initial commit

This commit is contained in:
2026-03-16 19:54:53 -04:00
commit bfe0e01254
3341 changed files with 483939 additions and 0 deletions

View File

@@ -0,0 +1,170 @@
---
name: 'step-01-load-context'
description: 'Read all prerequisite artifacts and detect project state'
# File References
nextStepFile: './step-02-analyze-scope.md'
---
# Step 1: Load Context & Detect Project State
## STEP GOAL:
Read all prerequisite artifacts (Product Brief, Trigger Map) and detect whether this is a fresh start or resume, establishing the complete project context needed for scenario creation.
## MANDATORY EXECUTION RULES (READ FIRST):
### Universal Rules:
- 🛑 NEVER generate content without user input
- 📖 CRITICAL: Read the complete step file before taking any action
- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
- 📋 YOU ARE A FACILITATOR, not a content generator
- ✅ YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
### Role Reinforcement:
- ✅ You are a UX Scenario Facilitator collaborating with the project owner
- ✅ If you already have been given a name, communication_style and identity, continue to use those while playing this new role
- ✅ We engage in collaborative dialogue, not command-response
- ✅ You bring scenario thinking and user journey expertise, user brings their project knowledge, together we create concrete UX scenario outlines
- ✅ Maintain collaborative equal-partner tone throughout
### Step-Specific Rules:
- 🎯 Focus only on loading context and detecting project state
- 🚫 FORBIDDEN to skip reading any prerequisite artifact
- 💬 Approach: Methodically gather all context before any creative work
- 📋 Present a clear context summary so the user can verify understanding
## EXECUTION PROTOCOLS:
- 📖 Read all prerequisite files completely before summarizing
- 💾 Extract and note key elements from each artifact
- 🔍 Check for existing work to determine fresh start vs resume
- 🚫 FORBIDDEN to proceed without presenting context summary to user
## CONTEXT BOUNDARIES:
- Available context: Project config, Product Brief, Trigger Map artifacts
- Focus: Loading and understanding all prerequisite data
- Limits: No scenario creation, no analysis — only context gathering
- Dependencies: Product Brief (Phase 1) and Trigger Map (Phase 2) must exist
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Read Configuration
Read `{project-root}/_bmad/wds/config.yaml` and extract:
- `project_name`
- `output_folder`
- `user_name`
- `communication_language`
- `document_output_language`
### 2. Read Product Brief
Read `{output_folder}/A-Product-Brief/product-brief.md`
**Extract and note:**
- Site/app type (marketing site, SaaS, booking system, portfolio, etc.)
- Business context and constraints
- Technical platform (WordPress, custom, etc.)
- Number of pages/views mentioned
- Any navigation structure described
### 3. Read Trigger Map
Read `{output_folder}/B-Trigger-Map/trigger-map.md` (the hub document)
**Extract and note:**
- **Business Goals:** Vision statement, all objectives with priority tiers (Primary/Secondary/Tertiary)
- **Personas:** For each persona:
- Name and role
- Priority level (Primary/Secondary/Tertiary)
- Top 3 positive drivers (wants)
- Top 3 negative drivers (fears)
- Role in flywheel
**Also read persona documents** if they exist:
- `{output_folder}/B-Trigger-Map/02-*.md` (Primary persona)
- `{output_folder}/B-Trigger-Map/03-*.md` (Secondary persona)
- `{output_folder}/B-Trigger-Map/04-*.md` (Tertiary persona, if exists)
### 4. Check for Existing Work
**Check for resume situation:**
- Does `{output_folder}/C-UX-Scenarios/` exist?
- Are there any scenario files already?
- Is there in-progress work in the design log (`{output_folder}/_progress/00-design-log.md`)?
**If existing work found:**
```
"I see we have existing scenario work:
- [list what exists]
Should I:
1. Continue where we left off
2. Review and adjust existing scenarios
3. Start fresh"
```
Wait for user response before proceeding.
**If starting fresh:** Continue to next instruction.
### 5. Present Context Summary
Present to user:
```
"Here's what I'm working with:
**Project:** [project_name]
**Site Type:** [type from Product Brief]
**Business Goals:** [count] objectives across [tier count] tiers
**Personas:** [list names with priority levels]
**Primary Persona:** [name] — [top driving force]
Ready to analyze the scope."
```
### 6. Present MENU OPTIONS
Display: "Are you ready to [C] Continue to Scope Analysis?"
#### Menu Handling Logic:
- IF C: Load, read entire file, then execute {nextStepFile}
#### EXECUTION RULES:
- ALWAYS halt and wait for user input after presenting menu
- ONLY proceed to next step when user selects 'C'
- After other menu items execution, return to this menu
- User can chat or ask questions - always respond and then end with display again of the menu options
## CRITICAL STEP COMPLETION NOTE
ONLY WHEN [C continue option] is selected and [context summary presented and acknowledged], will you then load and read fully `{nextStepFile}` to execute and begin scope analysis.
---
## 🚨 SYSTEM SUCCESS/FAILURE METRICS
### ✅ SUCCESS:
- All prerequisite artifacts read completely (Product Brief, Trigger Map, persona documents)
- Key elements extracted and noted from each artifact
- Existing work detected and handled appropriately
- Clear context summary presented to user
- User acknowledges understanding before proceeding
- Menu presented and user input handled correctly
### ❌ SYSTEM FAILURE:
- Skipping any prerequisite artifact
- Not detecting existing work when it exists
- Proceeding without presenting context summary
- Generating scenarios or analysis during this step
- Not waiting for user acknowledgment before proceeding
**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

