@uoyo/mvtt 2.0.0-beta.0

package/sources/skills/mvt-review/business.md

@@ -0,0 +1,49 @@
+## Execution Flow
+
+### Step 1: Identify Review Target
+- Latest implementation files from current change
+- Files specified by user
+- Files in current change artifacts
+
+### Step 2: Load Context
+- Read target files
+- Read project-context for architecture expectations
+- Load review checklist for active pattern (if available)
+
+### Step 3: Analyze Code
+- Check architecture compliance (layer assignments, dependencies)
+- Check code quality (functions small/focused, naming, duplication)
+- Check error handling
+- Check edge cases
+- Check readability
+- If `--aspect` specified -> Focus on that aspect
+
+### Step 4: Categorize Issues
+Classify each finding by severity:
+
+| Level | Description | Action Required |
+|-------|-------------|-----------------|
+| **Critical** | Bugs, security issues, breaks functionality | Must fix before merge |
+| **Warning** | Code quality issues, potential bugs | Should fix |
+| **Suggestion** | Improvements, best practices | Nice to have |
+
+### Step 5: Update Workspace
+1. Update `.ai-agents/workspace/session.yaml`:
+   - Set `progress.review: done`
+   - Set `session.last_command: "/mvt-review"`
+   - Append one-line summary to `recent_actions` (keep max 3)
+2. Write artifact: `.ai-agents/workspace/artifacts/{change-id}/review.md`
+
+## Review Checklist
+
+### Architecture Compliance
+- [ ] Follows established architecture pattern
+- [ ] Correct layer assignment
+- [ ] Proper dependency direction
+- [ ] Module boundaries respected
+
+### Code Quality
+- [ ] Functions are small and focused
+- [ ] Naming is clear and consistent
+- [ ] No code duplication
+- [ ] Proper error handling

package/sources/skills/mvt-review/manifest.yaml

@@ -0,0 +1,106 @@
+name: mvt-review
+output: .claude/skills/mvt-review/SKILL.md
+
+frontmatter:
+  name: mvt-review
+  description: "Perform code review for quality, standards compliance, and best practices. Identifies issues by severity and suggests improvements. Use when user wants code reviewed or quality checked."
+
+sections:
+  - type: inline
+    content: |
+      # MVT Review
+
+      ## Purpose
+
+      Review code for quality, standards compliance, and best practices. Identify issues by severity, suggest improvements, and ensure architecture compliance. This is the fourth phase in the full workflow: analyze -> design -> implement -> review -> test.
+
+  - type: shared
+    source: sections/role-header.md
+    params:
+      role: Reviewer
+      role_desc: "a Code Quality Guardian"
+      decision_rules:
+        - rule: "Critical issue found (security, data loss, crash) -> Mark as CRITICAL, require fix before merge"
+        - rule: "Architecture violation found -> Flag for Architect, suggest `/mvt-design`"
+        - rule: "Minor style issue -> Note as suggestion, don't block"
+        - rule: "Subjective preference -> Mark as \"non-blocking\" optional improvement"
+        - rule: "Good code pattern found -> Highlight positively"
+        - rule: "Bug found -> Document with reproduction steps, suggest `/mvt-fix`"
+        - rule: "Insufficient test coverage -> Recommend specific scenarios, suggest `/mvt-test`"
+      boundaries:
+        - scope: "fix code directly"
+          skill: "/mvt-fix"
+        - scope: "make architecture decisions"
+          skill: "/mvt-design"
+        - scope: "modify source code"
+          skill: "(This is a read-only review)"
+
+  - type: inline
+    content: |
+      ## Aspect Options
+
+      | Aspect | Focus Areas |
+      |--------|-------------|
+      | `architecture` | Pattern compliance, module boundaries, dependency direction |
+      | `security` | Input validation, injection prevention, authentication |
+      | `performance` | N+1 queries, memory leaks, caching |
+      | `style` | Naming conventions, formatting, documentation |
+
+      Usage: `/mvt-review` or `/mvt-review --aspect {type}`
+
+  - type: shared
+    source: sections/activation-load-context.md
+    params:
+      extended_context:
+        - ".ai-agents/knowledge/core/review-principles.md -- Universal review principles"
+        - ".ai-agents/knowledge/principle/coding-standards.md -- Project coding standards"
+        - ".ai-agents/knowledge/patterns/{pattern.active}/review-checklist.md -- Pattern-specific checklist"
+
+  - type: shared
+    source: sections/activation-load-config.md
+
+  - type: shared
+    source: sections/activation-preflight.md
+    params:
+      checks:
+        - order: "1"
+          field: "session.initialized_at"
+          level: "WARN"
+          message: 'Session not initialized. Run `/mvt-init` first.'
+        - order: "2"
+          field: "no code to review"
+          level: "WARN"
+          message: 'No code to review. Run `/mvt-implement` first or specify files.'
+        - order: "3"
+          field: "pattern.active"
+          level: "WARN"
+          message: 'Architecture pattern not set. Suggest `/mvt-init`." (allow user to proceed)'
+
+  - type: inline
+    content: |
+      ### Step 4: Execute
+      Proceed to Execution Flow below.
+
+  - type: file
+    source: ./business.md
+
+  - type: inline
+    content: |
+      ## Output Format
+
+      Read and use the output template from: `.ai-agents/skills/_templates/review-output.md`
+
+      If a custom version exists at `.ai-agents/skills/_templates/custom/review-output.md`, use the custom version instead.
+
+      Fill the template placeholders with the review results.
+
+      Every response MUST end with a Suggested Next Steps section.
+
+  - type: shared
+    source: sections/footer-next-steps.md
+    params:
+      next_primary: mvt-fix
+      next_primary_desc: "Address critical issues"
+      next_alternatives:
+        - skill: mvt-test
+          when: "Add missing tests"

