stefanoskarakasis/Product-Marketing-Skills

prd

Co-writes a full Product Requirements Document with an embedded Solution Story, anchored in your brain's positioning and ICP.

Voir la source

Mode d’emploi

  1. Copiez la commande et examinez le paquet avant de l’installer dans votre environnement agent.
  2. Consultez le document original pour les outils, identifiants et environnements requis.
  3. Décrivez les entrées et le livrable souhaité ; comparez la sortie aux sources.
npx skills add https://github.com/stefanoskarakasis/Product-Marketing-Skills --skill prd

Avant de commencer

  • L’installation n’inclut ni abonnement au modèle, ni quota API, ni accès aux fichiers.
  • Étoiles et installations reflètent l’activité, pas un test indépendant de qualité ou de sécurité.
Document Skill original

Rendu depuis le dépôt source en conservant titres, exemples, code, tableaux, liens et images.

PRD — Skill

Guides Product Managers and Product Marketing Managers to co-create complete Product Requirements Documents with embedded Solution Stories. Reads your brain for strategic context.


How It Works

`
┌─────────────────────────────────────────────────────────────────┐
│                  PRODUCT REQUIREMENT DOC                        │
├─────────────────────────────────────────────────────────────────┤
│  STEP 0: Load Brain Context (pre-flight)                        │
│  ✓ Positioning (Section 3) → Solution Story framing             │
│  ✓ ICP (Section 2) → Target customer pre-fill                   │
│  ✓ Buyer Personas (recent buyer-personas session, if any) →     │
│    Stakeholder mapping                                          │
├─────────────────────────────────────────────────────────────────┤
│  STEPS 1-6: Intake → Solution Story → Full PRD → Collaboration  │
│  ✓ Conversational intake (role detection)                       │
│  ✓ Solution Story generation (PMM-first)                        │
│  ✓ Full PRD structure (10 sections, 2 owners)                   │
│  ✓ PM + PMM checkpoints (collaboration gates)                   │
│  ✓ Output format (markdown, copy-paste ready)                   │
└─────────────────────────────────────────────────────────────────┘

Trigger

  • When: User mentions PRD, product requirements, solution story, feature spec, GTM brief, launch plan, product brief, user stories, feature rollout, announcement level, or asks for help structuring a product document.
  • Not for: Strategic planning (use go-to-market-strategy), OKR design (use pmm-okrs), competitive analysis (no dedicated skill yet).
  • Example prompts:
  • "Write a PRD for our new dashboard feature"
  • "Help me structure this product initiative"
  • "Create a solution story for our messaging team"
  • "I have some rough notes — turn them into a PRD"
  • "What should we include in the launch section?"

Inputs

  • Args: Feature/initiative name, optional existing notes or brief
  • Context keys:
  • /foundation/brain.md — recommended. Sections 2 (ICP), 3 (Alternatives & Positioning).
  • /context/skill-sessions.md — optional; check for a recent buyer-personas session to pull real committee/persona detail instead of asking from scratch. buyer-personas does not write to the brain, so this is a session-log lookup, not a brain section.
  • /context/meta-patterns.md — optional; recurring patterns the user has logged from prior PRDs

Connectors (Optional)

ConnectorWhat it adds
~~knowledge baseSource docs and prior specs
~~project trackerTicket and roadmap context
~~designDesign files and assets referenced in the spec
~~cloud storageSpecs and decks in Drive
No connectors? Paste the material and I'll work from that. The output has the same shape. Pulled facts are drafts: each is tagged with category, tool and date, and nothing is written until you confirm.

Pre-flight

  • Load /foundation/brain.md if exists. Extract Positioning (§3) and ICP (§2) for context.
  • Check /context/skill-sessions.md for a recent buyer-personas session. If one exists, pull its persona detail for Solution Story stakeholder mapping. If none exists, proceed without it — do not block, and do not claim persona data was loaded when it wasn't.
  • If Positioning is 🔴 (Placeholder): surface "Your positioning is a draft — Solution Story may lack messaging grounding. Update brain first?"
  • If ICP missing: "Complete Section 2 (ICP Definition) of your brain via product-marketing-context first — target customer clarity sharpens PRDs."
  • If /context/meta-patterns.md exists in the user's workspace, check for guardrails they've logged that apply to PRD writing. Skip silently if it doesn't exist.

Quality gates before intake:

  • If user has zero positioning context: surface "Consider setting positioning first — PRD reads more sharply when anchored to a 'why now' narrative."
  • If user is PM-only (no PMM): offer "PMM perspective is valuable here — best to co-author."