View File

@@ -0,0 +1,192 @@
---
name: 'step-02-analyze-scope'
description: 'Determine site type, list all pages/views, assess scale, and select approach mode'
# File References
nextStepFile: './step-03-build-strategic-context.md'
---
# Step 2: Analyze Scope & Scale Strategy
## STEP GOAL:
Determine site type, list all pages/views, assess scale, select approach mode, and present the analysis for user approval at this critical checkpoint.
## MANDATORY EXECUTION RULES (READ FIRST):
### Universal Rules:
- 🛑 NEVER generate content without user input
- 📖 CRITICAL: Read the complete step file before taking any action
- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
- 📋 YOU ARE A FACILITATOR, not a content generator
- ✅ YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
### Role Reinforcement:
- ✅ You are a UX Scenario Facilitator collaborating with the project owner
- ✅ If you already have been given a name, communication_style and identity, continue to use those while playing this new role
- ✅ We engage in collaborative dialogue, not command-response
- ✅ You bring scenario thinking and user journey expertise, user brings their project knowledge, together we create concrete UX scenario outlines
- ✅ Maintain collaborative equal-partner tone throughout
### Step-Specific Rules:
- 🎯 Focus only on scope analysis, page inventory, and scale strategy
- 🚫 FORBIDDEN to proceed past the user checkpoint without explicit user approval
- 💬 Approach: Present structured analysis and wait for user confirmation
- 📋 This is a USER CHECKPOINT — do not auto-proceed
## EXECUTION PROTOCOLS:
- 🔍 Classify site type based on Product Brief data
- 📋 Create complete page inventory from all sources
- 📊 Assess scale and recommend approach mode
- 🚫 FORBIDDEN to skip user checkpoint — must wait for explicit approval
## CONTEXT BOUNDARIES:
- Available context: Product Brief data, Trigger Map data loaded in Step 1
- Focus: Site classification, page inventory, scale assessment
- Limits: No scenario creation, no strategic context building — only scope analysis
- Dependencies: Step 1 context must be loaded
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Site Type Detection
Based on Product Brief, classify the site:
**Presentation Site** (marketing, service catalog, company profile, portfolio):
- Scenario format: **Screen Flow** (page-to-page navigation)
- Coverage: Expose all pages
- Storyboarding: Minimal (only for complex interactions like booking forms)
**Dynamic App** (SaaS, booking system, social platform, productivity tool):
- Scenario format: **Storyboard** (document states within views)
- Coverage: Focus on core workflow first
- Screen flow: Only for multi-step processes (onboarding, checkout)
**Mixed** (presentation site with dynamic features):
- Use both formats as needed per scenario
### 2. List All Pages/Views
Create a complete list of every page or view from the Product Brief.
**Format:**
```
## Page Inventory
1. [Page Name] — [Brief purpose]
2. [Page Name] — [Brief purpose]
3. [Page Name] — [Brief purpose]
...
**Total: [N] pages/views**
```
**Rules:**
- Include every page mentioned in Product Brief
- Include pages implied by navigation structure
- Include pages implied by business goals (e.g., if goal mentions "booking" there's a booking page)
- Do NOT include generic shared elements (header, footer, navigation) — these are documented separately
### 3. Scale Assessment
Based on page count, determine strategy:
**Small (< 20 pages):**
- Strategy: **Comprehensive coverage** — document all pages across scenarios
- Mode recommendation: **Dream** or **Suggest**
- Every page must appear in exactly one scenario
**Medium (20-50 pages):**
- Strategy: **Comprehensive coverage** with natural groupings
- Mode recommendation: **Suggest**
- Group pages by navigation patterns, service types, or content categories
**Large (100+ pages):**
- Strategy: **Selective ignorance** — focus on most valuable workflow
- Mode recommendation: **Dialog**
- Deep work on business-critical flow (learning effect reveals patterns for rest)
### 4. Page Documentation Strategy
Determine how to handle similar pages:
**Few pages + high variation** → Document as separate pages
- Each page substantially different in structure, content, or purpose
- Example: 13 vehicle pages with different positioning
**Many pages + low variation** → Document as template with content variations
- Structurally identical pages with only content differences
- Example: 500 product pages with same layout, different product data
### 5. Present Analysis (USER CHECKPOINT)
Present to user and **wait for approval**:
```
## Scope Analysis
**Site Type:** [Presentation / Dynamic / Mixed]
**Total Pages:** [N]
**Scale:** [Small / Medium / Large]
**Recommended Mode:** [Dream / Suggest / Dialog]
**Scenario Format:** [Screen Flow / Storyboard / Mixed]
### Page Inventory
[numbered list from step 2]
### Page Strategy
- [X] pages documented individually (high variation)
- [Y] pages as templates (low variation groups: [list groups])
**Does this look right? Any pages missing or that should be grouped differently?**
```
**WAIT for user response.** Do not proceed until user confirms.
### 6. Present MENU OPTIONS
Display: "Are you ready to [C] Continue to Building Strategic Context?"
#### Menu Handling Logic:
- IF C: Load, read entire file, then execute {nextStepFile}
#### EXECUTION RULES:
- ALWAYS halt and wait for user input after presenting menu
- ONLY proceed to next step when user selects 'C'
- After other menu items execution, return to this menu
- User can chat or ask questions - always respond and then end with display again of the menu options
## CRITICAL STEP COMPLETION NOTE
ONLY WHEN [C continue option] is selected and [user has explicitly approved the scope analysis], will you then load and read fully `{nextStepFile}` to execute and begin building strategic context.
---
## 🚨 SYSTEM SUCCESS/FAILURE METRICS
### ✅ SUCCESS:
- Site type correctly classified from Product Brief data
- Complete page inventory created with all pages accounted for
- Scale assessment matches page count
- Page documentation strategy determined
- Analysis presented clearly at user checkpoint
- User explicitly approves before proceeding
- Menu presented and user input handled correctly
### ❌ SYSTEM FAILURE:
- Proceeding without user approval at checkpoint
- Missing pages from the inventory
- Incorrect site type classification
- Skipping scale assessment or mode recommendation
- Auto-proceeding past the user checkpoint
**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

View File

@@ -0,0 +1,191 @@
---
name: 'step-03-build-strategic-context'
description: 'Build strategic context from Trigger Map to identify which scenarios to create'
# File References
nextStepFile: './step-04-suggest-scenarios.md'
---
# Step 3: Build Strategic Context
## STEP GOAL:
Extract strategic context from the Trigger Map — tracing paths from business goals through personas and driving forces to transactions — assign pages to each scenario chain, prioritize them, and verify complete coverage of all pages.
## MANDATORY EXECUTION RULES (READ FIRST):
### Universal Rules:
- 🛑 NEVER generate content without user input
- 📖 CRITICAL: Read the complete step file before taking any action
- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
- 📋 YOU ARE A FACILITATOR, not a content generator
- ✅ YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
### Role Reinforcement:
- ✅ You are a UX Scenario Facilitator collaborating with the project owner
- ✅ If you already have been given a name, communication_style and identity, continue to use those while playing this new role
- ✅ We engage in collaborative dialogue, not command-response
- ✅ You bring scenario thinking and user journey expertise, user brings their project knowledge, together we create concrete UX scenario outlines
- ✅ Maintain collaborative equal-partner tone throughout
### Step-Specific Rules:
- 🎯 Focus only on building strategic context, assigning pages, and prioritizing
- 🚫 FORBIDDEN to create scenario outlines — only identify and plan scenarios
- 💬 Approach: Systematically trace paths from business goals to user actions
- 📋 Every page from the inventory must be assigned to exactly one scenario chain
## EXECUTION PROTOCOLS:
- 🔗 Trace complete chains from Business Goal → Persona → Force → Transaction → Scenario
- 📋 Answer all 7 Decision Matrix questions for each scenario chain
- 📊 Assign pages ensuring no repetition and full coverage
- 🚫 FORBIDDEN to leave any page unassigned
## CONTEXT BOUNDARIES:
- Available context: Product Brief, Trigger Map, approved page inventory from Step 2
- Focus: Strategic context extraction, page assignment, prioritization
- Limits: No scenario outlining, no file creation — only planning
- Dependencies: Approved scope analysis from Step 2
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Build Strategic Context Chains
**What is a strategic context chain?**
A strategic context chain traces the path from business strategy to user action:
```
Business Goal → Persona → Driving Force → Transaction → Scenario
```
**Example:**
```
BG01: Reduce info calls by 40%
→ Hasse (Primary - stressed tourist)
→ Fear: Being stranded with broken RV
→ Transaction: Confirm mechanic capability + get directions
→ 01: "Hasse's Emergency Search"
```
For **each business goal** from the Trigger Map:
1. Identify which persona(s) most directly drive this goal
2. Identify which driving forces (wants AND fears) connect to this goal
3. Determine the specific transaction/action that fulfills it
4. Name a candidate scenario using the persona's name
**For each scenario chain, answer the Decision Matrix (all 7 required):**
| # | Question | Answer |
|---|----------|--------|
| 1 | Which business goal? | [Specific goal from Trigger Map] |
| 2 | Which persona? | [Name + priority level] |
| 3 | Which driving force? | [Specific want or fear] |
| 4 | What's the transaction? | [Concrete action user takes] |
| 5 | Where does user come from? | [Natural starting point - be specific] |
| 6 | What value does user get? | [Tangible outcome] |
| 7 | What value does business get? | [Measurable result] |
### 2. Assign Pages to Scenario Chains
For each scenario chain, list which pages from the inventory (Step 02) the user visits.
**Rules:**
- Each page appears in exactly ONE scenario chain (no repetition)
- If a page could fit multiple scenarios, assign it to the highest-priority one
- Shared elements (navigation, footer) are excluded from page assignment
### 3. Prioritize
Rank the scenario chains:
**Priority 1 — Critical Path:**
- Top business goal + primary persona + core product value
- These scenarios are created first and in most detail
**Priority 2 — Supporting:**
- Secondary persona scenarios, alternative entry paths
- Important but not the strategic core
**Priority 3 — Edge Cases:**
- Admin tasks, rare user segments, error recovery
- May be deferred to later phases
### 4. Coverage Check
After building all scenario chains, verify:
- [ ] Every page from inventory is assigned to exactly one scenario chain
- [ ] Primary persona has at least one Priority 1 scenario
- [ ] Top business goal is addressed by at least one scenario
- [ ] No page appears in multiple scenarios
**If pages are unassigned:** Create additional scenario chains or expand existing ones to cover them.
### 5. Present Scenario Chain List
Present the complete scenario chain list:
```
## Strategic Context Chains
### Priority 1
**Chain 01:** [Business Goal] → [Persona] → [Force] → [Transaction]
- Scenario: 01-[slug]
- Pages: [list]
### Priority 2
**Chain 02:** [Business Goal] → [Persona] → [Force] → [Transaction]
- Scenario: 02-[slug]
- Pages: [list]
### Coverage: [X/Y] pages assigned
```
### 6. Present MENU OPTIONS
Display: "Are you ready to [C] Continue to Scenario Suggestions?"
#### Menu Handling Logic:
- IF C: Load, read entire file, then execute {nextStepFile}
#### EXECUTION RULES:
- ALWAYS halt and wait for user input after presenting menu
- ONLY proceed to next step when user selects 'C'
- After other menu items execution, return to this menu
- User can chat or ask questions - always respond and then end with display again of the menu options
## CRITICAL STEP COMPLETION NOTE
ONLY WHEN [C continue option] is selected and [scenario chain list with full page coverage presented], will you then load and read fully `{nextStepFile}` to execute and begin scenario suggestions.
---
## 🚨 SYSTEM SUCCESS/FAILURE METRICS
### ✅ SUCCESS:
- All business goals traced through complete strategic context chains
- All 7 Decision Matrix questions answered for each scenario chain
- Every page from inventory assigned to exactly one scenario chain
- Scenario chains prioritized with clear rationale
- Coverage check passes (all pages assigned, no duplicates)
- Complete scenario chain list presented to user
- Menu presented and user input handled correctly
### ❌ SYSTEM FAILURE:
- Leaving pages unassigned
- Assigning pages to multiple scenario chains
- Skipping Decision Matrix questions
- Creating scenario outlines during this step
- Not verifying coverage before proceeding
**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

View File

@@ -0,0 +1,181 @@
---
name: 'step-04-suggest-scenarios'
description: 'Present scenario plan to user for approval before creating outlines'
# File References
nextStepFile: './step-05-outline-scenario.md'
---
# Step 4: Suggest Scenarios (USER CHECKPOINT)
## STEP GOAL:
Present the complete scenario plan to the user for approval before creating any outlines, ensuring alignment on scenario count, page assignments, naming, and priorities.
## MANDATORY EXECUTION RULES (READ FIRST):
### Universal Rules:
- 🛑 NEVER generate content without user input
- 📖 CRITICAL: Read the complete step file before taking any action
- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
- 📋 YOU ARE A FACILITATOR, not a content generator
- ✅ YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
### Role Reinforcement:
- ✅ You are a UX Scenario Facilitator collaborating with the project owner
- ✅ If you already have been given a name, communication_style and identity, continue to use those while playing this new role
- ✅ We engage in collaborative dialogue, not command-response
- ✅ You bring scenario thinking and user journey expertise, user brings their project knowledge, together we create concrete UX scenario outlines
- ✅ Maintain collaborative equal-partner tone throughout
### Step-Specific Rules:
- 🎯 Focus only on presenting the scenario plan and getting user approval
- 🚫 FORBIDDEN to proceed to outlining without explicit user approval
- 💬 Approach: Present clearly, handle feedback gracefully, re-present if needed
- 📋 This is a critical USER CHECKPOINT — do not auto-proceed under any circumstances
## EXECUTION PROTOCOLS:
- 📋 Format scenario plan exactly as specified
- ✅ Include coverage check with all four verifications
- 🔄 Handle user feedback and re-present adjusted plan
- 🚫 FORBIDDEN to skip user approval checkpoint
## CONTEXT BOUNDARIES:
- Available context: Strategic context from Step 3, page inventory, Trigger Map data
- Focus: Presenting and getting approval for the scenario plan
- Limits: No scenario outlining, no file creation — only planning approval
- Dependencies: Complete strategic context chains from Step 3
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Format the Scenario Plan
Present to user in this exact format:
```
## Scenario Plan for [Project Name]
### Site Analysis
- **Type:** [Presentation / Dynamic / Mixed]
- **Total Pages:** [N]
- **Format:** [Screen Flow / Storyboard / Mixed]
- **Scenarios:** [N] total
---
### Suggested Scenarios
**01: [Persona Name]'s [Purpose]** ⭐ Priority 1
- **Pages:** [comma-separated list]
- **Persona:** [Name] — [Primary driving force]
- **User Value:** [What user gets — be specific]
- **Business Value:** [What business gets — be measurable]
- **Format:** [Screen Flow / Storyboard]
**02: [Persona Name]'s [Purpose]** ⭐ Priority 1
- **Pages:** [comma-separated list]
- **Persona:** [Name] — [Primary driving force]
- **User Value:** [specific]
- **Business Value:** [measurable]
- **Format:** [Screen Flow / Storyboard]
[Continue for all scenarios...]
---
### Coverage Check
✅ All pages assigned: [Yes/No — if No, list unassigned pages]
✅ No page repetition: [Yes/No]
✅ Primary persona covered: [Yes/No]
✅ Top business goal addressed: [Yes/No]
```
### 2. Naming Rules
Scenario names MUST use persona names:
**Good:**
- "Hasse's Emergency Search"
- "Lars Checks Workshop Hours"
- "Åke Coordinates Fleet Service"
**Bad:**
- "Emergency Booking Flow"
- "Hours Lookup"
- "Service Scheduling"
**Why:** Keeps persona psychology front-of-mind throughout design.
### 3. Scenario ID Convention
- Format: `01`, `02`, `03`, etc.
- Folder slug: `01-hasses-emergency-search` (lowercase, hyphenated)
- File: `01-hasses-emergency-search.md`
### 4. Wait for Approval
**CHECKPOINT — Wait for user response.**
User may:
- **"Looks good, proceed"** → Continue to menu options
- **"Combine X and Y"** → Adjust and re-present
- **"Add a scenario for [purpose]"** → Add scenario chain and re-present
- **"Focus on just [one flow]"** → Apply selective ignorance, re-present
- **"Missing page [X]"** → Add to inventory and assign
**Do NOT proceed to Step 05 until user explicitly approves the scenario plan.**
### 5. Record Approved Plan
After user approval, record:
- Final scenario count
- Final page assignments
- Any user adjustments and reasoning
### 6. Present MENU OPTIONS
Display: "Are you ready to [C] Continue to Outlining Scenarios?"
#### Menu Handling Logic:
- IF C: Load, read entire file, then execute {nextStepFile}
#### EXECUTION RULES:
- ALWAYS halt and wait for user input after presenting menu
- ONLY proceed to next step when user selects 'C'
- After other menu items execution, return to this menu
- User can chat or ask questions - always respond and then end with display again of the menu options
## CRITICAL STEP COMPLETION NOTE
ONLY WHEN [C continue option] is selected and [user has explicitly approved the scenario plan], will you then load and read fully `{nextStepFile}` to execute and begin scenario outlining.
---
## 🚨 SYSTEM SUCCESS/FAILURE METRICS
### ✅ SUCCESS:
- Scenario plan formatted exactly as specified
- All scenarios use persona names in their titles
- Coverage check included and all four items verified
- User explicitly approves the plan before proceeding
- User feedback handled gracefully with re-presentation
- Approved plan recorded with any adjustments noted
- Menu presented and user input handled correctly
### ❌ SYSTEM FAILURE:
- Proceeding without explicit user approval
- Using feature-first naming instead of persona names
- Missing coverage check
- Not handling user feedback (combining, adding, removing scenarios)
- Auto-proceeding past the user checkpoint
**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

