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

Write Prd

ASecurity

Write a Product Requirements Document (PRD). Use when the user says "write a PRD", "document this feature", "product requirements for X", "write requirements", "I need a PRD", "pitch this feature", or wants to formalize a feature or product idea into a structured doc - even if they don't explicitly say "PRD".

20 stars
0 votes
0 copies
0 views
Added 10/4/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 10/4/2026

$npx -y skills add qa-aman/claude-skills --skill write-prd --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Write Prd?

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

Security grade badge for Write Prd
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/qa-aman-write-prd/badge)](https://www.skillsdirectory.com/skills/qa-aman-write-prd)

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: write-prd
description: >
  Write a Product Requirements Document (PRD). Use when the user says "write a PRD",
  "document this feature", "product requirements for X", "write requirements",
  "I need a PRD", "pitch this feature", or wants to formalize a feature or product
  idea into a structured doc - even if they don't explicitly say "PRD".
---

## Overview

Based on **Shape Up** by Ryan Singer (Basecamp). A PRD defines the problem, the appetite, and the solution boundaries - not a detailed spec. The key insight from Shape Up: fix the time, flex the scope. Define how much the team is willing to spend before deciding what to build.

## Workflow

### Step 1: Set the Appetite
Before writing requirements, define the appetite - how much time is this worth?
- **Small batch:** 1-2 weeks
- **Big batch:** 4-6 weeks

If the solution requires more time than the appetite allows, cut the scope - don't extend the time.

### Step 2: Write the Problem Statement
One paragraph. Answer: what is broken or missing today, who is affected, and what is the cost of not solving it. Avoid mentioning solutions here.

### Step 3: Write the Pitch (Shape Up format)
Structure:
```
# PRD: [Feature Name]
**Appetite:** [Small batch / Big batch]
**Status:** Draft
**Author:** [your name]

## Problem
[What's broken, who's affected, cost of inaction]

## Solution
[Fat marker sketch - broad strokes, not pixel-perfect]

## Rabbit Holes
[Specific technical or design traps to avoid]

## No-Gos
[Explicitly what this does NOT include]
```

### Step 4: Write the Solution at the right altitude
Shape Up's "fat marker sketch" principle: describe the solution broadly enough that engineers have room to make decisions. Over-specifying kills ownership and slows delivery.

Write requirements at the level of: "Users can do X" - not "There is a button in the top-right corner."

### Step 5: Define Rabbit Holes
List specific traps the team could fall into. Examples:
- "Don't rebuild the notification system - use existing infrastructure"
- "Don't support bulk operations in v1"

### Step 6: Define No-Gos
Explicit list of what this does NOT cover. This is the most important section for scope control.

### Step 7: Add Open Questions
Format:
```
Q: [question]
Owner: [name]
Due: [date]
```

## Anti-Patterns

**1. Specifying solutions in the problem statement**
Bad: "We need to add a modal because users don't see the CTA."
Good: "30% of users drop off at checkout. The CTA is not visible enough."

**2. No appetite defined**
Bad: PRD with requirements but no time boundary.
Good: "This is a small batch - 2 weeks max. If the solution needs more, cut scope."

**3. Missing No-Gos**
Bad: PRD with only what's included.
Good: Explicit No-Gos that prevent scope creep during build.

**4. Over-specified requirements**
Bad: "The button is blue, 48px, positioned top-right with 16px margin."
Good: "Users can trigger X from the main action area." (Let design decide the details.)

## Quality Checklist

- [ ] Appetite is defined (small or big batch)
- [ ] Problem statement explains "why", not "what"
- [ ] Solution is at the right altitude - no pixel-level specs
- [ ] Rabbit holes are listed
- [ ] No-Gos are explicit
- [ ] Open questions have owners and due dates

Attribution

qa-amanqa-aman
View sourceSee grades on GitHubMore from qa-aman →
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

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →