Memstack Product Prd Writer logo

Memstack Product Prd Writer

Community
cwinvestments
memstack-product-prd-writer

Use this skill when the user says 'PRD', 'product requirements', 'requirements document', or needs a complete engineering-ready PRD with problem statement, personas, MoSCoW features, and success metrics. Do NOT use for single feature specs or user story backlogs.

Overview

Publishercwinvestments
Repositorymemstack
Skill namememstack-product-prd-writer
Stars
425
Forks
45
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 cwinvestments on GitHub. Read the source before you install it.

Installation

Install the Memstack Product Prd Writer 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/cwinvestments/memstack/tree/master/skills/product/prd-writer
  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/cwinvestments/memstack.git /tmp/memstack
mkdir -p .claude/skills
cp -r /tmp/memstack/skills/product/prd-writer .claude/skills/memstack-product-prd-writer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Memstack Product Prd Writer 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 Memstack Product Prd Writer 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 Memstack Product Prd Writer 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.

PRD Writer: Writing product requirements document...

Generates a complete engineering-ready PRD with problem statement, user personas, functional and non-functional requirements, MoSCoW prioritization, success metrics, and implementation timeline.

Activation

When this skill activates, output:

PRD Writer: Writing product requirements document...

Then execute the protocol below.

Context Guard

ContextStatus
User says "PRD", "product requirements", "requirements document"ACTIVE
User wants a full product spec for engineering handoffACTIVE
User is planning a new product or major feature setACTIVE
User wants a spec for ONE featureDORMANT: use Feature Spec
User wants user stories for sprint planningDORMANT: use User Story Generator

Common Mistakes

MistakeWhy It's Wrong
"Start with the solution"Start with the problem. Requirements without clear problems lead to building the wrong thing.
"List every possible feature"A PRD with 50 features is a wish list, not a plan. MoSCoW forces hard trade-offs.
"Skip non-functional requirements"Performance, security, and scalability are invisible until they break. Spec them upfront.
"No success metrics"Without measurable outcomes, you can't tell if the product succeeded. Define metrics before building.
"Write it alone"PRDs need input from engineering, design, and stakeholders. Write the draft, then review together.

Protocol

Step 1: Gather Product Context

If the user hasn't provided details, ask:

  1. Product name: what are you building?
  2. Problem statement: what problem does this solve? For whom?
  3. Target users: who are the primary and secondary users?
  4. Business context: why now? What's the opportunity?
  5. Scope: is this a new product, a major feature set, or a v2?
  6. Constraints: timeline, budget, team size, tech stack?

Step 2: Write Problem Statement

Problem statement template:

markdown
## Problem Statement

### The Problem
[Target users] struggle with [specific problem].

Currently, they [workaround or current behavior], which results in
[negative consequences: wasted time, lost revenue, frustration, errors].

### Evidence
- [Data point 1: user research, support tickets, survey results]
- [Data point 2: market data, competitor traction, industry trends]
- [Data point 3: internal metrics showing the gap]

### Impact
If unsolved, this problem costs [users/business] approximately
[quantified impact: time, money, churn rate, opportunity cost].

### Opportunity
By solving this problem, we can [positive outcome for users]
and [positive outcome for the business: revenue, retention, growth].

Problem statement rules:

  • Be specific, "Users struggle with X" not "The experience could be better"
  • Include evidence: data, quotes, or research that proves the problem exists
  • Quantify the impact: makes prioritization decisions easier
  • Separate the problem from the solution (no feature names here)

Step 3: Define User Personas

Create 2-3 personas (no more):

Persona template:

markdown
### Persona: [Name]: [Role/Title]

**Demographics:** [Age range, job title, company size, tech savviness]

**Goals:**
1. [Primary goal, what they're trying to achieve]
2. [Secondary goal]

**Pain points:**
1. [Frustration 1, related to the problem statement]
2. [Frustration 2]
3. [Frustration 3]

**Current behavior:**
- Currently uses [tool/process] to [accomplish task]
- Spends [X hours/week] on [manual process]
- Workaround: [How they hack around the limitation]

**Success criteria:**
- This persona succeeds when they can [measurable outcome]

**Quote:** "[A sentence that captures their frustration in their own words]"

Persona rules:

  • Primary persona: The person the product is primarily designed for (gets priority in trade-offs)
  • Secondary persona: Benefits from the product but doesn't drive design decisions
  • Anti-persona: Who this product is NOT for (prevents scope creep)

Step 4: List Requirements (MoSCoW)

Functional requirements:

IDRequirementPriorityPersonaNotes
FR-001[User can do X]Must[Persona][Context]
FR-002[System does Y when Z]Must[Persona][Context]
FR-003[User can configure W]Should[Persona][Context]
FR-004[System supports V]Could[Persona][Context]
FR-005[User can do U]Won't (this version)[Persona][Context]

MoSCoW definitions:

PriorityMeaningRule of Thumb
MustProduct doesn't work without it60% of effort
ShouldImportant but not blocking launch20% of effort
CouldNice to have, include if time allows15% of effort
Won'tExplicitly out of scope for this version5% (spec only, don't build)

Non-functional requirements:

IDCategoryRequirementTarget
NFR-001PerformancePage load time<2 seconds (p95)
NFR-002PerformanceAPI response time<500ms (p95)
NFR-003ScalabilityConcurrent users[X] users
NFR-004AvailabilityUptime SLA99.9%
NFR-005SecurityAuthentication[Method: OAuth, JWT, etc.]
NFR-006SecurityData encryptionAt rest + in transit
NFR-007AccessibilityWCAG complianceLevel AA
NFR-008CompatibilityBrowser support[List of browsers]
NFR-009DataBackup frequency[Daily/hourly]
NFR-010ComplianceRegulations[GDPR, SOC 2, HIPAA, etc.]