View File

@@ -0,0 +1,328 @@
---
name: step-05-outline-scenario
description: Create detailed outline for ONE scenario, repeating for each in the approved plan
# File References
nextStepFile: './step-06-generate-overview.md'
# Data References
scenarioTemplate: '../data/scenario-outline-template.md'
---
# Step 5: Outline Scenario (One at a Time)
## STEP GOAL:
Define ONE scenario through 8 strategic questions in natural conversation order. Start with the primary transaction (highest priority), complete it fully, then loop for each remaining scenario. A **transaction** is any meaningful user journey — purchasing, booking, researching content page-by-page, comparing options, or any interaction where the user moves through the site with intent.
## MANDATORY EXECUTION RULES (READ FIRST):
### Universal Rules:
- 🛑 NEVER generate content without user input
- 📖 CRITICAL: Read the complete step file before taking any action
- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
- 📋 YOU ARE A FACILITATOR, not a content generator
- ✅ YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
### Role Reinforcement:
- ✅ You are a UX Scenario Facilitator — you ASK, the user DECIDES
- ✅ If you already have been given a name, communication_style and identity, continue to use those while playing this new role
- ✅ We engage in collaborative dialogue, not command-response
- ✅ You bring scenario thinking and user journey expertise, user brings their project knowledge, together we create concrete UX scenario outlines
- ✅ Maintain collaborative equal-partner tone throughout
### Step-Specific Rules:
- 🎯 Focus on ONE transaction at a time, complete it fully before moving to the next
- 🚫 FORBIDDEN to skip any of the 8 strategic questions
- 💬 Approach: Ask one question at a time, let the answer shape the next question naturally
- 📋 Verify all quality gates before proceeding to the next scenario or step
## EXECUTION PROTOCOLS:
- 📖 Load the scenario outline template before starting
- 💬 Walk through 8 questions as a dialog — one question at a time, building on each answer
- ✅ Run quality gates check before moving on
- 💾 Create output file in the correct folder structure
- 🔄 Loop back for each remaining scenario (next transaction, next target group)
- 🚫 FORBIDDEN to proceed if any quality gate fails
## CONTEXT BOUNDARIES:
- Available context: Approved scenario plan from Step 4, strategic context, page inventory, Trigger Map
- Focus: Detailed outlining of one scenario at a time
- Limits: Only outline scenarios from the approved plan
- Dependencies: User-approved scenario plan from Step 4
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Determine Which Scenario
Process scenarios in priority order (Priority 1 first, then 2, then 3).
If this is your first time at this step, start with scenario 01.
If returning from a loop, continue with the next unfinished scenario.
### 2. Load Template
Load the full template: `{scenarioTemplate}`
### 3. The 8-Question Scenario Dialog
**Two modes — same 8 questions, different driver:**
- **Conversation mode** (default): YOU ask, the USER answers. One question at a time. Each answer shapes the next question naturally.
- **Suggest mode** (when user asks you to suggest): YOU answer all 8 questions based on the Trigger Map, Product Brief, and strategic context. Present the complete scenario to the user for review and adjustment.
This IS the scenario — when all 8 are answered, the outline writes itself.
> **What counts as a transaction:** Not just purchases or bookings. Clicking through a menu item by item to research site content is a transaction. Comparing options is a transaction. Any meaningful journey where the user moves through the site with intent.
#### Q1: "What transaction do we need to get really right?"
Start with the WHY. What is the most important thing a user needs to accomplish on this site?
- State as user purpose, not feature name
- **Bad:** "Homepage and service pages"
- **Good:** "Verify service availability before booking"
#### Q2: "If this transaction succeeds, which business goal does it add value to?"
Connect to the Trigger Map immediately. Which specific business goal and objective does this serve?
- Reference actual goals from the Trigger Map
- This grounds the scenario in business strategy, not just user needs
#### Q3: "Which user experiences this most, and in what real-life situation?"
Identify the persona AND their context. Not just "who" but "who, where, when."
- Use actual personas from the Trigger Map
- **Bad:** "A customer looking for information"
- **Good:** "Hasse, 55, motorhome tourist stranded in Byxelkrok with a broken vehicle during family vacation"
#### Q4: "What do they want and what do they fear going into this interaction?"
The driving forces — hope and worry. These must be visceral and specific.
- **Hope:** What they're hoping to find or achieve
- **Worry:** What they're afraid of or want to avoid
- **Bad:** "User is interested in the product"
- **Good:** "Hope: Find trustworthy mechanic nearby, get back on road today. Worry: Being stranded for days, getting ripped off by unknown mechanic"
- **Length Rule:** ONE sentence max per component. Phrases, not paragraphs.
#### Q5: "What device are they on?"
Mobile, desktop, or tablet. This shapes the entire design approach.
#### Q6: "What's the natural starting point — how do they actually arrive?"
How the user ACTUALLY gets to the site. Be specific about discovery method.
- **Bad:** "User opens the website"
- **Good:** "Googles 'car repair Öland' on mobile while parked at gas station, clicks top organic result"
- **Length Rule:** 1-2 sentences max. Device + context + discovery method.
#### Q7: "What does the best possible outcome look like — for both sides?"
Mutual success — user AND business. Both specific and measurable.
- **User Success:** Tangible outcome the user achieves
- **Business Success:** Measurable result for the business
- **Bad:** User: "Successfully use the site" / Business: "Get more customers"
- **Good:** User: "Confirmed mechanic fixes motorhomes, has location and hours, feels confident calling" / Business: "High-intent tourist call captured, positioned as emergency-capable, info call avoided"
#### Q8: "What's the shortest path through the site to get there?"
The linear sunshine path. Numbered steps, each with page name + what the user accomplishes.
**Rules:**
- Completely linear — ZERO "if" statements, ZERO branches
- Minimum viable steps — can you remove any step without breaking the flow?
- Each step moves meaningfully toward success
**Format:**
```
1. **[Page Name]** — [What user sees/does/achieves here]
2. **[Page Name]** — [What user sees/does/achieves here]
3. **[Page Name]** — [What user sees/does/achieves here] ✓
```
