Mimir was removed in the workshop refactor. Update README, docs-guide,
and activation files to reflect the three-agent architecture.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Rename docs/learn-wds/ to docs/learn/ and update all 17 references
- Module 02: Replace manual clone/mkdir/Mimir with npx installer + direct
agent activation (Saga, Freya, Idunn — no Mimir)
- Module 08: Replace 9-section scenario template with Q1-Q8 dialog format
matching the actual workflow (step-05-outline-scenario.md)
- Update scenario naming convention to persona-based (01-name-purpose)
- Update folder structure to NN.step-page-slug format
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Remove "Strategic Context (Step 4)" from Phase 1 guide — Phase 1 is
casual business discovery, not trigger mapping
- Update flowchart to remove Strategic Context box
- Mark VTC guide as "Removed" (was "Deprecated")
- Historical session logs in docs/examples/ left as-is (records)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The VTC (Value Trigger Chain) was a separate concept that extracted
specific nodes from the Trigger Map into a YAML file. This caused
agents to run trigger mapping during Phase 1 (Product Brief), forcing
users to repeat the work in Phase 2. Observed in Monday workshop.
Architectural fix:
- Phase 1 is casual business discovery, NOT trigger mapping
- Phase 2 is where the Trigger Map gets built (unchanged)
- When scenarios/content need strategic context, they reference
the Trigger Map directly — no separate VTC concept needed
Removed (19 files deleted):
- 1-project-brief/vtc-workshop/ (14 step files + workflow)
- step-04-create-vtc.md and step-11a-create-vtc.md from Phase 1
- step-03c-create-vtc.md from Phase 0 alignment
- vtc-template.yaml
Renamed:
- step-03-build-vtcs.md → step-03-build-strategic-context.md
- step-02-vtc-consistency.md → step-02-trigger-map-consistency.md
- step-01-load-vtc-context.md → step-01-load-trigger-map-context.md
- 07-create-vtc.md → 07-reference-trigger-map.md
Rewritten:
- Phase 4 scenario init: "create VTC" → lightweight "pick from Trigger Map"
- Phase 6 content: load context from Trigger Map, not from VTC
- Templates: "Trigger Map" section → "Business Context" (Phase 1 scope)
Zero VTC references remain in src/.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Suggest workflow: Component Extraction Check prompts user to extract
shared elements when starting the 2nd+ page in a scenario
- Dream workflow: Auto-extracts shared components and reports in summary
- Spec audit Level 3: Cross-Page Duplicate Detection compares sections
across all pages, flags exact/near duplicates with severity levels
- Fix Freya role name (Scenario Architect → Facilitator)
- Remove duplicate trigger-map reference in Eira guide
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Remove duplicate `Reads: 2-strategy/trigger-map.md` line in eira-visual-designer.md
- Rename "Scenario Architect" to "Scenario Facilitator" in freya.activation.md
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Systematic cleanup of Value Trigger Chain (VTC) references in 60 files across
all phases. VTC is replaced with context-appropriate terms:
- "Trigger Map" when referencing the Phase 2 artifact
- "Strategic context" when referencing the extracted business/persona/forces data
- "Value Proposition" for customer-facing value descriptions
Remaining VTC references are only in VTC Workshop definition files (vtc-workshop/,
create-vtc steps) which will be addressed when those workflows are redesigned.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Freya menu: simpler descriptions, logical grouping (SC/UX/SP/SA/GA/DS/DD)
- Freya menu: remove AD and ST, add SC (Scenarios) and SP (Specifications)
- Fix VTC reference in freya agent and workflow-conceptualize
- Conceptualize: save findings to page spec, not separate notes file
- Conceptualize: offer Excalidraw sketching, user sketch first
- Conceptualize: require reading existing specs before drawing
- Conceptualize: no annotations on wireframes rule
- Add Excalidraw tool guide and update tools guide
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace Value Trigger Chain (VTC) with Trigger Map / Slim Trigger Map
across method guides, model docs, learn-wds tutorials, and docs index.
Historical examples left untouched.
- docs-guide.md: Remove VTC entry, update phase list
- method/: Replace VTC with Trigger Map in content guides
- models/: Replace VTC sections/links with Trigger Map references
- learn-wds/: Rename VTC to Slim Trigger Map in lessons and tutorials
- phase-2 guide: Fix What Comes Next + Related Resources
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- ui.js: Remove Idunn from available agents list
- ide-configs.js: Remove Mimir and Idunn, update Saga/Freya phase descriptions
- _base-ide.js: Remove Idunn fallback metadata
- cline.js: Remove idunn.md from cleanup agent list
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
After designing a page, the agent asks what's next: outline and design
the next page in the scenario [N], return to dashboard [R], or validate
[V]. Choosing [N] runs Phase 3's page outline dialog (purpose + exit
action) then designs the page, creating a continuous loop.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
[O] Outline now walks through pages as a conversation: for each page,
ask what the user accomplishes and what interaction moves them forward.