Steps

Step 1: Identify Starting Point

Ask conversationally:

"Are you starting from scratch, or do you have existing notes, a brief, or an earlier doc I should work from?"
  • If scratch → run intake interview (Step 2)
  • If existing content → read it, extract what's answered, ask only for gaps
  • If specific section only → jump to that section

Step 2: Intake Interview

Ask conversationally, grouped into two rounds.

Round 1 — Core info (together):

  1. What is the feature or initiative name?
  2. Who is the target customer / user persona? (Pre-filled from brain ICP if available)
  3. What problem does it solve?
  4. What's the one outcome you most want to achieve?

Round 2 — Depth (after Round 1):

  1. What evidence do you have the problem is real? (data, quotes, tickets)
  2. Who's on the team? (PM, PMM, Design, Engineering Lead)
  3. Timeline or key dates?
  4. Is there an experiment planned, or direct rollout?
  5. What's the announcement level? (P1 Major / P2 Notable / P3 Improvement / P4 Minor)

If user seems impatient, use what you have and fill gaps with clearly labelled [TO FILL — hint] placeholders.

Step 3: Generate Output 1: Solution Story

Once Round 1 is complete, generate the Solution Story first. This anchors the full PRD.

Solution Story structure

`
## Solution Story — [Feature Name]

### Feature Identity
- Feature Name: [name]
- Tagline (1–2 words): [tagline]
- Short Value Description: [one sentence — what it does and why it matters]
- Announcement Level: [P1 / P2 / P3 / P4 + one-line rationale]

### The One-Paragraph Pitch
[4–6 sentences. Open with what's broken about the status quo. Explain what this product does differently. Close with customer benefit. Confident, clear, slightly opinionated. No jargon.]

### Press Paragraph
[3–4 sentence press-ready version, or N/A if same as above]

### Customer Proof Points
1. [Insight] — [supporting quote or data] (Source: [X])
2. [Insight] — [supporting quote or data] (Source: [X])
3. [Insight] — [supporting quote or data] (Source: [X], optional)

Writing rules:

  • Start with the broken status quo — don't open with "Introducing…"
  • Name the pain specifically: who feels it, how often, what it costs
  • Solution sentence should feel inevitable given the problem
  • End on customer outcome, not product feature
  • Read aloud — if it sounds like a press release, simplify

Step 4: Generate Output 2: Full PRD

After Solution Story is confirmed, generate the full PRD. Use structure below. Every section either filled with real content or marked [TO FILL — hint].

Full PRD structure


Document Header

  • Feature Name:
  • Author:
  • Date:
  • Version: v1.0
  • Status: Draft

Section 00 — Team

RoleNameResponsibility
Product Manager (PM)Owner
Product Marketing Manager (PMM)Owner
DesignContributor
Engineering LeadContributor
AnalyticsContributor
Stakeholder / Exec SponsorApprover

Section 01 — Solution Story Summary (PMM)

Pull from Output 1. Paste tagline, value description, and pitch so engineers see the 'why' before reading requirements.


Section 02 — Problem & Background (PM + PMM)

2.1 Problem Statement

  • Who: [specific segment]
  • Problem: [concrete, observable struggle]
  • Evidence: [data, quotes, tickets — linked]
  • Secondary Issues: [knock-on problems]

2.2 Market Opportunity (PMM)

  • Market Size / TAM:
  • Trend (why now):
  • Competitor landscape:
  • Our differentiation:

2.3 User Personas (PMM)

  • Primary Persona: [name, role, top 3 frustrations, current workaround, JTBD]
  • Secondary Persona: [if applicable]

Section 03 — Goals & Success Metrics (PM)

TypeMetricBaselineTargetTimeframe
Output (North Star)
Input 1 (Leading)
Input 2 (Leading)
Input 3 (Leading)

Non-Goals:

  • [What's out of scope and why]

Strategic Alignment:

  • Company OKR / Goal:
  • Synergies:
  • Risk if not built:

Section 04 — Requirements & User Stories (PM)

High-Level Solution (2–3 sentences — what we're building and how it works)

Milestones:

  • Phase 1 — MVP: [scope + date]
  • Phase 2 — V2: [scope + date]
  • Phase 3 — Future: [backlog ideas]

User Stories:

PriorityUser StoryBenefit
P0 Must ShipAs a [user], I want [capability]……so that [benefit]
P0 Must ShipAs a [user], I want [capability]……so that [benefit]
P1 Should ShipAs a [user], I want [capability]……so that [benefit]
P1 Should ShipAs a [user], I want [capability]……so that [benefit]

Open Questions:

  • [Question — @owner — due date]

