What is project.write_prd?

A product-requirements document writer that turns a clear idea into a written description of what a product must and must not do. A PRD is a document that defines product requirements before implementation.

Use it to create a project's initial requirements document, record open questions, and link the requirements to the idea and supporting material.

It separates the product goal and scope from technical design and code, and asks for clarification instead of guessing when the idea is unclear.

project.write_prd — Skill for Claude Code by gpsaggese/helpers

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.

Any agent

npx skills add gpsaggese/helpers --skill project.write_prd

Clone the repo

git clone --depth 1 https://github.com/gpsaggese/helpers

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gpsaggese/helpers/project.write_prd/github.svg)](https://agentmods.dev/skills/gpsaggese/helpers/project.write_prd)

Your own site

<a href="https://agentmods.dev/skills/gpsaggese/helpers/project.write_prd"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/project.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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gpsaggese/helpers/project.write_prd"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/project.write_prd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 580 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.

Model	Per session	Once invoked
Fable 5.1	$0.00015	$0.00580
Opus 5.5	$0.00006	$0.00232
Sonnet 5.5	$0.00003	$0.00116
Haiku 4.5	$0.00002	$0.00058

Measured yesterday against content hash 5a281c638ff5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project.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 yesterday.

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:

project.write_prd — 91% identical, 34 lines differ

.claude/skills/project.write_prd/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal

Given an idea, write docs/01-prd.md: what the product must and must not do
Do not design the solution and do not write code

Input

<IDEA>: an idea file (e.g., research/ideas/<name>.md) or a free-text description
<DOCS_DIR>: the project's docs/ dir, optional
- If missing, use docs/ in the current dir

Workflow

Read the Idea

Read <IDEA> and the files it links to (papers, related ideas, existing code)
Read the existing docs in <DOCS_DIR>, if any, to avoid repeating them

Ask If the Idea Is Unclear

If the goal, users, or scope is not perfectly clear, do not write the PRD. Ask the user for clarification and wait for the answers
Do not guess a requirement to fill a section. Put each unresolved item in "Open Questions"

Write the PRD

Create <DOCS_DIR>/01-prd.md
Follow .claude/skills/project.rules.md section "Write a PRD" and the template .claude/templates/project_prd.template.md
Follow .claude/skills/markdown.rules.md and .claude/skills/text.rules.md
Point to the idea file and background instead of copying them

Update the Index

If <DOCS_DIR>/README.md exists, add a row for 01-prd.md, per .claude/skills/project.rules.md section "Write an Index in docs/README.md"

Conventions

Say in the PRD how it was generated, with this line right after the title:
```
- Generated by `.claude/skills/project.write_prd/SKILL.md`
```

Constraints

Do not describe the solution. That is the job of architecture.write_design
Do not commit any change
Do not create a GitHub issue

Verification

Every requirement is an H3 ### `R<N>` (<short description>) and a test can check it
The non-goals are listed
Every open question is numbered
The PRD does not contain design or code
The row for 01-prd.md is in <DOCS_DIR>/README.md, if the file exists
The PRD says that it was generated by .claude/skills/project.write_prd/SKILL.md

Read the full file on GitHub · 68 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.

yesterday First seen · 68 lines · 15 tokens per session scan A 5a281c638ff5

Subscribe to this mod's changes

project.write_prd is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 580 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 2026-11-06.

Project management

project.write_prd next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
project.write_prdgpsaggese/helpers	Skill	158	today	Apache-2.0	A	15	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex