wize-dev-kit 0.16.0 → 0.17.0

package/src/method-skills/3-solutioning/wize-create-architecture/steps/step-05-patterns.md

@@ -0,0 +1,109 @@
+# Step 5: Implementation Patterns & Consistency Rules
+
+## Mandatory execution rules
+
+- 🛑 Never generate content without user input.
+- ✅ Treat this as collaborative discovery.
+- 🎯 Focus on patterns that prevent AI agent implementation conflicts.
+- 🎯 Emphasize what agents could decide differently if not specified.
+- ⚠️ No time estimates.
+- ✅ Speak in `{communication_language}`; write artifacts in `{document_output_language}`.
+
+## Execution protocols
+
+- 🎯 Show analysis before taking action.
+- ⚠️ Present A/P/C menu after generating patterns content.
+- 💾 Only save when the user chooses C.
+- 📖 Update frontmatter `stepsCompleted: [1, 2, 3, 4, 5]` before loading the next step.
+
+## Collaboration menu (A/P/C)
+
+- **A (Advanced Elicitation)** — develop additional consistency patterns.
+- **P (Party Mode)** — identify conflict points from multiple perspectives.
+- **C (Continue)** — save and move to project structure.
+
+## Context boundaries
+
+- Core decisions from step 4 are complete.
+- Technology stack is decided.
+- Focus on HOW agents should implement, not WHAT.
+
+## Task
+
+Define implementation patterns and consistency rules so multiple AI agents write compatible code.
+
+## Pattern categories
+
+### Naming patterns
+
+- Database table/column naming
+- API endpoint naming
+- File and directory naming
+- Component/function/variable naming
+- Route parameter formats
+
+### Structure patterns
+
+- Where tests live
+- How components are organized
+- Where utilities and helpers go
+- Configuration file organization
+
+### Format patterns
+
+- API response wrappers
+- Error response structures
+- Date/time formats
+- JSON field naming (snake_case vs camelCase)
+
+### Communication patterns
+
+- Event naming conventions
+- Event payload structures
+- State update patterns
+- Action naming conventions
+- Logging formats and levels
+
+### Process patterns
+
+- Loading state handling
+- Error recovery
+- Retry implementation
+- Authentication flow
+- Validation timing and methods
+
+## Generate patterns content
+
+Append to `architecture.md`:
+
+```markdown
+## Implementation Patterns & Consistency Rules
+
+### Naming Patterns
+...
+
+### Structure Patterns
+...
+
+### Format Patterns
+...
+
+### Communication Patterns
+...
+
+### Process Patterns
+...
+
+### Enforcement Guidelines
+
+**All AI agents MUST:**
+- ...
+
+### Pattern Examples
+**Good:** ...
+**Anti-patterns:** ...
+```
+
+## Next step
+
+After C, load `./step-06-structure.md`.

package/src/method-skills/3-solutioning/wize-create-architecture/steps/step-06-structure.md