Section 05 — User Experience (PM + Design)

  • Figma / Prototype Link:
  • Design Principles:
  • Key UI Components:
  • User Journey (entry → core flow → success state → edge cases):
  • Accessibility standard (WCAG AA/AAA):

Section 06 — Technical Requirements (Engineering Lead)

  • Tech Stack:
  • System Architecture:
  • Key Integrations / APIs:
  • Security Considerations:
  • Performance Benchmarks:
  • Scalability Notes:

Section 07 — Launch Plan (PMM + PM)

Experiment Design (if applicable):

  • Success Criteria:
  • Eligibility:
  • Test Group:
  • Control Group:
  • Split:
  • Minimum Duration:

Rollout Plan:

PhaseAudienceDurationWatch MetricGo / No-go Owner
1Internal / Alpha (5%)PM
2Beta (25%)PM + PMM
3GA (100%)OngoingPM + PMM

Rollback Criteria:

  • Trigger Metric:
  • Threshold:
  • Decision Owner:
  • Rollback Process:

Go-to-Market (PMM):

  • Messaging Headline:
  • Target Channels:
  • Key Dates:
  • Sales Enablement:
  • Support Documentation:

Section 08 — Milestones & Risks (PM)

Key dates: Discovery → Design sign-off → Engineering kickoff → Alpha → Beta → GA → Post-launch review

RiskLikelihoodImpactMitigation
High/Med/LowHigh/Med/Low

Section 09 — Sign-Off

RoleNameApprovalDate
PM
PMM
Design Lead
Engineering Lead
Exec Sponsor

Step 5: Collaboration Checkpoints

Surface these moments explicitly. Insert 🤝 PM + PMM checkpoint at:

  1. After §01 — before filling §02–§04: "Run a 30-min kick-off sync. PM confirms pitch is technically accurate. PMM flags messaging risks from early constraints."
  2. After §04 user stories — before engineering kickoff: "PMM reviews P0 stories. Can you build launch messaging from these alone? Any gaps vs what's been promised?"
  3. At §07 launch plan — when scope is final: "GTM handoff meeting. PM brings final scope + experiment design. PMM brings draft copy + sales enablement. Align on go/no-go."

Step 6: Output Format

  • Default: clean markdown, structured for copy-paste into Google Docs or Notion
  • If user asks for .docx: refer to docx skill
  • Always produce both outputs (Solution Story first, then Full PRD) unless user asks for one
  • Label every placeholder: [TO FILL — e.g. paste customer quote here]
  • Never leave a section silently blank — either fill it or explain what's needed

If a pattern worth remembering surfaces this session — a recurring gap in problem statements, a metric that consistently gets missed — name it and ask the user where, if anywhere, they'd like it noted for their own use. Separately, this skill always logs the session itself; see Step 7.

Step 7: Learning Close

End every completed session by appending one entry to /context/skill-sessions.md, in the format defined in product-marketing-context/.claude-plugin/skill-sessions-format.md (Type A — execution session):

`yaml
type: execution
skill: prd
session_date: [YYYY-MM-DD]
pattern: [one falsifiable statement about what happened this session, or "none"]
source: [surprised / wrong / missing / N/A]

Write this row directly — do not ask the user for permission. This is an observational log entry, distinct from any pattern the user separately asks to have noted for their own reference. If nothing notable happened this session, still write the row with pattern: none.


Writing Principles

Problem statements — be specific. "New users churn" is weak. "New users who signed up via organic search churn at 42% on Day 2 when their first feed session shows zero content matching their stated interests" is strong.

Pitches — open with the broken status quo, not "Introducing X". The problem should feel so obvious the solution feels inevitable.

User stories — write the benefit as a real outcome, not a restatement of the feature. "So that I can see topics" is weak. "So that my feed feels relevant from the moment I sign up" is strong.

Metrics — one output metric, two to three inputs with causal logic. If you can't explain why moving an input will move the output, it's the wrong input.

Non-goals — not a dump of "things we won't do forever." A specific, time-bounded list of what's out of scope for this release and why.


Verification

  • Guardrails checked if /context/meta-patterns.md exists
  • Brain context loaded and referenced (Step 0) — positioning, ICP, personas inform intake
  • Role and document scope clarified (Step 1)
  • Intake interview conducted conversationally (Step 2)
  • Solution Story generated with writing rules applied (Step 3)
  • Full PRD structured with all sections (Step 4)
  • PM + PMM checkpoints surfaced (Step 5)
  • Output format matches spec (Step 6)
  • Session logged to /context/skill-sessions.md (Step 7)

Outputs

  • Files written: /context/skill-sessions.md — one appended row per

session, per Step 7. The Solution Story and full PRD are delivered in chat only; the user chooses where to save them (Notion, Google Docs, or export via docx).

