Pm requirements
Skill julianoczkowski/product-manager/skills/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.From its SKILL.md
npx -y skills add julianoczkowski/product-manager --skill pm-requirementsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
5.0 KB, ~1.1k tokens by cl100k_base, as published. Nobody here has run it
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:
| Impact | Definition |
|---|---|
| 99999 | Contractual obligation |
| 5 | Minimum purchase criteria (evaluator) |
| 4 | Potentials lose time or money due to the problem |
| 3 | Difficult for customers to achieve a primary goal |
| 2 | Customers have difficulty with a non-primary goal |
| 1 | Not 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)
- The target release goal and what market forces / content is driving it.
- The personas involved (link or summarize).
- The list of problems (persona's first person) + the evidence count for each.
- Impact rating per problem (use the scale) and any contractual must-haves (99999).
- Which problems naturally group together.
Artifact template — Market Requirements Document (MRD)
# <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.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most docs writing skills give in ~1.1k tokens
Counted across 1,951 of the 3,904 authors here whose files we hold, read 2026-09-06
- Use third-person for skill descriptionsin 54 of 1951, across 35 files
- Start descriptions with Use whenin 43 of 1951, across 29 files
- Run baseline scenarios before writing any skillin 40 of 1951, across 26 files
- Use active voicein 40 of 1951, across 36 files
- Map file responsibilities before defining tasksin 36 of 1951, across 29 files
- Use checkbox syntax for tracking stepsin 35 of 1951, across 27 files
- Ask one question at a timein 35 of 1951
- Offer execution options after saving the planin 33 of 1951, across 24 files
- Include complete code in every stepin 33 of 1951, across 27 files
- Design units with clear boundaries and interfacesin 31 of 1951, across 23 files
- Announce the skill usage at the startin 30 of 1951
- Verify agent compliance after adding the skillin 29 of 1951, across 17 files
Said here and by no other author read
- Articulate requirements as persona problems
- Describe problems without specifying solutions
- Calculate priority as market evidence times impact
- Group requirements that solve problems together
- Deliver complete groups rather than partial features
- Interview user for release goals and personas
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.