@@ -0,0 +1,97 @@
+# Step 6: Project Structure & Boundaries
+
+## Mandatory execution rules
+
+- 🛑 Never generate content without user input.
+- ✅ Treat this as collaborative discovery.
+- 🗺️ Create a complete project tree, not generic placeholders.
+- 🗺️ Map requirements/epics to architectural components.
+- ⚠️ No time estimates.
+- ✅ Speak in `{communication_language}`; write artifacts in `{document_output_language}`.
+
+## Execution protocols
+
+- 🎯 Show analysis before taking action.
+- ⚠️ Present A/P/C menu after generating project structure.
+- 💾 Only save when the user chooses C.
+- 📖 Update frontmatter `stepsCompleted: [1, 2, 3, 4, 5, 6]` before loading the next step.
+
+## Collaboration menu (A/P/C)
+
+- **A (Advanced Elicitation)** — explore innovative project organization.
+- **P (Party Mode)** — evaluate structure trade-offs.
+- **C (Continue)** — save and move to validation.
+
+## Context boundaries
+
+- All previous decisions are complete.
+- Implementation patterns are defined.
+- Focus on physical project structure and component boundaries.
+
+## Task
+
+Define the complete project structure and architectural boundaries based on all decisions made.
+
+## Structure sequence
+
+### 1. Analyze requirements mapping
+
+Map epics or FR categories to directories/services.
+
+### 2. Define project directory structure
+
+Create a complete, technology-specific tree:
+
+- Root configuration files
+- Source code organization
+- Test organization
+- Build and distribution
+
+### 3. Define integration boundaries
+
+- API boundaries
+- Component boundaries
+- Service boundaries
+- Data boundaries
+
+### 4. Map requirements to structure
+
+For each epic or feature cluster:
+
+```markdown
+Epic: User Management
+- Components: src/components/features/users/
+- Services: src/services/users/
+- API Routes: src/app/api/users/
+- Database: prisma/migrations/...
+- Tests: tests/features/users/
+```
+
+## Generate structure content
+
+Append to `architecture.md`:
+
+```markdown
+## Project Structure & Boundaries
+
+### Complete Project Directory Structure
+```
+{{tree}}
+```
+
+### Architectural Boundaries
+...
+
+### Requirements to Structure Mapping
+...
+
+### Integration Points
+...
+
+### File Organization Patterns
+...
+```
+
+## Next step
+
+After C, load `./step-07-validation.md`.

package/src/method-skills/3-solutioning/wize-create-architecture/steps/step-07-validation.md

@@ -0,0 +1,124 @@
+# Step 7: Architecture Validation & Completion
+
+## Mandatory execution rules
+
+- 🛑 Never generate content without user input.
+- ✅ Validate all requirements are covered by architectural decisions.
+- ⚠️ No time estimates.
+- ✅ Speak in `{communication_language}`; write artifacts in `{document_output_language}`.
+
+## Execution protocols
+
+- 🎯 Show analysis before taking action.
+- ✅ Run validation checks on the complete architecture.
+- ⚠️ Present A/P/C menu after generating validation results.
+- 💾 Only save when the user chooses C.
+- 📖 Update frontmatter `stepsCompleted: [1, 2, 3, 4, 5, 6, 7]` before loading the next step.
+
+## Collaboration menu (A/P/C)
+
+- **A (Advanced Elicitation)** — address complex architectural issues found.
+- **P (Party Mode)** — review validation from multiple perspectives.
+- **C (Continue)** — save validation results and complete the architecture.
+
+## Context boundaries
+
+- Complete architecture document is available.
+- All decisions, patterns, and structure are defined.
+- Focus on validation, gap analysis, and coherence.
+
+## Task
+
+Validate the complete architecture for coherence, completeness, and readiness.
+
+## Validation sequence
+
+### 1. Coherence validation
+
+- Decision compatibility
+- Pattern consistency
+- Structure alignment
+
+### 2. Requirements coverage validation
+
+- Epic/feature coverage
+- Functional requirements coverage
+- Non-functional requirements coverage
+
+### 3. Implementation readiness validation
+
+- Decision completeness
+- Structure completeness
+- Pattern completeness
+
+### 4. Gap analysis
+
+Identify critical, important, and nice-to-have gaps.
+
+### 5. Generate validation content
+
+Append to `architecture.md`:
+
+```markdown
+## Architecture Validation Results
+
+### Coherence Validation
+...
+
+### Requirements Coverage Validation
+...
+
+### Implementation Readiness Validation
+...
+
+### Gap Analysis Results
+...
+
+### Validation Issues Addressed
+...
+
+### Architecture Completeness Checklist
+
+**Requirements Analysis**
+- [ ] Project context thoroughly analyzed
+- [ ] Scale and complexity assessed
+- [ ] Technical constraints identified
+- [ ] Cross-cutting concerns mapped
+
+**Architectural Decisions**
+- [ ] Critical decisions documented with versions
+- [ ] Technology stack fully specified
+- [ ] Integration patterns defined
+- [ ] Performance considerations addressed
+
+**Implementation Patterns**
+- [ ] Naming conventions established
+- [ ] Structure patterns defined
+- [ ] Communication patterns specified
+- [ ] Process patterns documented
+
+**Project Structure**
+- [ ] Complete directory structure defined
+- [ ] Component boundaries established
+- [ ] Integration points mapped
+- [ ] Requirements to structure mapping complete
+
+### Architecture Readiness Assessment
+
+**Overall Status:** [READY FOR IMPLEMENTATION / READY WITH MINOR GAPS / NOT READY]
+**Confidence Level:** [high/medium/low]
+**Key Strengths:** ...
+**Areas for Future Enhancement:** ...
+
+### Implementation Handoff
+
+**AI Agent Guidelines:**
+- Follow all architectural decisions exactly as documented.
+- Use implementation patterns consistently.
+- Respect project structure and boundaries.
+- Refer to this document for all architectural questions.
+```
+
+## Next step
+
+After C, load `./step-08-complete.md`.

