Prd V04 Persona Definition logo

Prd V04 Persona Definition

Community
mattgierhart
prd-v04-persona-definition

Synthesize behavioral personas from prior stage evidence for journey mapping and marketing during PRD v0.4 User Journeys. Triggers on requests to define personas, create user profiles, identify target users, or when user asks "who are our users?", "define personas", "user profiles", "target users", "persona creation", "who uses this product?". Consumes CFD- (v0.1-v0.3), BR- (targeting from v0.3 Moat), FEA- (v0.3 Feature Value Planning). Outputs PER- entries with behavioral profiles and feature relationships. Feeds v0.4 User Journey Mapping.

Overview

Publishermattgierhart
RepositoryPRD-driven-context-engineering
Skill nameprd-v04-persona-definition
Stars
179
Forks
11
Bundled files
2
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.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Prd V04 Persona Definition 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.
  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/mattgierhart/PRD-driven-context-engineering.git /tmp/PRD-driven-context-engineering
mkdir -p .claude/skills
cp -r /tmp/PRD-driven-context-engineering/plugins/prd-ce/skills/prd-v04-persona-definition .claude/skills/prd-v04-persona-definition
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Prd V04 Persona Definition 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 Prd V04 Persona Definition 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 Prd V04 Persona Definition 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.

Persona Definition

Position in workflow: v0.3 Feature Value Planning → v0.4 Persona Definition → v0.4 User Journey Mapping

Personas are not demographic profiles—they are behavioral models synthesized from evidence. Every persona must trace back to CFD- research, BR- targeting rules, and FEA- features they care about.

Consumes

This skill requires prior work from v0.1-v0.3:

  • CFD-* problem statements and pain points (from v0.1 Problem Framing) — Behavioral signals about what users struggle with
  • CFD-* value hypotheses (from v0.1 User Value Articulation) — Evidence about what users want to accomplish
  • CFD-* competitive intelligence and segment gaps (from v0.2 Competitive Landscape) — Market segmentation and underserved signals
  • BR-* targeting rules (from v0.3 Moat Definition) — Constraints on which segments to pursue (switchers vs. new-to-category, etc.)
  • BR-* product type classification (from v0.2 Product Type Classification) — Determines which personas matter (Clone = feature parity users; Undercut = price-sensitive niche)
  • FEA-* entries (from v0.3 Features Value Planning) — Feature list to validate which features each persona cares about
  • MVP-SCOPE artifact (from v0.3 Features Value Planning) — The explicit list of features defining MVP; personas map to MVP feature set only

This skill assumes v0.1-v0.3 work is complete.

Produces

This skill creates/updates:

  • PER-* entries (persona definitions, confidence 2-3/5) — Behavioral profiles tied to CFD/BR/FEA evidence with acquisition channels and pricing sensitivity
  • Persona coverage artifact — Map of which personas are Primary/Secondary and which product type segments they represent

All PER- entries should include:

  • confidence: 2-3/5 (based on evidence tier from CFD interviews and BR targeting decisions)
  • Evidence source citations (CFD-ID references + BR-ID targeting rules)
  • Forward target: "Would move to 4/5 if we validate persona behaviors with 5+ actual customers"

Example PER- entry with confidence:

markdown
PER-001: The Overwhelmed Ops Manager
Source IDs: CFD-003 (pain: manual tracking), CFD-012 (value: automation), BR-041 (targeting: switchers at renewal)
Type: Primary
Confidence: 3/5 (source: 4-customer-interviews-jan-2026 + competitive-landscape confirms segment underserved)
Segment: SMB SaaS companies (10-50 employees)

Demographics:
  Role: Operations Manager / Head of Ops
  Context: Growing startup, wearing multiple hats, no dedicated tools budget
  Technical Level: Intermediate (comfortable with SaaS, not a developer)

Behavioral Profile:
  Goals: Reduce time spent on manual reporting (CFD-012)
  Frustrations: Current tools require too much setup (CFD-003)
  Decision Factors: Ease of use > feature count, must show ROI to CEO (CFD-025)
  Current Workflow: Spreadsheets + manual data entry + weekly report compilation

Product Relationship:
  Primary Value: CFD-012 ("Save 5 hours/week on reporting")
  Key Features: FEA-001 (auto-sync), FEA-003 (one-click reports), FEA-007 (dashboard) — all in MVP-SCOPE
  Pricing Sensitivity: BR-030 (SMB tier ≤$50/mo)
  Acquisition Channel: BR-041 (target at contract renewal of competing tools)

Marketing Hook: "Stop building reports. Start using them."
Next Target: "Would move to 4/5 if 5+ actual SMB ops managers validate this behavior in paid usage"

Core Constraint

Maximum 5 personas. Most products need 1-2.

If you have more than 3, you're likely over-segmenting by demographics instead of behavior. Consolidate ruthlessly.

Persona Types

TypeDefinitionWhen to Create
PrimaryCore user, drives most revenueAlways (at least 1)
SecondaryImportant but not primary buyerIf distinct needs exist
NegativeWho we explicitly excludeIf exclusion is strategic
AspirationalFuture target, not current focusOnly for roadmap planning

Rule: Primary personas must link to primary revenue KPI-. If a persona doesn't influence revenue, question whether it's truly primary.

Evidence Requirements

Every persona field must link to prior stage evidence:

Persona FieldMust Link ToSource Stage
GoalsCFD- value hypothesisv0.1 User Value Articulation
FrustrationsCFD- pain pointsv0.1 Problem Framing
Decision FactorsCFD- competitive researchv0.2 Competitive Landscape
Key FeaturesFEA- entriesv0.3 Feature Value Planning
Pricing SensitivityBR- pricing rulesv0.3 Pricing Model
Acquisition ChannelBR- targeting rulesv0.3 Moat Definition

No link = No claim. If you can't cite evidence, the attribute is assumption, not fact.

Synthesis Process

  1. Pull USER TYPE from v0.1 Problem Framing (CFD-)

    • These are your candidate personas
  2. Pull SEGMENTS from v0.2 Market Definition (CFD-, BR-)

    • How is the market divided? Which segments are we targeting?
  3. Pull TARGETING RULES from v0.3 Moat Definition (BR-)

    • New-to-category vs. Switchers? Trigger moments?
  4. Synthesize behavioral patterns from all CFD- evidence

    • What goals unite this segment?
    • What frustrations are consistent?
  5. Map FEA- features to each persona

    • Which features matter most to each?
    • This informs journey mapping
  6. Create PER- entries with full traceability

PER- Output Template

PER-XXX: [Persona Name]
Source IDs: [CFD-XXX, CFD-YYY, BR-ZZZ that inform this persona]
Type: [Primary | Secondary | Negative | Aspirational]
Segment: [From v0.2 market segment]

Demographics:
  Role: [Job title / function]
  Context: [Company size, industry, team structure]
  Technical Level: [Novice | Intermediate | Expert]

Behavioral Profile:
  Goals: [What they're trying to achieve — link to CFD- value]
  Frustrations: [Current pain points — link to CFD- pain]
  Decision Factors: [What influences their choices — link to CFD- research]
  Current Workflow: [How they solve this today]

Product Relationship:
  Primary Value: [CFD- value hypothesis they care about most]
  Key Features: [FEA-XXX, FEA-YYY most relevant to them]
  Pricing Sensitivity: [From BR- pricing rules]
  Acquisition Channel: [How they'll find us — from BR- targeting]

Marketing Hook: [One-sentence pitch for this persona]

Example PER- entry:

PER-001: The Overwhelmed Ops Manager
Source IDs: CFD-003 (pain: manual tracking), CFD-012 (value: automation), BR-041 (target: switchers at renewal)
Type: Primary
Segment: SMB SaaS companies (10-50 employees)

Demographics:
  Role: Operations Manager / Head of Ops
  Context: Growing startup, wearing multiple hats, no dedicated tools budget
  Technical Level: Intermediate (comfortable with SaaS, not a developer)

Behavioral Profile:
  Goals: Reduce time spent on manual reporting (CFD-012)
  Frustrations: Current tools require too much setup (CFD-003)
  Decision Factors: Ease of use > feature count, must show ROI to CEO (CFD-025)
  Current Workflow: Spreadsheets + manual data entry + weekly report compilation

Product Relationship:
  Primary Value: CFD-012 ("Save 5 hours/week on reporting")
  Key Features: FEA-001 (auto-sync), FEA-003 (one-click reports), FEA-007 (dashboard)
  Pricing Sensitivity: BR-030 (SMB tier ≤$50/mo)
  Acquisition Channel: BR-041 (target at contract renewal of competing tools)

Marketing Hook: "Stop building reports. Start using them."

Anti-Patterns to Avoid

Anti-PatternSignalFix
Persona explosion>5 personasConsolidate by behavior, not demographics
Fictional personasNo CFD- linksEvery attribute needs evidence
Demographic-only"25-35 year old male"Focus on behaviors and goals
All personas are primary"Everyone is important"Rank by revenue potential
Copy-paste from competitorsGeneric descriptionsGround in YOUR research
Features without personasPersonas created but no FEA- linksMap features to who cares

Quality Gates

Before proceeding to User Journey Mapping:

  • Maximum 5 personas (ideally 1-3)
  • At least one Primary persona defined
  • Every persona has CFD- evidence links
  • Key Features mapped from FEA- entries
  • Acquisition Channel specified from BR- targeting
  • Marketing Hook is specific and testable

Downstream Connections

PER- entries feed into:

ConsumerWhat It UsesExample
v0.4 User Journey MappingEach UJ- references a PER-UJ-001 is for PER-001
v0.4 Screen Flow DefinitionPersona context shapes UISCR-001 optimized for PER-001 tech level
v0.9 GTMMarketing messaging per personaCampaign targeting PER-002 segment
Sales EnablementPersona-specific pitchesDiscovery questions per PER-

Detailed References

  • Persona creation examples: See references/examples.md
  • PER- entry template: See assets/per.md

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Prd V04 Persona Definition AI skill do?

Synthesize behavioral personas from prior stage evidence for journey mapping and marketing during PRD v0.4 User Journeys. Triggers on requests to define personas, create user profiles, identify target users, or when user asks "who are our users?", "define personas", "user profiles", "target users", "persona creation", "who uses this product?". Consumes CFD- (v0.1-v0.3), BR- (targeting from v0.3 Moat), FEA- (v0.3 Feature Value Planning). Outputs PER- entries with behavioral profiles and feature relationships. Feeds v0.4 User Journey Mapping.

Why use Prd V04 Persona Definition on TypingMind?

Because you install it once and use it with any model. Prd V04 Persona Definition 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 Prd V04 Persona Definition in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/plugins/prd-ce/skills/prd-v04-persona-definition. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Prd V04 Persona Definition?

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 Prd V04 Persona Definition?

As many as you like. As long as a model supports skills, you can use Prd V04 Persona Definition with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Prd V04 Persona Definition AI skill free?

Yes. It is published on GitHub by mattgierhart 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 👇