package/sources/skills/mvt-status/business.md

@@ -0,0 +1,24 @@
+## Execution Flow
+
+### Step 1: Load State
+- Read `session.yaml` for progress, active change, recent actions
+- Read `project-context.yaml` for project info, tech stack, architecture
+
+### Step 2: Determine Current Phase
+- Check `progress` fields (analyze, design, implement, review, test)
+- Identify which phases are `done`, `pending`, or `in-progress`
+- Determine the current active phase
+
+### Step 3: Build Workflow Visualization
+- Generate Mermaid flowchart showing phase progression
+- Color-code phases: green (done), yellow (current), gray (pending)
+
+### Step 4: Compile Status Report
+- Project info summary
+- Progress table with phase status
+- Active change details (if any)
+- Recent actions history
+
+### Step 5: Suggest Next Step
+- Based on current progress, recommend the logical next command
+- If all phases done -> Suggest `/mvt-cleanup` or starting a new feature

package/sources/skills/mvt-status/manifest.yaml

@@ -0,0 +1,74 @@
+name: mvt-status
+output: .claude/skills/mvt-status/SKILL.md
+
+frontmatter:
+  name: mvt-status
+  description: "Show current project and workflow status including progress through phases, active changes, and session state. Use when user wants to check project status or see where they are in the workflow."
+
+sections:
+  - type: inline
+    content: |
+      # MVT Status
+
+      ## Purpose
+
+      Display comprehensive project and workflow status, showing progress through development phases, active changes, and current session state.
+
+  - type: shared
+    source: sections/role-header.md
+    params:
+      role: Conductor
+      role_desc: "a Workflow Coordinator"
+      decision_rules:
+        - rule: "If project not initialized -> Warn and suggest `/mvt-init`"
+        - rule: "If no active change -> Show project info only, suggest starting a workflow"
+        - rule: "If workflow in progress -> Highlight current phase and next recommended step"
+      boundaries:
+        - scope: "analyze requirements"
+          skill: "/mvt-analyze"
+        - scope: "design architecture"
+          skill: "/mvt-design"
+        - scope: "write implementation code"
+          skill: "/mvt-implement"
+
+  - type: shared
+    source: sections/activation-load-context.md
+
+  - type: shared
+    source: sections/activation-load-config.md
+
+  - type: shared
+    source: sections/activation-preflight.md
+    params:
+      checks:
+        - order: "1"
+          field: "session.initialized_at"
+          level: "WARN"
+          message: 'Session not initialized. Run `/mvt-init` first.'
+        - order: "2"
+          field: "project.name"
+          level: "WARN"
+          message: 'Project not initialized. Run `/mvt-init` first.'
+
+  - type: inline
+    content: |
+      ### Step 4: Execute
+      Proceed to Execution Flow below.
+
+  - type: file
+    source: ./business.md
+
+  - type: inline
+    content: |
+      ## Output Format
+
+      Read and use the output template from: `.ai-agents/skills/_templates/status-output.md`
+
+      If a custom version exists at `.ai-agents/skills/_templates/custom/status-output.md`, use the custom version instead.
+
+      Fill the template placeholders with the current state data.
+
+      Every response MUST end with a Suggested Next Steps section.
+
+      ## Suggested Next Steps
+      After completion, suggest the logical next workflow step based on current progress.

package/sources/skills/mvt-sync-context/business.md

@@ -0,0 +1,25 @@
+## Execution Flow
+
+### Step 1: Detect Changes
+- If git available:
+  - Run `git diff --name-only` (unstaged changes)
+  - Run `git diff --name-only --cached` (staged changes)
+  - Run `git diff --name-only HEAD~1` (last commit changes)
+  - Merge results and deduplicate
+- If git not available:
+  - Scan for recently modified files in source directories
+
+### Step 2: Analyze Changed Files
+- Read each changed file
+- Extract entities (classes, models, types)
+- Extract services (service classes, API handlers)
+- Extract keywords and topics
+
+### Step 3: Update Workspace
+1. Update `.ai-agents/workspace/project-context.yaml`:
+   - Add new entities to architecture section
+   - Add new services
+   - Update module mappings
+2. Update `.ai-agents/workspace/session.yaml`:
+   - Set `session.last_command: "/mvt-sync-context"`
+   - Append one-line summary to `recent_actions` (keep max 3)

package/sources/skills/mvt-sync-context/manifest.yaml

@@ -0,0 +1,84 @@
+name: mvt-sync-context
+output: .claude/skills/mvt-sync-context/SKILL.md
+
+frontmatter:
+  name: mvt-sync-context
+  description: "Synchronize workspace context with code changes after manual modifications or git operations. Use when context seems out of sync with code, after manual edits, or after git merge/rebase."
+
+sections:
+  - type: inline
+    content: |
+      # MVT Sync Context
+
+      ## Purpose
+
+      Synchronize the MVTT workspace context with code changes made outside the workflow. This is a code-driven, automatic synchronization that scans git diffs and file changes to update project context.
+
+  - type: shared
+    source: sections/role-header.md
+    params:
+      role: Conductor
+      role_desc: "a Workflow Coordinator"
+      decision_rules:
+        - rule: "Git available -> Use git diff to detect changes"
+        - rule: "Git not available -> Scan for recently modified files"
+        - rule: "Changes detected -> Analyze and update context"
+        - rule: "No changes detected -> Report context is already in sync"
+      boundaries:
+        - scope: "analyze requirements"
+          skill: "/mvt-analyze"
+        - scope: "design architecture"
+          skill: "/mvt-design"
+        - scope: "write implementation code"
+          skill: "/mvt-implement"
+
+  - type: inline
+    content: |
+      ### When to Use
+      - After manual code changes outside the workflow
+      - When context seems out of sync with code
+      - After git operations (merge, rebase, etc.)
+
+  - type: shared
+    source: sections/activation-load-context.md
+
+  - type: shared
+    source: sections/activation-load-config.md
+
+  - type: shared
+    source: sections/activation-preflight.md
+    params:
+      checks:
+        - order: "1"
+          field: "project-context is empty"
+          level: "WARN"
+          message: 'Project not initialized. Run `/mvt-init` first.'
+
+  - type: inline
+    content: |
+      ### Step 4: Execute
+      Proceed to Execution Flow below.
+
+  - type: file
+    source: ./business.md
+
+  - type: inline
+    content: |
+      ## Output Format
+
+      Read and use the output template from: `.ai-agents/skills/_templates/sync-context-output.md`
+
+      If a custom version exists at `.ai-agents/skills/_templates/custom/sync-context-output.md`, use the custom version instead.
+
+      Fill the template placeholders with the sync results.
+
+      Every response MUST end with a Suggested Next Steps section.
+
+  - type: shared
+    source: sections/footer-next-steps.md
+    params:
+      next_primary: mvt-status
+      next_primary_desc: "Verify context state after sync"
+      next_alternatives:
+        - skill: "(continue)"
+          when: "Continue with your current task"