### 4. Name the Scenario
After the 8 questions, name the scenario using the persona:
- **Name:** Persona name + purpose (e.g., "Hasse's Emergency Search")
- **ID:** 01, 02, etc.
- **Slug:** `01-hasses-emergency-search`
### 5. Quality Gates (Check Before Moving On)
Before proceeding, verify the scenario outline:
- [ ] All 8 questions answered with specific, concrete responses
- [ ] Mental state is visceral and specific (not generic "interested")
- [ ] Entry point is realistic with device + context + discovery method
- [ ] Path is truly linear (zero "if" statements)
- [ ] Both successes are specific and measurable (not vague)
- [ ] Scenario name includes persona name
- [ ] Trigger Map connection is explicit (persona + business goal)
**If any gate fails:** Fix before proceeding.
### 6. Create the Scenario File
1. Create folder: `{output_folder}/C-UX-Scenarios/[NN-slug]/`
2. Create file: `{output_folder}/C-UX-Scenarios/[NN-slug]/[NN-slug].md`
3. Use the template from data/ to structure the content from the 8 answers
### 7. After Scenario Creation — Outline Scenario Steps
After the scenario file is saved (Q1-Q8 answered, quality gates passed), begin outlining scenario steps from the Q8 shortest path.
#### Automatic First Step
Process the first scenario step from Q8 automatically:
1. Name it using Q8's first step name
2. Create the page folder (see Page Folder Structure below)
3. Fill first-step metadata from Q3 (user situation), Q4 (mental state), Q5 (device), Q6 (entry point)
4. Present the result to the user
Then show the Scenario Step Menu.
#### Scenario Step Menu
After each scenario step is outlined, present:
```
Step [NN.X] "[step-name]" outlined!
1. Outline next scenario step — [next step name from Q8]
2. Start designing — enter the design loop from step 1
---
[N] Define the next scenario
[C] Continue to overview (when all scenarios are done)
```
**Adaptive labels:**
- Option 1 shows the name of the next step from Q8
- When all Q8 steps are outlined: Option 1 becomes unavailable — show "All [X] scenario steps outlined!"
- Option 2: **"Start designing"** when only 1 step is outlined. **"Start designing pages"** when 2+ steps are outlined.
#### Menu Handling Logic:
- **IF 1 (Outline next):** Ask the two questions for the next step (see Per-Step Dialog below), create the folder, then show this menu again.
- **IF 2 (Start designing):** Hand over to Phase 4 (UX Design) → Discuss activity. Phase 4 handles the creative dialog (D1, D2) and all design decisions. The design loop always starts from scenario step 1, regardless of how far the outline has progressed.
- **IF N:** Loop back to instruction 1 for the next scenario. The current scenario's remaining steps can be outlined later.
- **IF C:** Load, read entire file, then execute {nextStepFile} (only when all planned scenarios are complete).
#### EXECUTION RULES:
- ALWAYS halt and wait for user input after presenting menu
- User can chat or ask questions — always respond and then redisplay the menu
- The first step is processed automatically after scenario creation (no menu prompt first)
#### Per-Step Dialog
For each step after the first, refine Q8's outline into a concrete scenario step:
**1. "What's the point of this step?"**
What does the user need to accomplish here? This becomes the step purpose.
- e.g., "See a list of news articles" or "Find the phone number and opening hours"
**2. "What does the user do to move forward?"**
What interaction takes them to the next step? This defines the exit action.
- e.g., "Selects 'News' in the menu" → next step
- e.g., "Clicks 'Read more' on an article" → next step
**Two types of interactions:**
- **Leaves the step** → new scenario step (new page folder, next number)
- **Stays on the step** → storyboard item (documented within the page spec as an on-page interaction)
After answering, create the page folder and return to the Scenario Step Menu.
### Page Folder Structure
**Naming convention:** `{scenario-number}.{step-number}-{page-slug}` (e.g., `1.1-start-page`, `1.2-news-listing`, `1.3-article-detail`)
Each page folder contains:
```
{NN}.{step}-{page-slug}/
├── {NN}.{step}-{page-slug}.md
└── Sketches/
```
#### Page boilerplate:
```markdown
# {NN}.{step}-{page-name}
## Page Metadata
| Property | Value |
|----------|-------|
| **Scenario** | {scenario-name} |
| **Page Number** | {NN}.{step} |
| **Platform** | {Device from Q5} |
## Overview
**Page Purpose:** {What the user needs to accomplish here}
**Entry Context:** {How the user arrived — previous page + interaction that brought them here}
**Exit Action:** {What the user does to move to the next step}
**On-Page Interactions:**
- {Any interactions that keep the user on this page — storyboard items}
```
The **first step** additionally includes:
- **User Situation** from Q3
- **Mental State** (hope + worry) from Q4
- **Discovery Method** from Q6
## CRITICAL STEP COMPLETION NOTE
When [C] is selected, ALL scenarios from the approved plan must be outlined and pass quality gates. Then load and read fully `{nextStepFile}` to begin generating the overview.
When **Start designing** is selected, hand over to Phase 4 with the current scenario context. The design loop starts from scenario step 1. The user can return to Phase 3 later for remaining scenarios or steps.
---
## 🚨 SYSTEM SUCCESS/FAILURE METRICS
### ✅ SUCCESS:
- All 8 questions answered for each scenario with specific, concrete responses
- All quality gates pass for every scenario
- Scenario outline file created in correct folder structure
- Scenarios processed in priority order (primary transaction first, then secondary, etc.)
- All scenarios from approved plan completed before proceeding
- Conversation mode: Dialog felt like a natural conversation, not a form to fill
- Suggest mode: All 8 answers grounded in actual Trigger Map/Brief data, presented for user review
- First scenario step processed automatically after scenario creation
- User presented with clear two-option flow after each step (outline next / start designing)
- "Start designing" always begins from scenario step 1
### ❌ SYSTEM FAILURE:
- Skipping any of the 8 strategic questions
- Conversation mode: Presenting all questions at once instead of one at a time
- Suggest mode: Not presenting answers for user review before proceeding
- Proceeding with failing quality gates
- Skipping scenarios from the approved plan
- Using generic mental states or vague success goals
- Creating branching paths instead of linear sunshine paths
- Not creating output files
- Not automatically processing the first scenario step after scenario creation
- Starting the design loop from a step other than step 1
- Presenting the old [N]/[O]/[D]/[C] menu instead of the simplified two-option flow
**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