package/src/method-skills/3-solutioning/wize-create-architecture/steps/step-08-complete.md

@@ -0,0 +1,59 @@
+# Step 8: Architecture Completion & Handoff
+
+## Mandatory execution rules
+
+- 🛑 Never generate content without user input.
+- ✅ Treat this as collaborative completion.
+- 🎯 Provide clear next steps for implementation.
+- ⚠️ No time estimates.
+- ✅ Speak in `{communication_language}`; write artifacts in `{document_output_language}`.
+
+## Execution protocols
+
+- 🎯 Show completion summary and implementation guidance.
+- 📖 Update frontmatter with final workflow state.
+- 🚫 This is the final step.
+
+## Task
+
+Complete the architecture workflow and guide the user to the next phase.
+
+## Completion sequence
+
+### 1. Summarize achievements
+
+Congratulate the user and summarize what was built together:
+
+- Architecture document path
+- Number of ADRs produced
+- Key decisions made
+- Patterns defined
+- Validation status
+
+### 2. Update frontmatter
+
+```yaml
+status: ready-for-stories
+owner: Tony Stark
+updated: "{{date}}"
+stepsCompleted: [1, 2, 3, 4, 5, 6, 7, 8]
+workflowType: architecture
+lastStep: 8
+```
+
+### 3. Next steps guidance
+
+```
+Architecture complete. Next:
+1. Hawkeye: run wize-tea-risk to build the global risk profile.
+2. Tony: run wize-create-epics-and-stories to slice the work.
+3. Use `/wize` (or `/wize-help`) anytime to check what comes next.
+```
+
+## On complete
+
+Run `{workflow.on_complete}` if non-empty.
+
+## Workflow complete
+
+The architecture is now the single source of truth for all technical decisions, ensuring consistent implementation across the project lifecycle.

package/src/method-skills/3-solutioning/wize-create-architecture/workflow.md

@@ -1,64 +1,71 @@
 ---
+
 code: wize-create-architecture
+description: "Use quando o PRD e UX design estiverem prontos e precisar projetar a arquitetura do sistema com componentes, sequências e ADRs."
 name: Create Architecture
 phase: 3-solutioning
 owner: wize-agent-architect   # Tony Stark
-status: stub
+status: ready
 ---
 
 # Create Architecture
 
-**Goal.** Design the system inside Fury's frame. Components, sequences, data flows, ADRs. Concrete enough that Shuri can implement and Hawkeye can test.
+**Goal.** Design the system inside Fury's frame through collaborative, step-by-step discovery. Produces `.wize/solutioning/architecture.md` + `.wize/solutioning/adrs/` that multiple AI agents can implement consistently.
+
+Tony Stark drives. Pepper Potts and Nick Fury may be invoked via `wize-party-mode` or `wize-advanced-elicitation` at any step.
 
 ## Inputs
-- `.wize/planning/prd.md`
-- `.wize/planning/ux/ux-design/`
-- `.wize/planning/tech-vision.md` (Fury)
-- `.wize/planning/nfr-principles.md` (Fury)
-- `.wize/solutioning/design-system/` (Mantis)
-- `.wize/knowledge/document-project/` (if brownfield)
+
+- `.wize/planning/prd.md` (required)
+- `.wize/planning/ux/ux-scenarios.md` and `.wize/planning/ux/ux-design/` (when available)
+- `.wize/planning/tech-vision.md`
+- `.wize/planning/nfr-principles.md`
+- `.wize/solutioning/design-system/` (when available)
+- Stack catalogs from active overlays
+- `.wize/knowledge/document-project/` (brownfield only)
 
 ## Outputs
+
 - `.wize/solutioning/architecture.md`
-- `.wize/solutioning/adrs/{ADR-NNN}-{slug}.md`
+- `.wize/solutioning/adrs/ADR-NNN-{slug}.md`
+
+## Workflow architecture
+
+This skill uses **micro-file architecture**:
+
+- Each step is a self-contained file with embedded rules.
+- Sequential progression with user control at each step.
+- Document state tracked in frontmatter (`stepsCompleted`).
+- Append-only document building through the conversation.
+- Never proceed to a step file if the current step indicates the user must approve continuation.
+
+## On activation
+
+1. Load `.wize/config/project.toml` and `.wize/config/user.toml`.
+2. Resolve `user_name`, `communication_language`, `document_output_language`, `output_folder`, and the active profiles.
+3. Greet the user in `communication_language`.
+4. Read fully and follow `./steps/step-01-init.md`.
 
 ## Steps
-1. **Stack interview.** Tony asks the user (via Wizer) about preferences: language, runtime, deployment target. Consults overlay stack catalogs (web/app) if active. Records decisions.
-2. **Components.** List components, responsibilities, boundaries.
-3. **Sequences.** For each critical scenario from Mantis, write a sequence (text or PlantUML).
-4. **Data model.** Tables / collections / contracts.
-5. **Cross-cutting.** Auth, logging, observability, error handling.
-6. **ADRs.** Every significant trade-off becomes its own ADR: context, options, decision, consequences.
-7. **Validate against NFRs.** Check each Fury principle.
-8. **Hand-off to epics.**
-
-## Architecture doc template
-
-```markdown
-# Architecture — {{project_name}}
-
-## Stack
-- Language: …
-- Runtime: …
-- Storage: …
-- Deploy: …
-
-## Components
-| Component | Responsibility | Boundary |
-|---|---|---|
-
-## Data model
-…
-
-## Cross-cutting
-- Auth: …
-- Observability: …
-- Errors: …
-
-## NFR check
-- Performance: …
-- Security: …
-- Reliability: …
-- Accessibility: …
-- Cost: …
-```
+
+1. `step-01-init.md` — detect continuation, discover inputs, create `architecture.md` from template.
+2. `step-02-context.md` — analyze PRD, UX, and research for architectural implications.
+3. `step-03-starter.md` — discover technical preferences and evaluate starter templates.
+4. `step-04-decisions.md` — make core architectural decisions (data, auth, API, frontend, infra).
+5. `step-05-patterns.md` — define implementation patterns that prevent agent conflicts.
+6. `step-06-structure.md` — map requirements to concrete project structure and boundaries.
+7. `step-07-validation.md` — validate coherence, coverage, and implementation readiness.
+8. `step-08-complete.md` — finalize frontmatter and hand off to implementation.
+
+## Global step rules
+
+- Always read the complete step file before acting.
+- Speak in `communication_language`.
+- Write artifacts in `document_output_language`.
+- Never generate content without user input or confirmation.
+- Every code reference uses CWD-relative `path:line` format.
+- No time estimates — AI development speed has fundamentally changed.
+
+## Hand-off
+
+> Architecture and ADRs are in `.wize/solutioning/`. Sequences hit the NFR targets. Hawkeye can write `tea-risk.md` against this. Tony continues with `wize-create-epics-and-stories`.