write-prd

write-prd is a command for Claude Code from phuryn/pm-skills. It costs 20 tokens per session (793 once invoked), scanned A, original, MIT.

A command for creating a Product Requirements Document (PRD) from anything from a rough idea to a detailed brief. A PRD describes the problem, users, success measures, limits, and proposed solution.

In plain words
What is it for?
Use it to document feature ideas, investigate user problems, define success metrics, and prepare a specification from notes or uploaded documents.
Why use it?
It helps turn incomplete information into a structured product plan by asking for missing context. This reduces misunderstandings before development begins.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the pm-execution plugin — 16 skills, 11 commands shipped together

Good fit Use it to document feature ideas, investigate user problems, define success metrics, and prepare a specification from notes or uploaded documents.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/phuryn/pm-skills/write-prd
About the project

phuryn/pm-skills is a marketplace of reusable skills, commands, and plugins that guide AI assistants through product-management work such as discovery, strategy, planning, metrics, launches, and growth. It is for product managers and teams using Claude Code, Cowork, or compatible assistants. The catalogue entries are the project's own workflows and extensions.

phuryn/pm-skills · 27,375 stars · on GitHub · productcompass.pm

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/phuryn/pm-skills

Made for: Claude Code.

Or install pm-execution, the plugin that ships this one along with the rest of its 16 skills, 11 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for write-prd

README.md
[![agentmods](https://agentmods.dev/badge/commands/phuryn/pm-skills/write-prd/github.svg)](https://agentmods.dev/commands/phuryn/pm-skills/write-prd)
Your own site
<a href="https://agentmods.dev/commands/phuryn/pm-skills/write-prd"><img src="https://agentmods.dev/badge/commands/phuryn/pm-skills/write-prd/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for write-prd

Your own site · 80×15
<a href="https://agentmods.dev/commands/phuryn/pm-skills/write-prd"><img src="https://agentmods.dev/badge/commands/phuryn/pm-skills/write-prd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 793 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.00793
Opus 5.5 $0.00008 $0.00317
Sonnet 5.5 $0.00004 $0.00159
Haiku 4.5 $0.00002 $0.00079

Measured 16d ago against content hash 52951d61e2d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

write-prd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • write-prd — 100% identical, 73 lines differ
pm-execution/commands/write-prd.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/write-prd -- Product Requirements Document

Create a lean PRD that aligns stakeholders and guides development. Accepts anything from a vague idea to a detailed brief.

Invocation

/write-prd SSO support for enterprise customers
/write-prd Users are dropping off during onboarding — we need to fix step 3
/write-prd [upload a brief, research doc, or strategy deck]

Workflow

Step 1: Understand the Feature

Accept the input in any form:

  • A feature name ("SSO support")
  • A problem statement ("Enterprise customers keep asking for centralized auth")
  • A user request ("Users want to export their data as CSV")
  • A vague idea ("We should do something about onboarding drop-off")
  • An uploaded document (brief, research, Slack thread, email)

Step 2: Fill Only the Gaps That Matter

Extract what the input already gives you, and research what the web can answer (prior art, competitors, market context) instead of asking. If any of these three is missing, ask about it before writing, in one message, three questions at most:

  1. User problem: What problem does this solve? Who experiences it, and how painful is it?
  2. Target users: Which user segment(s)? What's their current workaround?
  3. Success metrics: How will we know this worked? What moves if we nail it?

Constraints, prior art, and scope preference are worth asking about only if the user wants the detailed version. If the user says "just write it", go ahead and mark the gaps as assumptions.

Step 3: Generate the PRD

Apply the create-prd skill: its 8-section template, lean by default (about one to two pages). Write the detailed version only if the user asks for it. Start the document with:

## Product Requirements Document: [Feature Name]

**Author**: [user]
**Date**: [today]
**Status**: Draft

Then the eight sections: Summary, Contacts (if known), Background, Objective, Market Segment(s), Value Proposition(s), Solution, Release. Market Segments and Value Propositions are always included; each value proposition uses the 6-part template (Who, Why, What before, How, What after, Alternatives). Put what the first version will not do in Release, and what's still unknown in Solution → Assumptions and open questions.

Read the full file on GitHub · 72 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 16d ago Changed · -47 lines · +7 tokens per session 52951d61e2d8
  2. 1mo ago First seen · 119 lines · 13 tokens per session scan A 7c7a1646905e

Subscribe to this mod's changes

write-prd is a command published in the GitHub repository phuryn/pm-skills (27,375 stars, last pushed 9d ago), licensed MIT. It adds 20 tokens to every session and 793 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.