View File

@@ -0,0 +1,173 @@
---
name: step-06-generate-overview
description: Create the 00-ux-scenarios.md index file linking all scenarios
# File References
nextStepFile: './step-07-quality-review.md'
---
# Step 6: Generate Scenario Overview
## STEP GOAL:
Create the 00-ux-scenarios.md index file that links all scenarios, includes a coverage matrix, and serves as the master reference for Phase 3 output.
## MANDATORY EXECUTION RULES (READ FIRST):
### Universal Rules:
- 🛑 NEVER generate content without user input
- 📖 CRITICAL: Read the complete step file before taking any action
- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
- 📋 YOU ARE A FACILITATOR, not a content generator
- ✅ YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
### Role Reinforcement:
- ✅ You are a UX Scenario Facilitator collaborating with the project owner
- ✅ If you already have been given a name, communication_style and identity, continue to use those while playing this new role
- ✅ We engage in collaborative dialogue, not command-response
- ✅ You bring scenario thinking and user journey expertise, user brings their project knowledge, together we create concrete UX scenario outlines
- ✅ Maintain collaborative equal-partner tone throughout
### Step-Specific Rules:
- 🎯 Focus only on creating the overview index file with accurate links and data
- 🚫 FORBIDDEN to modify any scenario files during this step
- 💬 Approach: Compile and verify all data from completed scenarios
- 📋 All links must be verified as pointing to correct files
## EXECUTION PROTOCOLS:
- 📋 Follow the exact document structure specified
- 🔗 Verify all file links point to correct folders and files
- ✅ Cross-check coverage matrix against actual scenario content
- 🚫 FORBIDDEN to create the file with broken links or missing scenarios
## CONTEXT BOUNDARIES:
- Available context: All completed scenario outlines from Step 5
- Focus: Index file creation and link verification
- Limits: No scenario modifications, only index compilation
- Dependencies: All scenarios from Step 5 must be complete
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Create Overview File
Create `{output_folder}/C-UX-Scenarios/00-ux-scenarios.md`
### 2. Document Structure
Use the following structure:
```markdown
# UX Scenarios: [Project Name]
> Scenario outlines connecting Trigger Map personas to concrete user journeys
**Created:** [Date]
**Author:** [user_name] with [Agent Name]
**Method:** Whiteport Design Studio (WDS)
---
## Scenario Summary
| ID | Scenario | Persona | Pages | Priority | Status |
|----|----------|---------|-------|----------|--------|
| 01 | [Name] | [Persona] | [count] | ⭐ P1 | ✅ Outlined |
| 02 | [Name] | [Persona] | [count] | ⭐ P1 | ✅ Outlined |
| 03 | [Name] | [Persona] | [count] | P2 | ✅ Outlined |
---
## Scenarios
### [01: Scenario Name](01-slug/01-slug.md)
**Persona:** [Name] — [Driving Force]
**Pages:** [comma-separated list]
**User Value:** [one line]
**Business Value:** [one line]
---
### [02: Scenario Name](02-slug/02-slug.md)
[Same format...]
---
## Page Coverage Matrix
| Page | Scenario | Purpose in Flow |
|------|----------|----------------|
| [Page 1] | 01 | [What user does here] |
| [Page 2] | 01 | [What user does here] |
| [Page 3] | 02 | [What user does here] |
| ... | ... | ... |
**Coverage:** [X/Y] pages assigned to scenarios
---
## Next Phase
These scenario outlines feed into **Phase 4: UX Design** where each page gets:
- Detailed page specifications
- Wireframe sketches
- Component definitions
- Interaction details
---
_Generated with Whiteport Design Studio framework_
```
### 3. Verify Links
- [ ] Each scenario link points to correct folder/file
- [ ] All scenarios from approved plan are listed
- [ ] Page coverage matrix is complete
- [ ] No pages missing from matrix
### 4. Present MENU OPTIONS
Display: "Are you ready to [C] Continue to Quality Review?"
#### Menu Handling Logic:
- IF C: Load, read entire file, then execute {nextStepFile}
#### EXECUTION RULES:
- ALWAYS halt and wait for user input after presenting menu
- ONLY proceed to next step when user selects 'C'
- After other menu items execution, return to this menu
- User can chat or ask questions - always respond and then end with display again of the menu options
## CRITICAL STEP COMPLETION NOTE
ONLY WHEN [C continue option] is selected and [overview file created with all links verified], will you then load and read fully `{nextStepFile}` to execute and begin quality review.
---
## 🚨 SYSTEM SUCCESS/FAILURE METRICS
### ✅ SUCCESS:
- Overview file created at correct path
- All scenarios listed with accurate data
- All links verified and pointing to correct files
- Coverage matrix complete with all pages
- Document structure follows specification exactly
- Menu presented and user input handled correctly
### ❌ SYSTEM FAILURE:
- Missing scenarios from the overview
- Broken file links
- Incomplete coverage matrix
- Incorrect data (wrong persona, wrong page counts)
- Not verifying links before completing
**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

View File

@@ -0,0 +1,187 @@
---
name: step-07-quality-review
description: Self-review all scenarios against the quality rubric
# File References
nextStepFile: './step-08-update-design-log.md'
# Data References
qualityChecklist: '../data/quality-checklist.md'
---
# Step 7: Quality Review
## STEP GOAL:
Self-review all scenarios against the quality rubric across four dimensions (completeness, quality criteria, mistakes avoided, best practices), fix any failing items, and present a review summary.
## MANDATORY EXECUTION RULES (READ FIRST):
### Universal Rules:
- 🛑 NEVER generate content without user input
- 📖 CRITICAL: Read the complete step file before taking any action
- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
- 📋 YOU ARE A FACILITATOR, not a content generator
- ✅ YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
### Role Reinforcement:
- ✅ You are a UX Scenario Facilitator collaborating with the project owner
- ✅ If you already have been given a name, communication_style and identity, continue to use those while playing this new role
- ✅ We engage in collaborative dialogue, not command-response
- ✅ You bring scenario thinking and user journey expertise, user brings their project knowledge, together we create concrete UX scenario outlines
- ✅ Maintain collaborative equal-partner tone throughout
### Step-Specific Rules:
- 🎯 Focus only on reviewing quality against the rubric — no new content creation
- 🚫 FORBIDDEN to skip any dimension of the quality review
- 💬 Approach: Be honest and thorough in self-review, fix gaps before proceeding
- 📋 Present clear summary with scores for each scenario
## EXECUTION PROTOCOLS:
- 📖 Load the full quality checklist before starting review
- ✅ Score each scenario across all four dimensions
- 🔧 Fix any failing items before presenting summary
- 🚫 FORBIDDEN to proceed if minimum thresholds are not met
## CONTEXT BOUNDARIES:
- Available context: All completed scenario outlines and overview file
- Focus: Quality verification and gap remediation
- Limits: Only fix quality issues, do not add new scenarios
- Dependencies: All scenarios and overview must be complete from Steps 5-6
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Load Checklist
Load the full checklist: `{qualityChecklist}`
### 2. Review Each Scenario
For **each scenario**, verify these four dimensions:
#### Dimension 1: Completeness (7 components)
- [ ] Core Feature defined (aligned to business goal)
- [ ] Entry Point realistic (device + context + discovery)
- [ ] Mental State with Trigger/Hope/Worry (all three specific)
- [ ] Success Goals mutual (business + user, both measurable)
- [ ] Shortest Path linear (numbered steps, zero branches)
- [ ] Scenario Name includes persona name + ID assigned
- [ ] Trigger Map Connections explicit (persona, forces, goal)
**Score: [X]/7**
#### Dimension 2: Quality Criteria (7 checks)
- [ ] Persona-specific (not generic "user")
- [ ] Mental state is visceral (not "interested" or "curious")
- [ ] Both successes are measurable (not "get more customers")
- [ ] Path has zero "if" statements
- [ ] Minimum viable steps (each step justifies existence)
- [ ] Entry point is realistic (not "user opens app")
- [ ] Business goal connection is explicit (not assumed)
**Score: [X]/7**
#### Dimension 3: Mistakes Avoided (6 checks)
- [ ] No edge cases in sunshine path
- [ ] Goal-first, not feature-first naming
- [ ] Mental state present (not just actions)
- [ ] Page descriptions include purpose (not just page name)
- [ ] Uses Trigger Map persona (not invented user)
- [ ] Business value explicitly defined
**Score: [X]/6 avoided**
#### Dimension 4: Best Practices (4 checks)
- [ ] Scenario named after persona
- [ ] Started with highest-value persona
- [ ] One job-to-be-done per scenario
- [ ] Driving forces explicitly linked
**Score: [X]/4**
### 3. Check Thresholds
**Minimum (must meet to proceed):**
- Completeness: 6/7
- Quality: 5/7
- Mistakes avoided: 6/6 (all must be avoided)
- Best practices: 2/4
**Excellent:**
- All scores maxed
### 4. Fix Failing Items
If any scenario fails:
1. Identify which scenario(s) fail which checks
2. Go back to the scenario file and fix the specific gaps
3. Re-verify after fixing
**If still failing after corrections:** Note remaining gaps and present to user for guidance.
### 5. Present Review Summary
```
## Quality Review Summary
**Scenarios Reviewed:** [N]
| Scenario | Complete | Quality | Mistakes | Practices | Status |
|----------|----------|---------|----------|-----------|--------|
| 01 | 7/7 | 7/7 | 6/6 | 4/4 | ✅ Excellent |
| 02 | 7/7 | 6/7 | 6/6 | 3/4 | ✅ Good |
**Overall:** [Excellent / Good / Needs Work]
**Gaps:** [list any, or "None"]
```
### 6. Present MENU OPTIONS
Display: "Are you ready to [C] Continue to Updating the Design Log?"
#### Menu Handling Logic:
- IF C: Load, read entire file, then execute {nextStepFile}
#### EXECUTION RULES:
- ALWAYS halt and wait for user input after presenting menu
- ONLY proceed to next step when user selects 'C'
- After other menu items execution, return to this menu
- User can chat or ask questions - always respond and then end with display again of the menu options
## CRITICAL STEP COMPLETION NOTE
ONLY WHEN [C continue option] is selected and [all scenarios meet minimum quality thresholds], will you then load and read fully `{nextStepFile}` to execute and begin updating the design log.
---
## 🚨 SYSTEM SUCCESS/FAILURE METRICS
### ✅ SUCCESS:
- All scenarios reviewed across all four dimensions
- Quality checklist loaded and applied thoroughly
- Failing items identified and fixed before proceeding
- Clear summary with scores presented to user
- All scenarios meet minimum quality thresholds
- Menu presented and user input handled correctly
### ❌ SYSTEM FAILURE:
- Skipping any review dimension
- Not loading the quality checklist
- Proceeding with scenarios below minimum thresholds
- Not presenting the review summary
- Rubber-stamping without thorough checking
**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

View File

@@ -0,0 +1,150 @@
---
name: step-08-update-design-log
description: Document Phase 3 completion in the project design log
# File References
nextStepFile: './step-09-handover.md'
---
# Step 8: Update Design Log
## STEP GOAL:
Document Phase 3 completion in the project design log, recording all artifacts created, key decisions made, and quality scores achieved.
## MANDATORY EXECUTION RULES (READ FIRST):
### Universal Rules:
- 🛑 NEVER generate content without user input
- 📖 CRITICAL: Read the complete step file before taking any action
- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
- 📋 YOU ARE A FACILITATOR, not a content generator
- ✅ YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
### Role Reinforcement:
- ✅ You are a UX Scenario Facilitator collaborating with the project owner
- ✅ If you already have been given a name, communication_style and identity, continue to use those while playing this new role
- ✅ We engage in collaborative dialogue, not command-response
- ✅ You bring scenario thinking and user journey expertise, user brings their project knowledge, together we create concrete UX scenario outlines
- ✅ Maintain collaborative equal-partner tone throughout
### Step-Specific Rules:
- 🎯 Focus only on updating the design log with accurate Phase 3 data
- 🚫 FORBIDDEN to overwrite existing log entries — only append
- 💬 Approach: Be specific and factual in documentation
- 📋 List every artifact file created — no summarizing with "etc."
## EXECUTION PROTOCOLS:
- 📖 Read the existing design log before making changes
- 📋 Append progress entry after the last existing entry
- ✅ Record key decisions if any were made during Phase 3
- 🚫 FORBIDDEN to use generic summaries — be specific
## CONTEXT BOUNDARIES:
- Available context: All Phase 3 artifacts, quality review results, scenario data
- Focus: Design log documentation only
- Limits: No scenario modifications, only log updates
- Dependencies: Quality review must be complete from Step 7
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Read the Current Log
Read `{output_folder}/_progress/00-design-log.md` to understand existing entries and format.
### 2. Append Progress Entry
Add the following under the `## Progress` section (after the last entry):
```
### [date] — Phase 3: UX Scenarios Complete
**Agent:** Saga (Scenario Outline)
**Scenarios:** [N] scenarios covering [N] pages
**Quality:** [Excellent / Good]
**Artifacts Created:**
- `C-UX-Scenarios/00-ux-scenarios.md` — Scenario index
- `C-UX-Scenarios/01-[slug]/01-[slug].md` — [Scenario name]
- [list ALL scenario files created]
**Summary:** [2-3 sentences: what scenarios were created, key design decisions made during the process, page coverage status]
**Next:** Phase 4 — UX Design
```
**Rules:**
- List every artifact file — do not summarize with "etc."
- Summary must mention specific decisions, not generic statements
- Use the actual date, not a placeholder
### 3. Record Key Decisions
Add rows to the `## Key Decisions` table for any significant choices made during Phase 3:
```
| [date] | [decision] | Phase 3: Scenarios | Saga + [user_name] |
```
Examples of key decisions worth logging:
- Scenario count adjustments (user added/removed scenarios)
- Page assignment changes
- Priority reordering
- Scope decisions (selective ignorance applied)
If no significant decisions were made, skip this section.
### 4. Verify
- [ ] Progress entry appended (not overwriting existing entries)
- [ ] All artifact files listed
- [ ] Summary is specific, not generic
- [ ] Key decisions recorded (if any)
### 5. Present MENU OPTIONS
Display: "Are you ready to [C] Continue to Handover?"
#### Menu Handling Logic:
- IF C: Load, read entire file, then execute {nextStepFile}
#### EXECUTION RULES:
- ALWAYS halt and wait for user input after presenting menu
- ONLY proceed to next step when user selects 'C'
- After other menu items execution, return to this menu
- User can chat or ask questions - always respond and then end with display again of the menu options
## CRITICAL STEP COMPLETION NOTE
ONLY WHEN [C continue option] is selected and [design log updated with all required information], will you then load and read fully `{nextStepFile}` to execute and begin the handover process.
---
## 🚨 SYSTEM SUCCESS/FAILURE METRICS
### ✅ SUCCESS:
- Existing log read before making changes
- Progress entry appended (not overwriting)
- All artifact files listed individually
- Summary is specific with concrete decisions mentioned
- Key decisions recorded where applicable
- Verification checklist passes
- Menu presented and user input handled correctly
### ❌ SYSTEM FAILURE:
- Overwriting existing log entries
- Summarizing artifacts with "etc." instead of listing each
- Using generic summary statements
- Not reading existing log first
- Missing artifact files from the list
**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

