Pm prd
Assemble a full, market-driven Product Requirements Document (PRD) the Pragmatic way — problem-before-solution, evidence-based, persona-first. Use when the PM asks for a PRD, product spec, feature doc, "write the requirements doc", or "put it all together for the team". Pulls in existing personas, positioning, market problems, requirements and use scenarios if present, and gathers anything missing inline. Produces a Product Requirements Document as a Markdown or Word .docx artifact.From its SKILL.md
npx -y skills add julianoczkowski/product-manager --skill pm-prdAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
5.5 KB, ~1.3k tokens by cl100k_base, as published. Nobody here has run it
Product Requirements Document (Pragmatic Framework: Planning)
A PRD here is a market requirements document — it specifies the WHAT (the
market problems, personas, and prioritized requirements). The HOW (design,
flows, UI, prototypes, error conditions) belongs to the team. Lead with the
problem, cite evidence, and write problems in the persona's first-person voice.
See ../pm-copilot/references/framework.md for the primitives used below.
Requirement form: [persona] has [problem, described in a use scenario] with [frequency]. Priority = Market Evidence × Impact (advanced: × (B + U + C + V) — Buying, Using, Vision, Competitive).
Reuse what already exists
Before gathering inputs, find or resume the feature dossier as described in
../pm-copilot/references/artifact-output.md ("Find or resume the feature dossier"
and "Reuse prior artifacts"): look for the feature folder (or
NN-*.md files, or artifacts earlier in this conversation) and reuse their personas,
problems, positioning statement, and prioritized requirements — don't duplicate work,
and carry their open caveats forward. If nothing exists yet, gather inline (or offer
to run pm-personas, pm-market-problems, pm-requirements, pm-use-scenarios
first).
Interview the user (batch questions)
- Product & release — name, version, and the goal of this release.
- Market forces — what's driving this now? Is it content-driven (ship when the problems are solved) or target-date-driven (a fixed market window)?
- Personas — who is the buyer, who is the user? (summarize or link)
- Top market problems — in the persona's first person, each with evidence (interview count, % of customers, win/loss, support tickets, usage data).
- Success metrics — how will you know it worked? (Value / Quality / Progress / Satisfaction)
- Out of scope, dependencies, risks.
Artifact template
# Product Requirements Document — <Product> <Version>
*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:** <feature / product name>
**Author:** <author> · **Contact:** <email> · **Date created:** <date> · **Version:** 1.0
## 1. Overview of the target release
Goal of this release: <one paragraph>.
Market forces driving it: <evidence-backed forces>.
Driven primarily by: <content | target date>. Target window: <date/quarter>.
Related artifacts: <positioning doc, roadmap, canvas, links>.
## 2. Personas
### Buyer persona — <name>
<motivations, buying process, barriers>
### User persona — <name>
<goals, behaviors, problems>
## 3. Market problems (persona's first person, with evidence)
- "<I can't …>" — evidence: <n interviews / % customers / win-loss>
- "<It takes too long to …>" — evidence: <…>
## 4. Requirements (grouped, prioritized)
### GROUP 1 — <group name>
1. **<Requirement>** — <Persona> has <problem, in a use scenario> with <frequency>.
Priority: <evidence> (inputs) × <impact> (impact) = **<priority>**.
2. **<Requirement>** — … Priority: … = **<priority>**.
### GROUP 2 — <group name>
1. …
## 5. Use scenarios (day-in-the-life)
**<Scenario name>** — <Persona> is trying to <goal>. Today, <what happens, the pain,
the current workaround>. This happens <frequency>. <Why it matters.>
## 6. Requirements summary
| Requirement | Persona | Market Evidence | Impact | Priority | Group | Group Order |
| :--- | :--- | ---: | ---: | ---: | :--- | ---: |
| <name> | <persona> | 25 | 4 | 100 | <group> | 1 |
## 7. Out of scope / non-goals
- <explicitly not doing …>
## 8. Success metrics
| Metric category | Metric | Current | Goal |
| :--- | :--- | :--- | :--- |
| Value | <LTV / revenue> | | |
| Quality | <defects / coverage> | | |
| Progress | <cycle time> | | |
| Satisfaction | <NPS / CSAT / renewal> | | |
## 9. Dependencies & risks
- <dependency / risk> — <mitigation>
## 10. Approvals
| Name | Title | Date | Signature |
| :--- | :--- | :--- | :--- |
| | Product Manager | | |
| | Systems Architect | | |
| | Development Manager | | |
| | Interaction Designer | | |
| | QA Lead | | |
## 11. Change tracking
| Version | Date | Changes | Reason |
| :--- | :--- | :--- | :--- |
| 1.0 | <date> | Initial draft | |
## Open questions / evidence to gather
- > TODO: <unproven claim or missing evidence>
Deliver the artifact
Follow ../pm-copilot/references/artifact-output.md: confirm inputs (fill gaps with
clearly-marked assumptions rather than inventing evidence), ask Markdown or .docx,
write the .md, convert to .docx on request via your environment's native document-creation capability.
Then offer the next stage: turn the prioritized requirements into a committed
pm-release-plan, and set up pm-stakeholder-communication to keep everyone aligned.
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 ~1.3k 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
- Find or resume the existing feature dossier
- Lead with the market problem
- Cite evidence for all market problems
- Write problems in the persona's first-person voice
- Fill missing information with clearly-marked assumptions
- Ask the user for Markdown or .docx format
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.