package/sources/skills/mvt-template/business.md

@@ -0,0 +1,49 @@
+## Execution Flow
+
+### Step 1: Load Template Inventory
+- Read registry to get all registered templates
+- Scan `custom/` directory for existing custom versions
+- Build status list: default / customized for each template
+
+### Step 2: Display Template List
+Show all templates with their status:
+
+```markdown
+## Output Templates
+
+| # | Template | Skill | Status |
+|---|---------|-------|--------|
+| 1 | analyze-output.md | mvt-analyze | Default |
+| 2 | design-output.md | mvt-design | Customized |
+| ... | ... | ... | ... |
+
+**Actions**: `view {#}`, `customize {#}`, `reset {#}`, `export {#}`
+```
+
+### Step 3: Execute Action (based on user choice)
+
+**View**:
+- Display full template content
+- If custom version exists, show that; otherwise show default
+- Indicate which version is being shown
+
+**Customize**:
+1. Show current default template
+2. Ask user to describe desired modifications
+3. Generate new template based on modifications
+4. Preview the customized template
+5. Save to `custom/{template-name}` after user confirmation
+6. Custom template must retain frontmatter (`id`, `version`, `skill`)
+
+**Reset**:
+1. Confirm user wants to reset to default
+2. Delete the custom version from `custom/`
+3. Confirm reset complete
+
+**Export**:
+- Output template content to user-specified location
+- Or display in a code block for manual copy
+
+### Step 4: Confirmation
+- Show result of the action taken
+- Confirm files modified

package/sources/skills/mvt-template/manifest.yaml

@@ -0,0 +1,71 @@
+name: mvt-template
+output: .claude/skills/mvt-template/SKILL.md
+
+frontmatter:
+  name: mvt-template
+  description: "View, customize, and manage output templates for MVTT skills. Use when user wants to see available templates, create custom template versions, reset to defaults, or export templates."
+
+sections:
+  - type: inline
+    content: |
+      # MVT Custom Template
+
+      ## Purpose
+
+      Provide an interactive tool for viewing, customizing, and managing MVTT output templates. Users can inspect default templates, create custom versions that override defaults, reset customizations, and export templates.
+
+  - type: shared
+    source: sections/role-header.md
+    params:
+      role: Conductor
+      role_desc: "a Workflow Coordinator"
+      decision_rules:
+        - rule: "No arguments -> Show template list with status"
+        - rule: "User selects \"view\" -> Display full template content (custom version if exists)"
+        - rule: "User selects \"customize\" -> Guide through modification process"
+        - rule: "User selects \"reset\" -> Delete custom version, restore default"
+        - rule: "User selects \"export\" -> Output template to specified location"
+        - rule: "Custom template must preserve frontmatter format"
+      boundaries:
+        - scope: "modify default templates in `_templates/` root"
+          skill: "(Only create/modify in `custom/`)"
+        - scope: "modify skill logic"
+          skill: "(Only change output formatting)"
+
+  - type: shared
+    source: sections/activation-load-context.md
+    params:
+      extended_context:
+        - ".ai-agents/registry.yaml -- Template registry"
+        - "Scan `.ai-agents/skills/_templates/custom/` for existing customizations"
+
+  - type: shared
+    source: sections/activation-load-config.md
+
+  - type: inline
+    content: |
+      ### Step 3: Pre-flight Checks
+      - No blocking checks required.
+
+      ### Step 4: Execute
+      Proceed to Execution Flow below.
+
+  - type: file
+    source: ./business.md
+
+  - type: inline
+    content: |
+      ## Output Format
+
+      No external template -- output is inline based on the action:
+
+      ```markdown
+      ## Template Manager
+
+      {Action-specific content}
+
+      ---
+      **Suggested Next Steps**:
+      - `/mvt-template` -- Manage more templates
+      - `/mvt-help` -- View all available skills
+      ```

package/sources/skills/mvt-test/business.md

@@ -0,0 +1,36 @@
+## Execution Flow
+
+### Step 1: Load Context
+- Read implementation files
+- Read project-context for tech stack and test framework
+- Identify test framework conventions
+
+### Step 2: Analyze Test Scenarios
+- Identify happy path scenarios
+- Identify edge cases and boundary conditions
+- Identify error scenarios
+- Identify security test cases (if applicable)
+
+### Step 3: Design Test Cases
+- Create test case table with IDs, scenarios, inputs, expected outputs
+- Define preconditions for each test
+- Prioritize by type (happy path and edge cases first)
+
+### Step 4: Write Test Code
+- Follow project's test framework conventions
+- Write clear, descriptive test names
+- Include setup, action, and assertion sections
+- Use mocks/stubs for external dependencies
+
+### Step 5: Coverage Analysis (with --coverage)
+- Map test cases to requirements
+- Identify coverage gaps
+- Recommend additional tests for missing coverage
+
+### Step 6: Update Workspace
+1. Update `.ai-agents/workspace/session.yaml`:
+   - Set `progress.test: done`
+   - Set `session.last_command: "/mvt-test"`
+   - Append one-line summary to `recent_actions` (keep max 3)
+2. Write test files to the project
+3. Write artifact: `.ai-agents/workspace/artifacts/{change-id}/tests/`

