writing-product-requirements

writing-product-requirements is a skill for Claude Code from shennawardana23/skillme. It costs 111 tokens per session (1,873 once invoked), scanned A, original, Apache-2.0.

A method for writing product requirements by describing the customer benefit first, often as a future press release and a list of questions and answers. A PRD is a shorter document that states the problem, goals, requirements, and open questions.

In plain words
What is it for?
Use it to draft product requirements, a PRD, or a PR-FAQ for a new product, customer-facing feature, or major initiative.
Why use it?
It helps teams agree on why a product or feature should exist before debating implementation details. It also reveals unclear ideas early.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the skillme plugin — 137 skills, 2 commands shipped together

Good fit Use it to draft product requirements, a PRD, or a PR-FAQ for a new product, customer-facing feature, or major initiative.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shennawardana23/skillme/writing-product-requirements
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 shennawardana23/skillme --skill writing-product-requirements
Clone the repo
git clone --depth 1 https://github.com/shennawardana23/skillme

Made for: Claude Code.

Or install skillme, the plugin that ships this one along with the rest of its 137 skills, 2 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 writing-product-requirements

README.md
[![agentmods](https://agentmods.dev/badge/skills/shennawardana23/skillme/writing-product-requirements/github.svg)](https://agentmods.dev/skills/shennawardana23/skillme/writing-product-requirements)
Your own site
<a href="https://agentmods.dev/skills/shennawardana23/skillme/writing-product-requirements"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/writing-product-requirements/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 writing-product-requirements

Your own site · 80×15
<a href="https://agentmods.dev/skills/shennawardana23/skillme/writing-product-requirements"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/writing-product-requirements.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,873 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 $0.00111 $0.01873
Opus 5 $0.00056 $0.00937
Sonnet 5 $0.00022 $0.00375
Haiku 4.5 $0.00011 $0.00187

Measured 9d ago against content hash 6fd00c4c3be7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

writing-product-requirements 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 9d 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.

skills/writing-product-requirements/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Product Requirements

Write requirements by working backwards from the customer's experience, not forwards from a feature list. The PR-FAQ format forces this: you write the press release and customer quote for a product that doesn't exist yet, before any design or engineering work starts, and the difficulty of writing a truthful, compelling press release is itself the test of whether the idea deserves resources.

Step 1: Decide PR-FAQ vs. lighter PRD

Use a full PR-FAQ when:

  • The initiative is a new product, a new customer-facing surface, or a strategic bet that will consume more than a few weeks of a team's time.
  • Multiple teams or leadership need to align on why before anyone argues about how.
  • The idea is genuinely uncertain — if you can't yet write an honest customer quote, that uncertainty is exactly what the exercise surfaces.

Use a lighter one-page PRD (problem, goal, non-goals, requirements, open questions) when:

  • The work is a well-understood extension of an existing product (a settings toggle, an internal tool, a known bug-driven feature).
  • There is no real ambiguity about customer value — only about implementation.
  • Forcing a press release would be theater, not a forcing function. A PR-FAQ written for a task nobody doubts wastes a day and teaches nothing.

Doing this step wrong is a failure mode on its own: writing a PR-FAQ for a trivial internal feature (nobody reads it, it becomes a rubber stamp) or skipping it for a genuinely risky bet (the team argues about implementation before agreeing on customer value) are both common misapplications.

Step 2: Write the press release first

Write it as if the product shipped today and a journalist is covering it. Standard structure, roughly one page:

  1. Headline — one sentence, names the product and the customer benefit in language a customer would actually use. Not "New Platform Capability Launched" — that tells no one what changed for them.
  2. Sub-headline — one sentence naming the target customer and the primary benefit.
  3. Summary paragraph — what the product is, who it's for, the problem it solves. Datelined as if announced.
  4. Problem paragraph — the customer's problem today, described from their point of view, not the company's. Should be specific enough that a reader recognizes the pain without being told it's a pain.
  5. Solution paragraph — how the product solves it, in plain language, no internal jargon or codenames.
  6. A quote attributed to a company spokesperson — states why the company built this, tying it to strategy.
  7. A quote attributed to a customer — describes their experience using it, in the customer's own voice, specific enough to be falsifiable (what they could do before vs. after). This is the line most drafts get lazy on — see Gotchas.
  8. A call to action — how a customer gets started today.

Read the full file on GitHub · 160 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 160 lines · 111 tokens per session scan A 6fd00c4c3be7

Subscribe to this mod's changes

writing-product-requirements is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 15d ago), licensed Apache-2.0. It adds 111 tokens to every session and 1,873 once invoked, about $0.0006 per session on Opus 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 2026-09-03.

Related

Other skills, from other repositories

autonomous-workflow

The phase-based machinery (0–7) behind the aw dispatcher — task intake through tested PR delivery in an isolated Git worktree, with optional companion skills for planning, quality gates, TDD, UX, code quality, docs, and CI verification. Companions skip silently if not installed. NOT the entry point and not…

mthines/agent-skills · 142 tokens

batch-linear-tickets

Batch-analyze and resolve multiple Linear tickets — bug fixes and feature work. For each ticket: classifies as bug or feature (auto from Linear labels, or via the --type flag), dispatches the appropriate per-ticket analysis (linear-ticket-investigator + rca-investigator for bugs, just linear-ticket-investigator for…

mthines/agent-skills · 146 tokens

aw

Ships autonomous, end-to-end coding work — implement a feature or fix, all the way to a tested draft PR — from a single opt-in entry point. Detects the task tier (Micro / Lite / Full) and routes: Micro/Lite run single-pass in this context; Full hands off to the aw-planner → aw-executor agents. Use when the user asks…

mthines/agent-skills · 193 tokens

openspec-implementation

A workflow for implementing an approved technical specification one task at a time. It reads the proposal, makes the changes, runs tests, and validates the result.

sutchan/Agent-Skills-Hub · 86 tokens

codely-plan-create-github

Create a plan for the specified task and store it as GitHub issues in the repository of the current working directory. Given the URL of a GitHub issue, it turns that issue into the parent "plan" issue (Goal, Context and a checklist of phases) and creates one child issue per phase, linking every phase as a native…

CodelyTV/agent-harness · 116 tokens

codely-plan_phase-implement-github

Implement one phase of a plan stored as GitHub issues in the repository of the current working directory. Given the URL of a phase (child) issue it implements that phase; given the parent plan issue it finds and implements the current phase. Only implements a single phase per invocation, then stops for user review. It…

CodelyTV/agent-harness · 96 tokens