Pm Requirements logo

Pm Requirements

Community
julianoczkowski
pm-requirements

Write market-driven, prioritized product requirements (a Market Requirements Document / MRD) the Pragmatic Institute way. Use when the PM asks for "requirements", "an MRD", "what should we build", "prioritize features", "market requirements", or wants development to stop saying "requirements aren't specific enough". Articulates each requirement as a persona's problem, prioritizes with Market Evidence × Impact, and groups them for delivery. Produces a Market Requirements Document as a Markdown or Word .docx artifact.

Overview

Publisherjulianoczkowski
Repositoryproduct-manager
Skill namepm-requirements
Stars
51
Forks
7
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by julianoczkowski on GitHub. Read the source before you install it.

Installation

Install the Pm Requirements AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/julianoczkowski/product-manager/tree/main/skills/pm-requirements
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/julianoczkowski/product-manager.git /tmp/product-manager
mkdir -p .claude/skills
cp -r /tmp/product-manager/skills/pm-requirements .claude/skills/pm-requirements
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pm Requirements in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pm Requirements on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pm Requirements is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Market Requirements (Pragmatic Framework: Planning → Requirements)

Rule: market problems drive requirements that work. A requirement articulates a problem, not a solution — the what (owned by the PM), never the how (owned by the team). Write every requirement as:

[persona] has [problem, described in a use scenario] with [frequency].

If personas or use scenarios aren't ready, run pm-personas and pm-use-scenarios first. See ../pm-copilot/references/framework.md.

Prioritize objectively (never High/Med/Low or voting)

Priority = Market Evidence × Impact.

  • Market Evidence — a tally of documented occurrences across inputs (discovery interviews, surveys, sales calls, support tickets, win/loss, analyst reports, reviews, usage data). "How many times have we seen it? What % experience it?"
  • Impact — an objective 1–5 scale (adapt to your strategy) plus a 99999 contractual override:
ImpactDefinition
99999Contractual obligation
5Minimum purchase criteria (evaluator)
4Potentials lose time or money due to the problem
3Difficult for customers to achieve a primary goal
2Customers have difficulty with a non-primary goal
1Not in the target market segment

Advanced — the Four Forces (BUVC):

Priority = Evidence × Impact × (B + U + C + V) Buying (what the buyer needs to make the sale), Using (what the user needs to solve their problem), Vision (long-term strategic goals), Competitive (stay competitive). Apply as per-criterion multipliers (example weights B=2, U=1, C=1, V=1).

Group & Group Order: a Group is two or more requirements that make sense to solve together; Group Order + Priority set the sequence handed to development. "Deliver 100% of something, not 70% of everything."

Interview the user (batch questions)

  1. The target release goal and what market forces / content is driving it.
  2. The personas involved (link or summarize).
  3. The list of problems (persona's first person) + the evidence count for each.
  4. Impact rating per problem (use the scale) and any contractual must-haves (99999).
  5. Which problems naturally group together.

Artifact template — Market Requirements Document (MRD)

markdown
# <Product Name> — Market Requirements Document

*This document is confidential and subject to change. For internal use only. No external
commitments can be made based on this document since it is in early planning stages.
Content and timing are very likely to change.*

**Company:** <company>  ·  **Feature / Product:** <product name>
**Author:** <author>  ·  **Contact:** <email>  ·  **Date created:** <date>  ·  **Date last updated:** <date>

## Overview of Target Release
<What is the goal for this release? What market forces are driving this project? What
other artifacts have been created? Are we driven primarily by content or by a target date?>

## Requirements

### GROUP #1 — <Group Name>
<Short description of the group.>

**Requirement #1 — <problem>**
<Persona> has <problem, described in a use scenario> with <frequency>.
**Priority:** 25 (inputs) × 4 (impact) = 100

**Requirement #2 — <problem>**
<Persona> has <problem> with <frequency>.
**Priority:** <evidence> × <impact> = <priority>

### GROUP #2 — <Group Name>
…

## Persona Details
<Full personas, one per page or linked.>

## Requirements Summary
| Name | Market Evidence | Impact | Priority (Evidence × Impact) | Group Name | Group Order |
| :--- | ---: | ---: | ---: | :--- | ---: |
| <req> | 25 | 4 | 100 | <group> | 1 |
<!-- Sort by Group Order ascending, then Priority descending. -->

## Approvals
| Name | Title | Date | Signature |
| :--- | :--- | :--- | :--- |
| | Systems Architect | | |
| | Interaction Designer | | |
| | Product Manager | | |
| | Development Manager | | |
| | Quality Assurance Lead | | |
| | Project Manager | | |

## Change Tracking
| Version | Date | Changes | Reason |
| :--- | :--- | :--- | :--- |
| 1.0 | <date> | Initial draft | — |

Deliver the artifact

Follow ../pm-copilot/references/artifact-output.md: confirm inputs, ask Markdown or .docx, write the .md, convert to .docx on request via your environment's native document-creation capability. Then offer the next stages: add context with pm-use-scenarios, assemble a full pm-prd, or commit an increment with pm-release-plan.

Frequently asked questions

What does the Pm Requirements AI skill do?

Write market-driven, prioritized product requirements (a Market Requirements Document / MRD) the Pragmatic Institute way. Use when the PM asks for "requirements", "an MRD", "what should we build", "prioritize features", "market requirements", or wants development to stop saying "requirements aren't specific enough". Articulates each requirement as a persona's problem, prioritizes with Market Evidence × Impact, and groups them for delivery. Produces a Market Requirements Document as a Markdown or Word .docx artifact.

Why use Pm Requirements on TypingMind?

Because you install it once and use it with any model. Pm Requirements is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pm Requirements in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/julianoczkowski/product-manager/tree/main/skills/pm-requirements. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Pm Requirements?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pm Requirements?

As many as you like. As long as a model supports skills, you can use Pm Requirements with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pm Requirements AI skill free?

Yes. It is published on GitHub by julianoczkowski under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