Prd V04 Screen Flow Definition logo

Prd V04 Screen Flow Definition

Community
mattgierhart
prd-v04-screen-flow-definition

Connect user journeys to screens, defining the UI structure and navigation paths during PRD v0.4 User Journeys. Triggers on requests to define screens, design screen flows, map UI structure, plan navigation, or when user asks "what screens do we need?", "define screens", "screen flow", "UI structure", "information architecture", "navigation design", "wireframe planning". Consumes UJ- (User Journey Mapping), FEA- (Feature Value Planning), BR- (constraints). Outputs SCR- entries for screens and DES- entries for design system elements. Feeds v0.5 Red Team Review.

Overview

Publishermattgierhart
RepositoryPRD-driven-context-engineering
Skill nameprd-v04-screen-flow-definition
Stars
179
Forks
11
Bundled files
6
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.

  • 6 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 Screen Flow 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-screen-flow-definition .claude/skills/prd-v04-screen-flow-definition
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Prd V04 Screen Flow 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 Screen Flow 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 Screen Flow 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.

Screen Flow Definition

Position in workflow: v0.4 User Journey Mapping → v0.4 Screen Flow Definition → v0.5 Red Team Review

Screens are where journeys become tangible. This skill transforms user journeys into a screen inventory with navigation paths and feature mappings.

Consumes

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

  • UJ-* user journey entries (from v0.4 User Journey Mapping) — Journey steps become screens; each step asks "What screen enables this action?"
  • FEA-* feature entries (from v0.3 Features Value Planning) — Features map to screens showing which features appear on which screens
  • PER-* persona entries (from v0.4 Persona Definition) — Persona context (technical level, role) shapes screen design choices and complexity
  • MVP-SCOPE artifact (from v0.3 Features Value Planning) — Explicit feature boundary; screens must render only MVP-scoped features, backlog features deferred
  • BR-* business rules (from v0.3 Commercial Model) — Constraints affecting screen layout (pricing tier rules affect which settings appear, role-based visibility, data refresh rates, etc.)

This skill assumes v0.4 User Journey Mapping is complete.

Produces

This skill creates/updates:

  • SCR-* entries (screens, confidence 2-3/5) — Screen inventory with journey/feature/persona mappings showing purpose, actions, navigation, and constraints
  • DES-* entries (design system components, confidence 2-3/5) — Reusable UI elements and patterns identified across screens
  • Feature-to-Screen matrix — Validation artifact showing every FEA- and every UJ- step mapped to SCR-
  • Screen count and complexity assessment — Critical for v0.5 technical stack selection (number of screens informs frontend framework needs)

All SCR- entries should include:

  • confidence: 2-3/5 (based on journey validation and feature implementation status)
  • Evidence source citations (UJ-ID, FEA-ID, PER-ID references)
  • Forward target: "Would move to 4/5 if validated in wireframe review or prototype testing"

Example SCR- entry with confidence:

markdown
SCR-001: Main Dashboard
Type: Page
Purpose: Central hub showing key metrics and quick actions
Journeys: UJ-001 (Step 4), UJ-002 (Step 5), UJ-003 (Step 1)
Features: FEA-007 (dashboard), FEA-003 (reports preview), FEA-012 (notifications) — all in MVP-SCOPE
Confidence: 2/5 (source: journey-mapping + design-validation; not yet wireframed)

Primary Actions: Create Report, View Data Sources, Access Settings
Secondary Actions: Invite Team, View Help

Navigation:
  From: SCR-000 (Login), any screen via nav bar
  To: SCR-002 (Report Builder), SCR-003 (Data Sources), SCR-010 (Settings)

Content:
  - Key metrics summary (3-5 cards) → DES-001 (Data Card)
  - Recent reports list → DES-002 (Report List)
  - Data source health status → DES-003 (Status Badge)
  - Notification bell → FEA-012

Constraints: BR-015 (data refresh rate), BR-020 (role-based visibility)
Design Notes: PER-001 needs "busy dashboard" - show progress at a glance without overwhelming

Next Target: "Would move to 4/5 if wireframe validated with 3+ target personas"

Example DES- entry with confidence:

markdown
DES-001: Data Card
Type: Component
Used In: SCR-001 (Dashboard), SCR-005 (Analytics)
Purpose: Display single metric with trend indicator
Confidence: 2/5 (source: design-pattern-research; component not yet coded)

States:
  - Default: Shows value + trend arrow
  - Loading: Skeleton placeholder
  - Empty: "No data yet" message
  - Error: "Failed to load" with retry

Variants: Small (dashboard, 120px width), Large (detail view, 240px width)
Accessibility: ARIA labels for trend direction, keyboard navigation support

Next Target: "Would move to 4/5 if implemented and tested across both use cases"

Screen Types

TypeDefinitionDesign PriorityExample
PageFull viewport, primary navigation targetHighDashboard, Settings
ModalOverlay, blocks underlying pageMediumConfirmation, Quick Edit
PanelSlide-out, contextual detailMediumDetail View, Filters
ComponentReusable UI elementVariesHeader, Data Table

Rule: Start with Pages, then identify where Modals/Panels reduce navigation friction.

Navigation Patterns

Choose a pattern based on product type:

PatternWhen to UseExample Products
Hub & SpokeDashboard-centric appsAnalytics, CRM
Linear FlowWizard/checkout processesOnboarding, E-commerce
HierarchicalContent-heavy appsDocumentation, CMS
FlatSimple single-purpose appsTimer, Calculator

Most SaaS products use Hub & Spoke with occasional Linear Flows for onboarding/purchase.

Mapping Process

  1. Pull UJ- (journeys) and FEA- (features) from prior steps

    • Journeys define the paths; features define the capabilities
  2. Inventory unique screens needed across all journeys

    • Walk through each journey step and ask: "What screen does this happen on?"
  3. Map features to screens (many:many relationship)

    • One feature may appear on multiple screens
    • One screen may contain multiple features
  4. Define navigation structure

    • How do users get from screen to screen?
    • What's the hierarchy? What's always accessible?
  5. Identify shared components

    • Headers, footers, navigation bars
    • Common patterns: data tables, forms, cards
  6. Create SCR- entries with journey and feature traceability

  7. Create DES- entries for design system elements

SCR- Output Template

SCR-XXX: [Screen Name]
Type: [Page | Modal | Panel | Component]
Purpose: [What user accomplishes on this screen]
Journeys: [UJ-XXX, UJ-YYY that use this screen]
Features: [FEA-XXX, FEA-YYY rendered on this screen]

Primary Actions: [Key user actions available]
Secondary Actions: [Less common but available actions]

Navigation:
  From: [SCR-XXX, SCR-YYY — how users arrive]
  To: [SCR-XXX, SCR-YYY — where users can go next]

Content:
  - [Data/element 1]
  - [Data/element 2]

Constraints: [BR-XXX rules affecting this screen]
Design Notes: [Persona-specific considerations from PER-]

Example SCR- entry:

SCR-001: Main Dashboard
Type: Page
Purpose: Central hub showing key metrics and quick actions
Journeys: UJ-001 (Step 4), UJ-002 (Step 5), UJ-003 (Step 1)
Features: FEA-007 (dashboard), FEA-003 (reports preview), FEA-012 (notifications)

Primary Actions: Create Report, View Data Sources, Access Settings
Secondary Actions: Invite Team, View Help

Navigation:
  From: SCR-000 (Login), any screen via nav bar
  To: SCR-002 (Report Builder), SCR-003 (Data Sources), SCR-010 (Settings)

Content:
  - Key metrics summary (3-5 cards)
  - Recent reports list
  - Data source health status
  - Notification bell

Constraints: BR-015 (data refresh rate), BR-020 (role-based visibility)
Design Notes: PER-001 needs "busy dashboard" - show progress at a glance

DES- Output Template

DES-XXX: [Component/Pattern Name]
Type: [Component | Pattern | Layout]
Used In: [SCR-XXX, SCR-YYY]
Purpose: [What this element does]

States:
  - Default: [Normal state]
  - Loading: [When fetching data]
  - Empty: [No data state]
  - Error: [Error state]
  - Disabled: [When not interactive]

Variants: [If multiple versions exist]
Accessibility: [A11y considerations]

Example DES- entry:

DES-001: Data Card
Type: Component
Used In: SCR-001 (Dashboard), SCR-005 (Analytics)
Purpose: Display single metric with trend indicator

States:
  - Default: Shows value + trend arrow
  - Loading: Skeleton placeholder
  - Empty: "No data yet" message
  - Error: "Failed to load" with retry

Variants: Small (dashboard), Large (detail view)
Accessibility: ARIA labels for trend direction

Screen Categories

Organize screens by function:

CategoryExamplesDesign Priority
Entry PointsLogin, Landing, SignupHigh (first impressions)
Core WorkflowMain task screensHigh (value delivery)
Settings/AdminPreferences, Account, BillingMedium (necessary)
Support/HelpDocs, Contact, FAQLow (failure recovery)

Rule: Invest design effort proportional to priority. Don't over-design settings screens.

Feature-to-Screen Matrix

Create a mapping matrix:

FeatureSCR-001SCR-002SCR-003SCR-004
FEA-001 (auto-sync)
FEA-003 (reports)PreviewFull
FEA-007 (dashboard)
FEA-010 (auth)

This reveals:

  • Features spread across multiple screens (normal)
  • Features on no screens (problem: orphaned)
  • Screens with no features (problem: unnecessary)

Anti-Patterns to Avoid

Anti-PatternSignalFix
Screen explosion>20 unique screens for MVPConsolidate; use modals/panels instead
Feature-per-screen1:1 FEA to SCR mappingGroup related features on screens
No shared componentsEvery screen is uniqueExtract DES- patterns
Navigation dead-endsCan't get back from a screenEnsure bidirectional paths
Journey disconnectSCR- not tied to UJ-Every screen serves a journey
Modal abuseEverything is a modalModals for confirmations/quick edits only

Quality Gates

Before proceeding to v0.5 Red Team Review:

  • All UJ- steps mapped to screens
  • All FEA- features appear on at least one screen
  • Navigation paths are bidirectional (no dead-ends)
  • Shared components identified as DES- entries
  • Screen count reasonable for MVP (<15 pages)
  • Entry points and core workflow prioritized

Downstream Connections

SCR- and DES- entries feed into:

ConsumerWhat It UsesExample
v0.5 Technical Stack SelectionScreen complexity informs frontend needs"20 screens → need component library"
v0.6 Technical SpecificationScreens inform API data needsSCR-001 → API-001 (dashboard data)
v0.7 Build ExecutionScreens become implementation tasksEPIC-03 builds SCR-001–005
DesignSCR- entries become wireframes/mockupsSCR-001 → Figma design

Detailed References

  • Screen flow examples: See references/examples.md
  • SCR- entry template: See assets/scr.md
  • DES- entry template: See assets/des.md
  • Navigation patterns guide: See references/navigation-patterns.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 Screen Flow Definition AI skill do?

Connect user journeys to screens, defining the UI structure and navigation paths during PRD v0.4 User Journeys. Triggers on requests to define screens, design screen flows, map UI structure, plan navigation, or when user asks "what screens do we need?", "define screens", "screen flow", "UI structure", "information architecture", "navigation design", "wireframe planning". Consumes UJ- (User Journey Mapping), FEA- (Feature Value Planning), BR- (constraints). Outputs SCR- entries for screens and DES- entries for design system elements. Feeds v0.5 Red Team Review.

Why use Prd V04 Screen Flow Definition on TypingMind?

Because you install it once and use it with any model. Prd V04 Screen Flow 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 Screen Flow 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-screen-flow-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 Screen Flow 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 Screen Flow Definition?

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

Is the Prd V04 Screen Flow 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 👇