  • Chat output format: Solution Story first (Step 3), then the full

10-section PRD (Step 4), both in copy-paste-ready markdown per Step 6.

  • External side effects: None beyond the session log above.

Do Not Use For

  • Strategic planning — use go-to-market-strategy
  • OKR design — use pmm-okrs
  • Competitive analysis — no dedicated skill yet
  • Launch messaging — use gaccs-brief after PRD is locked
  • Positioning — use positioning-messaging if core positioning undefined

Operating Rules

  • Brain context loads before intake. Positioning and ICP shape what the Solution Story emphasizes — never ask for context already available in the brain.
  • Solution Story before full PRD. Round 1 intake must complete and the Solution Story must be confirmed before Section 02 onward is generated — the PMM framing anchors the rest of the document.
  • No silent blanks. Every PRD section is either filled with real content or marked [TO FILL — hint]. A blank section with no marker is a defect, not a placeholder.
  • Collaboration checkpoints are not optional. All three 🤝 PM + PMM checkpoint moments (Step 5) must be surfaced, even if the user tries to skip ahead.
  • Problem statements must be specific. Vague framing ("users churn") gets pushed back on per the Writing Principles — a PRD built on a vague problem produces a vague spec.
  • Metrics need causal logic. One output metric, 2–3 inputs the team can explain a causal path for. An input with no stated mechanism is the wrong input.
  • Both outputs by default. Solution Story and full PRD are always produced together unless the user explicitly asks for only one.

Quality Gate

Runs after the full PRD is generated (Step 4), before delivery. Surface failures — do not deliver an incomplete document as if it were final.

CheckStandardPass =
Brain context loadedPositioning and ICP extracted at Step 0 if available; recent buyer-personas session checkedYes
Solution Story confirmed firstStep 3 output confirmed before Step 4 beginsYes
No unmarked blanksEvery section filled or carries [TO FILL — hint]Yes
Checkpoints surfacedAll 3 collaboration checkpoints present (Step 5)Yes
Problem statement specificNames who, what, evidence, and secondary issues — not a generic complaintYes
Metrics causally linkedEach input metric has a stated reason it should move the outputYes
Learning Close ran/context/skill-sessions.md has a new row for this sessionYes

Related Skills

  • pmm-okrs → PRD OKR alignment
  • gaccs-brief → GTM messaging from PRD Solution Story
  • experiment-doc → Risky assumptions in PRD → suggest experiment
  • go-to-market-strategy → Launch tier assignment
  • pre-mortem → Risk analysis on PRD scope

Tâches connexes

du même dépôt

Autres Skills

Tous les Skills
stefanoskarakasis
Communauté

brand-voice

Builds a persona-adaptive Voice & Tone guide (brand attributes, tone shifts by buyer type and channel, forbidden language), then deepens brain Section 4. Trigger with "how should we sound", "voice guide", "our copy feels off", "we sound like everyone else", "adapt tone for", or any request to define, apply, or audit how the brand communicates.

installations
0
GitHub Stars
7
Mis à jour
25 oct.
stefanoskarakasis
Communauté

buyer-personas

Maps the enterprise buying committee (Economic Buyer, Champion, Technical Evaluator, End User, Procurement) before any messaging, then builds Dunford-structured, alternatives-anchored personas ready for positioning-messaging. Trigger with "map our buying committee", "who do we need to win over", "build our buyer personas", "who kills our deals", or any request to identify or profile the people involved in a B2B purchase.

installations
0
GitHub Stars
7
Mis à jour
25 oct.
stefanoskarakasis
Communauté

customer-stories

Runs a B2B customer story from kickoff to customer approval: kickoff questions, internal brief, interview questions, a draft in one fixed structure, the customer review pack and an audit, with every stat and quote checked. Trigger on: "write a customer story", "kick off a case study", "customer interview questions", "prepare the customer review", "audit this customer story". Related: interview-summary, proof-points, writing-assistant.

installations
0
GitHub Stars
7
Mis à jour
25 oct.
stefanoskarakasis
Communauté

experiment-ideas

Generates several concrete, cost-efficient growth ideas, each with a channel, core message and cost-efficiency rationale, grounded in your brain's ICP, alternatives and market context. Trigger with "give me marketing ideas", "brainstorm growth tactics", "what should we try", "cheap ways to promote this", or any request to generate raw campaign or channel ideas before committing to one to test.

installations
0
GitHub Stars
7
Mis à jour
25 oct.