Prd V04 User Journey Mapping logo

Prd V04 User Journey Mapping

Community
mattgierhart
prd-v04-user-journey-mapping

Map user missions from trigger to value moment, organizing features into coherent paths during PRD v0.4 User Journeys. Triggers on requests to map user journeys, define user flows, describe how users accomplish goals, or when user asks "map user journeys", "define user flows", "user missions", "how do users accomplish X?", "journey mapping", "what steps do users take?", "pain to value flow". Consumes PER- (Persona Definition), FEA- (Feature Value Planning), KPI- (Outcome Definition). Outputs UJ- entries with step flows, pain points, and value moments. Feeds v0.4 Screen Flow Definition.

Overview

Publishermattgierhart
RepositoryPRD-driven-context-engineering
Skill nameprd-v04-user-journey-mapping
Stars
179
Forks
11
Bundled files
3
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.

  • 3 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 User Journey Mapping 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-user-journey-mapping .claude/skills/prd-v04-user-journey-mapping
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Prd V04 User Journey Mapping 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 User Journey Mapping 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 User Journey Mapping 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.

User Journey Mapping

Position in workflow: v0.4 Persona Definition → v0.4 User Journey Mapping → v0.4 Screen Flow Definition

User journeys transform features into paths. A journey answers: "How does [persona] go from [trigger] to [value moment] using [features]?"

Consumes

This skill requires prior work from v0.3-v0.4:

  • PER-* persona entries (from v0.4 Persona Definition) — Behavioral profiles that journeys are built around; each journey belongs to a specific persona
  • FEA-* feature entries (from v0.3 Features Value Planning) — Feature list that becomes journey steps; validates that journeys use only MVP-scoped features
  • KPI-* outcome definitions (from v0.3 Outcome Definition) — Success metrics that journeys drive; Core journeys must tie to Tier 1/2 KPIs
  • MVP-SCOPE artifact (from v0.3 Features Value Planning) — Explicit feature boundary; journeys must use only features in MVP-SCOPE, no backlog features
  • BR-* business rules (from v0.3 Commercial Model) — Constraints that affect journey design (pricing tiers affect onboarding paths, moat rules affect targeting journeys, etc.)

This skill assumes v0.4 Persona Definition is complete.

Produces

This skill creates/updates:

  • UJ-* entries (user journeys, confidence 2-3/5) — Paths from trigger through steps to value moment, tied to PER-/FEA-/KPI- with pain point identification
  • Journey sequencing artifact — Dependency map showing which journeys gate which (Onboarding gates Core; Core gates Power User)

All UJ- entries should include:

  • confidence: 2-3/5 (based on design validation and feature implementation certainty)
  • Evidence source citations (PER-ID, FEA-ID, KPI-ID references)
  • Forward target: "Would move to 4/5 if validated in beta with actual persona users"

Example UJ- entry with confidence:

markdown
UJ-001: First Report Generation
Persona: PER-001 (Overwhelmed Ops Manager)
Type: Core
Trigger: User completes onboarding and sees empty dashboard
Goal: Generate first automated report to see time-saving value
Confidence: 2/5 (source: design-validation + feature-status-in-development; KPI-002 links to conversion)

Steps:
  1. Click "Create Report" → FEA-003 (one-click reports) [In MVP-SCOPE]
  2. Select data source → FEA-001 (auto-sync) [In MVP-SCOPE]
  3. Choose report template → FEA-008 (templates) [In MVP-SCOPE]
  4. Preview report → FEA-003 [In MVP-SCOPE]
  5. Export/share report → FEA-009 (export) [In MVP-SCOPE]

Pain Points:
  - Step 2: User may not have connected data source yet (dependency on UJ-002)
  - Step 3: Template overload if too many choices (design concern; recommend 3-5 templates max)

Moment of Value: Seeing the completed report with their actual data
KPI Link: KPI-002 (activation rate — user completes first valuable action)
Success Metric: Time from "Create Report" click to export ≤ 5 minutes
Dependencies: BR-015 (data format rules), UJ-002 (data source connection must precede)

Next Target: "Would move to 4/5 if 5+ beta users complete this journey in ≤5 minutes and report value"

Journey Types

TypePurposePriority SignalExample
CorePrimary value deliveryMust complete for activationFirst report generated
OnboardingFirst-time user setupBlocks all other journeysAccount creation → first action
RecoveryError handling, supportRetention protectionPassword reset, billing issue
Power UserAdvanced workflowsExpansion/upsellBulk operations, integrations

Rule: Define Onboarding first (it gates everything), then Core journeys (they deliver KPI-), then others.

Journey Anatomy

Every journey has:

  1. Trigger — What causes the user to start? (Event, not "opens app")
  2. Steps — Actions linked to FEA- features
  3. Pain Points — Where friction exists (design around these)
  4. Moment of Value — When user achieves goal (this drives KPI-)

Mapping Process

  1. Pull PER- (personas) from Persona Definition

    • Each journey belongs to a specific persona
  2. Pull FEA- (features) and KPI- (outcomes) from v0.3

    • Features are the building blocks of journey steps
    • KPIs tell you which journeys matter most
  3. Define trigger events

    • What causes the user to start this journey?
    • Be specific: "Receives calendar invite" not "opens app"
  4. Map step flow using features

    • Each step = an action the user takes
    • Link each step to the FEA- that enables it
  5. Identify pain points

    • Where might the user get confused, frustrated, or blocked?
    • These inform UX design decisions
  6. Mark "moments of value"

    • When does the user get the payoff?
    • This should tie to KPI- measurement
  7. Create UJ- entries with full traceability

UJ- Output Template

UJ-XXX: [Journey Title]
Persona: [PER-XXX]
Type: [Core | Onboarding | Recovery | Power User]
Trigger: [Event that initiates journey]
Goal: [What user wants to accomplish]

Steps:
  1. [Action] → FEA-XXX
  2. [Action] → FEA-XXX
  3. [Action] → FEA-XXX
  ...

Pain Points:
  - [Step X]: [Potential friction — e.g., "requires context switch"]
  - [Step Y]: [Potential friction]

Moment of Value: [When user achieves goal — be specific]
KPI Link: [KPI-XXX this journey drives]
Success Metric: [How we measure journey completion]
Dependencies: [BR-XXX constraints, API-XXX if known]

Example UJ- entry:

UJ-001: First Report Generation
Persona: PER-001 (Overwhelmed Ops Manager)
Type: Core
Trigger: User completes onboarding and sees empty dashboard
Goal: Generate first automated report to see time-saving value

Steps:
  1. Click "Create Report" → FEA-003 (one-click reports)
  2. Select data source → FEA-001 (auto-sync)
  3. Choose report template → FEA-008 (templates)
  4. Preview report → FEA-003
  5. Export/share report → FEA-009 (export)

Pain Points:
  - Step 2: User may not have connected data source yet (dependency on UJ-002)
  - Step 3: Template overload if too many choices

Moment of Value: Seeing the completed report with their actual data
KPI Link: KPI-002 (activation rate)
Success Metric: Time from "Create Report" click to export ≤ 5 minutes
Dependencies: BR-015 (data format rules), UJ-002 (data source connection)

Feature-to-Journey Validation

After mapping journeys, validate:

  • No orphaned features: Every FEA- appears in at least one UJ-
  • No journey gaps: Every step has a FEA- that enables it
  • KPI coverage: Core journeys tie to Tier 1/2 KPIs

If a FEA- isn't in any journey, either:

  1. Add it to a journey (you missed a use case), or
  2. Cut it from scope (it's not needed)

Journey Sequencing

Map dependencies between journeys:

UJ-000: Onboarding (gates all)
UJ-001: First Report (Core) ← KPI-002 (activation)
UJ-002: Data Source Connection (Core) ← KPI-003 (depth)
UJ-003: Team Invite (Power User) ← KPI-004 (expansion)

Anti-Patterns to Avoid

Anti-PatternSignalFix
Feature-first journeysSteps = feature list dumped in orderStart with user goal, then map features to it
No trigger"User opens app"Define specific event: "receives notification"
No value momentJourney ends without payoffEach journey needs clear outcome
Orphaned featuresFEA- not in any journeyAdd to journey or cut from scope
Generic personas"User does X"Specify PER-: "PER-001 does X"
Happy path onlyNo pain points identifiedAnticipate where users struggle
Mega-journeys15+ stepsSplit into sub-journeys

Quality Gates

Before proceeding to Screen Flow Definition:

  • Onboarding journey defined first
  • All Core journeys mapped to KPI-
  • Every FEA- appears in at least one journey
  • Every journey has a specific trigger (not "opens app")
  • Pain points identified for friction design
  • Journey dependencies documented

Downstream Connections

UJ- entries feed into:

ConsumerWhat It UsesExample
v0.4 Screen Flow DefinitionSteps become screensUJ-001 Step 3 → SCR-005
v0.6 Technical SpecificationJourneys inform API sequencesUJ-001 → API-001, API-002 flow
v0.7 Test PlanningJourneys become E2E testsTEST-020 validates UJ-001
v0.9 GTMJourney-based onboarding messaging"Complete [UJ-001] in 5 minutes"

Detailed References

  • Journey mapping examples: See references/examples.md
  • UJ- entry template: See assets/uj.md
  • Journey sequencing guide: See references/sequencing.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 User Journey Mapping AI skill do?

Map user missions from trigger to value moment, organizing features into coherent paths during PRD v0.4 User Journeys. Triggers on requests to map user journeys, define user flows, describe how users accomplish goals, or when user asks "map user journeys", "define user flows", "user missions", "how do users accomplish X?", "journey mapping", "what steps do users take?", "pain to value flow". Consumes PER- (Persona Definition), FEA- (Feature Value Planning), KPI- (Outcome Definition). Outputs UJ- entries with step flows, pain points, and value moments. Feeds v0.4 Screen Flow Definition.

Why use Prd V04 User Journey Mapping on TypingMind?

Because you install it once and use it with any model. Prd V04 User Journey Mapping 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 User Journey Mapping 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-user-journey-mapping. 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 User Journey Mapping?

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 User Journey Mapping?

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

Is the Prd V04 User Journey Mapping 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 👇