1 — Approval gate

Show a 3-line summary (feature, number of FRs, open hypotheses), then ask:

```
Approve this PRD? Approved PRDs can be turned into a roadmap.
(y = mark APPROVED / n = keep as DRAFT)
```

On yes → set the header line to `Status: APPROVED`. On no → keep `Status: DRAFT`.
Never set `APPROVED` without the user's explicit yes.

### STEP 5 — Ask about JSON export

```
The PRD has been generated in Markdown.

Would you also like a JSON export with English keys? (y/n)
```

If yes → generate `.planning/prds/{slug}/prd.json` following the canonical
JSON structure in `<plugin-root>/references/interview-method.md`.

### STEP 6 — Ask about commit

```
📋 PRD created: .planning/prds/{slug}/PRD.md

Would you like to commit this PRD to the repository? (y/n)
```

If yes:
```bash
git add .planning/prds/{slug}/
git commit -m "docs(prd): add PRD for {slug}"
```

### STEP 7 — Summary

```
✅ PRD created

📄 Files:
  .planning/prds/{slug}/PRD.md      ← Structured PRD
  .planning/prds/{slug}/prd.json    ← JSON export (if requested)

📊 Summary:
  Product: {product}
  Status: {DRAFT | APPROVED}
  Feature: {feature}
  Functional requirements: {N}
  Business rules: {N}
  Non-functional requirements: {N}
  Risks: {N}
  Acceptance criteria: {N}

👉 Next:
  /pwdev-prd:refine {slug}     → Update this PRD
  /pwdev-prd:roadmap {slug}    → Roadmap with dependency chain and draft stories (needs Status: APPROVED)
  /pwdev-prd:stories {slug}    → Evolve each feature: user stories, CA and RN
  /pwdev-prd:publish {slug}    → GitHub Project + issues from the roadmap (pwdev-github)
  /pwdev-prd:export {slug}     → JSON, or a single GitHub issue with the PRD
  /pwdev-feat:feat             → Create action plan from this PRD (if pwdev-feat installed)
  /pwdev-code:discover         → Start full workflow from this PRD (if pwdev-code installed)
```

## Prohibitions
- NEVER skip the interview — always ask questions
- NEVER invent requirements the user didn't provide
- NEVER include specific technology choices (PRDs are technology-agnostic)
- NEVER commit without asking

Language: resolve `lang` per `references/language.md` before any human-facing output. Paths `<plugin-root>/...`, `references/`, `scripts/`, `templates/` are relative to the plugin root; tool names, subagent dispatch and the command form to show the user depend on the runtime (`references/runtime.md`).

Attribution

pwdev-solucoespwdev-solucoes
View sourceSee grades on GitHubMore from pwdev-solucoes →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Email Composer

Draft professional emails for various contexts including business, technical, and customer communication. Use when the user needs help writing emails or composing professional messages.

304952 votes

Solution Architect

Designs system architecture, component specifications, and technical integration strategy. Use when: designing solutions, system architecture, technology stack, or integration approaches.

192 votes

Akorchak:Venture Assessment

Generate a comprehensive VC investment assessment report for a company

72 votes

Telegram Compose

Compose rich, readable Telegram messages using HTML formatting via direct Telegram API. Use when: (1) Sending any Telegram message beyond a simple one-line reply, (2) Creating structured messages with sections, lists, or status updates, (3) Need formatting unavailable via Clawdbot's Markdown conversion (underline, spoilers, expandable blockquotes, user mentions by ID), (4) Sending alerts, reports, summaries, or notifications to Telegram, (5) Want professional, scannable message formatting wit...

6511 votes

Just Fucking Cancel

Find and cancel unwanted subscriptions by analyzing bank transactions. Detects recurring charges, calculates annual waste, and helps you cancel with direct URLs and browser automation. Use when: 'cancel subscriptions', 'audit subscriptions', 'find recurring charges', 'what am I paying for', 'save money', 'subscription cleanup', 'stop wasting money'. Supports CSV import (Apple Card, Chase, Amex, Citi, Bank of America, Capital One, Mint, Copilot) OR Plaid API for automatic transaction pull. Out...

6511 votes
View all in business →