Requirement writing rules:

  • Each requirement should be testable (you can verify it's done)
  • Use "User can [action]" or "System [behavior] when [condition]"
  • Never combine two requirements in one row
  • Include "Won't" items explicitly, prevents scope creep conversations later

Step 5: Define User Flows

For each Must requirement, document the primary user flow:

User flow template:

markdown
### Flow: [Action Name]

**Trigger:** [What initiates this flow]
**Actor:** [Which persona]
**Preconditions:** [What must be true before this flow starts]

**Happy path:**
1. User [action]
2. System [response]
3. User [action]
4. System [response]
5. User sees [outcome/confirmation]

**Error states:**
- If [condition], show [error message] and [recovery action]
- If [condition], redirect to [fallback]

**Edge cases:**
- [Edge case 1: what happens when...]
- [Edge case 2: what happens when...]

Step 6: Define Success Metrics

MetricCurrentTargetTimeframeHow to Measure
[Primary metric, e.g., conversion rate][X]%[Y]%[90 days][Analytics tool]
[Secondary metric, e.g., time-on-task][X min][Y min][90 days][Analytics tool]
[Business metric, e.g., revenue impact]$[X]$[Y][6 months][Revenue dashboard]
[User satisfaction, e.g., NPS][X][Y][90 days][Survey tool]

Metric rules:

  • 1 primary metric (the North Star for this product/feature)
  • 2-3 secondary metrics (supporting indicators)
  • 1 guardrail metric (something that must NOT get worse, e.g., page load time)
  • All metrics must have current baselines and targets with timeframes

Step 7: Outline Timeline & Dependencies

Phase breakdown:

PhaseScopeDurationDependencies
Phase 1: FoundationMust-have features only[X weeks][None / design complete / API ready]
Phase 2: EnhancementShould-have features[X weeks]Phase 1 complete
Phase 3: PolishCould-have features + optimization[X weeks]Phase 2 complete

Key dependencies:

  • [Dependency 1: Design mockups for [flow]: needed by [date]]
  • [Dependency 2: API endpoint from [team]: needed by [date]]
  • [Dependency 3: Third-party integration approval: needed by [date]]

Risks:

RiskProbabilityImpactMitigation
[Risk 1]High/Med/LowHigh/Med/Low[Mitigation strategy]
[Risk 2]High/Med/LowHigh/Med/Low[Mitigation strategy]

Output Format

markdown
# PRD: [Product Name]

**Author:** [Name]
**Date:** [Date]
**Version:** [1.0]
**Status:** [Draft / In Review / Approved]

## 1. Problem Statement
[From Step 2]

## 2. User Personas
[From Step 3]

## 3. Requirements
### 3.1 Functional Requirements
[MoSCoW table from Step 4]
### 3.2 Non-Functional Requirements
[NFR table from Step 4]

## 4. User Flows
[From Step 5]

## 5. Success Metrics
[From Step 6]

## 6. Timeline & Dependencies
[From Step 7]

## 7. Open Questions
[Anything unresolved that needs stakeholder input]

## 8. Appendix
[Wireframes, research data, competitive context]

Completion

PRD Writer: Complete!

Product: [Name]
Problem: [One-line summary]
Personas: [Count]
Must-have requirements: [Count]
Total requirements: [Count]
Phases: [Count]
Estimated timeline: [X weeks]

Next steps:
1. Review with engineering for feasibility and estimates
2. Review with design for user flow validation
3. Get stakeholder sign-off on MoSCoW priorities
4. Break Phase 1 "Must" requirements into user stories (use User Story Generator)
5. Schedule kickoff meeting

Level History

  • Lv.1: Base: Problem statement template with evidence/impact/opportunity, persona template (goals, pains, behaviors, quote), MoSCoW functional requirements table, non-functional requirements (10 categories), user flow template with error states and edge cases, success metrics with baselines/targets/timeframes, phased timeline with dependencies and risk matrix. (Origin: MemStack Pro v3.2, Mar 2026)

Frequently asked questions

What does the Memstack Product Prd Writer AI skill do?

Use this skill when the user says 'PRD', 'product requirements', 'requirements document', or needs a complete engineering-ready PRD with problem statement, personas, MoSCoW features, and success metrics. Do NOT use for single feature specs or user story backlogs.

Why use Memstack Product Prd Writer on TypingMind?

Because you install it once and use it with any model. Memstack Product Prd Writer 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 Memstack Product Prd Writer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cwinvestments/memstack/tree/master/skills/product/prd-writer. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Memstack Product Prd Writer?

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 Memstack Product Prd Writer?

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

Is the Memstack Product Prd Writer AI skill free?

Yes. It is published on GitHub by cwinvestments 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 👇