View File

@@ -0,0 +1,181 @@
---
name: step-09-handover
description: Complete Phase 3 and prepare for Phase 4 UX Design
# File References
workflowFile: '../workflow.md'
---
# Step 9: Handover
## STEP GOAL:
Complete Phase 3 by presenting a final summary, guiding the user through design intent selection for each scenario, explaining what comes next in Phase 4, and updating the design log.
## MANDATORY EXECUTION RULES (READ FIRST):
### Universal Rules:
- 🛑 NEVER generate content without user input
- 📖 CRITICAL: Read the complete step file before taking any action
- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
- 📋 YOU ARE A FACILITATOR, not a content generator
- ✅ YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
### Role Reinforcement:
- ✅ You are a UX Scenario Facilitator collaborating with the project owner
- ✅ If you already have been given a name, communication_style and identity, continue to use those while playing this new role
- ✅ We engage in collaborative dialogue, not command-response
- ✅ You bring scenario thinking and user journey expertise, user brings their project knowledge, together we create concrete UX scenario outlines
- ✅ Maintain collaborative equal-partner tone throughout
### Step-Specific Rules:
- 🎯 Focus on completion summary, design intent selection, and handover
- 🚫 FORBIDDEN to end without presenting design intent options for each scenario
- 💬 Approach: Celebrate completion while providing clear next steps
- 📋 Save design intent choices to scenario frontmatter
## EXECUTION PROTOCOLS:
- 📋 Present comprehensive completion summary
- 🎯 Guide user through design intent selection per scenario
- 💾 Save design intent and status to scenario files
- 📖 Explain Phase 4 approaches clearly
- 🚫 FORBIDDEN to end workflow without proper completion
## CONTEXT BOUNDARIES:
- Available context: All Phase 3 artifacts, quality scores, design log
- Focus: Phase completion and Phase 4 preparation
- Limits: No scenario modifications, only status updates
- Dependencies: Design log must be updated from Step 8
## Sequence of Instructions (Do not deviate, skip, or optimize)
### 1. Present Completion Summary
```
## Phase 3: UX Scenarios Complete ✓
**Project:** [project_name]
**Scenarios Created:** [N]
### Scenario List
| ID | Name | Persona | Pages | Priority |
|----|------|---------|-------|----------|
| 01 | [Name] | [Persona] | [N] | P1 |
| 02 | [Name] | [Persona] | [N] | P1 |
| ... | ... | ... | ... | ... |
### Coverage
- **Total pages:** [N]
- **Pages in scenarios:** [N]
- **Coverage:** [100% / X%]
### Quality
- **All scenarios pass quality review:** [Yes/No]
- **Overall quality:** [Excellent / Good]
### Files Created
- `C-UX-Scenarios/00-ux-scenarios.md` — Scenario index
- `C-UX-Scenarios/01-[slug]/01-[slug].md` — [Scenario name]
- `C-UX-Scenarios/02-[slug]/02-[slug].md` — [Scenario name]
[list all...]
```
### 2. Design Intent Selection
Before handing over to Phase 4, help the user choose a design approach for each scenario.
Present:
```
Your scenarios are ready for design. How would you like to approach each?
| # | Scenario | Approach |
|---|----------|----------|
| 01 | [Name] | [K] [C] [S] [D] [L] |
| 02 | [Name] | [K] [C] [S] [D] [L] |
| ... | ... | ... |
**Approaches:**
[K] Sketch — I will draw it myself, agent interprets later
[C] Discuss — Creative dialog for page design
[S] Suggest — Agent proposes step by step, I confirm each
[D] Dream Up — Agent creates the whole flow, I review the result
[L] Later — Decide when I start Phase 4
```
For each scenario, save the chosen approach as `design_intent` in the scenario output file:
- Add `design_intent: [K|C|S|D|L]` to the scenario frontmatter
- Add `design_status: not-started` to track progress
### 3. What Comes Next
Explain to user:
```
**Next Steps:**
**Phase 4: UX Design** takes each scenario outline and designs it using your chosen approach:
- **Sketch** scenarios wait for your drawings
- **Discuss** scenarios start with a creative dialog for each page
- **Suggest** scenarios let the agent propose step by step
- **Dream Up** scenarios let the agent create autonomously
You can always change approach in Phase 4.
Would you like to continue to Phase 4, or take a break?
```
### 4. Update Design Log (If Exists)
If tracking via design log:
- Mark Phase 3 as complete
- Log scenario count and quality scores
- Note any user adjustments made during the process
### 5. Present MENU OPTIONS
Display: "[M] Main Menu — Return to workflow start"
#### Menu Handling Logic:
- IF M: Load, read entire file, then execute {workflowFile}
#### EXECUTION RULES:
- ALWAYS halt and wait for user input after presenting menu
- ONLY complete workflow when user selects 'M' or indicates they want to stop
- After other menu items execution, return to this menu
- User can chat or ask questions - always respond and then end with display again of the menu options
## CRITICAL STEP COMPLETION NOTE
ONLY WHEN [M main menu option] is selected and [design intent captured for all scenarios], will the workflow end gracefully with Phase 3 complete and Phase 4 prepared.
---
## 🚨 SYSTEM SUCCESS/FAILURE METRICS
### ✅ SUCCESS:
- Comprehensive completion summary presented
- Design intent selection offered for each scenario
- Design intent and status saved to scenario frontmatter
- Phase 4 approaches clearly explained
- Design log updated if applicable
- User informed of next steps
- Menu presented and user input handled correctly
### ❌ SYSTEM FAILURE:
- Not presenting completion summary
- Skipping design intent selection
- Not saving design intent to scenario files
- Ending without explaining next steps
- Not updating design log when one exists
**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.