Interactions that leave the page create new steps; interactions that
stay on the page become storyboard items within the page spec.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
[S] → [O] Outline scenario pages. User can cycle through pages
one at a time and stop whenever they want, rather than creating
all at once.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Instead of always creating all page folders, the post-scenario menu
now offers: [N] next scenario, [S] scaffold all page folders,
[D] create first page and design, [C] generate overview. Page folder
structure uses NN.step-slug naming with Sketches/ subfolder.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove Mimir references (3 agents now: Saga, Freya, Idunn). Update all
9 phases with correct names, agents, and output folders. Add section on
the 8-question scenario dialog. Update IDE list and project structure.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Phase 4 now checks for existing Phase 3 scenarios before page design.
If no scenario exists, redirects user to Phase 3's 8-question dialog
instead of attempting a lighter inline version.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
After completing a scenario, the user can now choose to:
- [N] Define the next scenario
- [D] Jump to Phase 4 and start designing the first page
- [C] Generate the overview (when all scenarios done)
This lets users design one scenario before defining the rest,
creating a more natural workflow.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Restructure Phase 3 scenario creation around a natural conversation
flow instead of a template checklist:
- 8 strategic questions asked in logical order: transaction → business
goal → user & situation → driving forces → device → starting point
→ best outcome → shortest path
- Two modes: conversation (agent asks, user answers) and suggest
(agent answers from Trigger Map, user reviews)
- Broader transaction definition: includes content browsing and
research, not just purchases/bookings
- Agent creates first page specification after Q8, giving Phase 4
a concrete starting point
- Template reordered to match Q1-Q8 dialog flow
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Implement BMad-style IDE handler architecture for WDS:
- Base class (_base-ide.js) with template method pattern
- Dynamic handler discovery via IdeManager
- Priority handlers: Windsurf, Cursor, Claude Code, Cline, GitHub Copilot
- Installer integration after agent compilation step
- Saga activation now branches on starting_point config (pitch vs brief)
- Remove parenthetical hint from learning material prompt
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Removed all pre-selection (all unchecked by default)
- Removed star markers (⭐) - no preferences shown
- Sorted alphabetically for neutral presentation
- Users must actively choose their tools
- Validation still requires at least one selection
Platform-agnostic: WDS works equally well with any AI coding tool
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Changed from single-select list to checkbox (multiselect)
- Added full IDE list from BMad: Windsurf, Cursor, Claude Code, GitHub Copilot, Cline, VS Code, Other
- Windsurf and Cursor marked as preferred (pre-checked)
- Validation requires at least one IDE selected
- Updated config.yaml to store ides array instead of single ide
- Updated success message to display multiple IDEs (e.g., "Windsurf or Cursor")
- Ensures WDS commands work cross-platform for all selected IDEs
User request: "Look at the BMad installer, there is a multiselect box for IDEs use the full list from the BMad installer"
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Added IDE selection question (Windsurf, VS Code, Cursor, Other)
- Made learning material installation optional with confirm prompt
- Success message now shows selected IDE name
- Store IDE preference in config.yaml
- Installer now has 5 questions (up from 3)
User feedback: "IDE selection is crucial for the installer" and "ask if the learn section should be installed"
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
User feedback: UX design happens IN the scenarios (C), not as separate phase.
Old (incorrect):
- A-Product-Brief
- B-Trigger-Map
- C-UX-Scenarios
- D-UX-Design (redundant!)
- E-Design-System
New (correct):
- A-Product-Brief
- B-Trigger-Map
- C-UX-Scenarios (UX design is done here)
- D-Design-System
4 phases instead of 5 - cleaner and more accurate.
More conversational and explicit:
- 'Get Started with Your Product Brief' (goal-oriented)
- 'Locate the chat window in your IDE' (explicit location)
- 'type:' instead of 'paste this command:' (simpler action)
- Command in quotes to make it clear it's text to type
- Better line breaks for readability
Old message was too technical and vague.
New message:
- Clear numbered steps (1-2-3)
- Specific: 'Open this folder in Windsurf or VS Code'
- Exact command to paste (not just 'tell the AI')
- Clear outcome: 'Saga will greet you by name'
- Cleaner layout with separator
Addresses workshop feedback about confusing instructions.
Workshop feedback: 00-*.md files were confusing and ignored by users.
Changes:
- Remove createFolderGuides() and createProjectInfoFile() methods
- Folders still created but empty (only .gitkeep)
- Agents will create files dynamically during workflows
- Cleaner, less confusing user experience
- Add 3rd question: Output folder name (default: design-process)
- Users can customize to docs/, deliverables/, etc.
- Update config.yaml to use dynamic root_folder
- Update template placeholders to use config.root_folder
Balances simplification (3 questions vs 7+) with useful customization.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Remove mimir-orchestrator.agent.yaml (orchestration layer removed)
- Add activation prompt to Saga for immediate greeting
- Saga now direct entry point (no orchestrator needed)
- Greets user by name and starts Product Brief workflow
Workshop finding: 50% bypassed orchestration, Mimir added complexity.
Direct activation simplifies user journey.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Users can now choose between design-process/, docs/, or deliverables/
- Removes folder auto-detection logic that caused duplicate folders
- Installer creates folders at user's chosen location
- Prevents conflict with project setup workflow
Fixes issue where both design-process/ and docs/ were created.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
createFolderGuides() needs config parameter for template replacements.
This was causing "config is not defined" error during installation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Publishes to npm on tag push (v*) or manual trigger.
Bypasses local 2FA issues by using NPM_TOKEN secret.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Mårten Angner