package/sources/skills/mvt-test/manifest.yaml

@@ -0,0 +1,111 @@
+name: mvt-test
+output: .claude/skills/mvt-test/SKILL.md
+
+frontmatter:
+  name: mvt-test
+  description: "Generate and design tests to validate implementations. Creates test cases covering happy paths, edge cases, negative scenarios, and security. Use when user wants to write tests or validate code."
+
+sections:
+  - type: inline
+    content: |
+      # MVT Test
+
+      ## Purpose
+
+      Design and write tests to validate implementations against requirements. Ensure code works correctly with comprehensive coverage of happy paths, edge cases, and error scenarios. This is the fifth phase in the full workflow: analyze -> design -> implement -> review -> test.
+
+  - type: shared
+    source: sections/role-header.md
+    params:
+      role: Tester
+      role_desc: "a Quality Assurance Specialist"
+      decision_rules:
+        - rule: "Happy path works -> Add edge case and boundary tests"
+        - rule: "Bug found during testing -> Document with reproduction steps, suggest `/mvt-fix`"
+        - rule: "Coverage gap found -> Add tests focused on that area"
+        - rule: "Flaky test detected -> Flag for investigation"
+        - rule: "Test requires external service -> Use mocks/stubs, document the dependency"
+        - rule: "Security constraints in requirements -> Add security-focused test cases"
+        - rule: "Existing tests conflict with new implementation -> Flag the conflict"
+      boundaries:
+        - scope: "modify the code being tested"
+          skill: "/mvt-fix"
+        - scope: "make architecture decisions"
+          skill: "(Test against existing design)"
+        - scope: "skip edge cases or negative tests"
+          skill: "(Never)"
+
+  - type: inline
+    content: |
+      ## Variants
+
+      | Variant | Description |
+      |---------|-------------|
+      | `/mvt-test` | Generate tests for recent implementation |
+      | `/mvt-test {feature}` | Generate tests for specific feature |
+      | `/mvt-test --coverage` | Generate tests with coverage analysis |
+
+  - type: shared
+    source: sections/activation-load-context.md
+    params:
+      extended_context:
+        - ".ai-agents/knowledge/core/review-principles.md -- Code quality principles"
+        - ".ai-agents/knowledge/patterns/{pattern.active}/ -- Active pattern knowledge"
+        - ".ai-agents/knowledge/principle/coding-standards.md -- Project coding standards"
+        - "Implementation files to be tested"
+
+  - type: shared
+    source: sections/activation-load-config.md
+
+  - type: shared
+    source: sections/activation-preflight.md
+    params:
+      checks:
+        - order: "1"
+          field: "session.initialized_at"
+          level: "WARN"
+          message: 'Session not initialized. Run `/mvt-init` first.'
+        - order: "2"
+          field: "no implementation files"
+          level: "WARN"
+          message: 'No implementation found. Run `/mvt-implement` first.'
+        - order: "3"
+          field: "pattern.active"
+          level: "WARN"
+          message: 'Architecture pattern not set. Suggest `/mvt-init`." (allow user to proceed)'
+
+  - type: inline
+    content: |
+      ### Step 4: Execute
+      Proceed to Execution Flow below.
+
+      ## Test Case Types
+
+      | Type | Description | Priority |
+      |------|-------------|----------|
+      | Happy Path | Normal successful flow | High |
+      | Edge Case | Boundary conditions | High |
+      | Negative | Invalid inputs, errors | High |
+      | Security | Authentication, injection | Medium |
+      | Performance | Load, stress | Low |
+
+  - type: file
+    source: ./business.md
+
+  - type: inline
+    content: |
+      ## Output Format
+
+      Read and use the output template from: `.ai-agents/skills/_templates/test-output.md`
+
+      If a custom version exists at `.ai-agents/skills/_templates/custom/test-output.md`, use the custom version instead.
+
+      Fill the template placeholders with the test design results.
+
+      Every response MUST end with a Suggested Next Steps section.
+
+  - type: shared
+    source: sections/footer-next-steps.md
+    params:
+      next_primary: mvt-fix
+      next_primary_desc: "Run tests with the appropriate command; if tests fail, use this"

package/sources/templates/analyze-code-output/body.md

@@ -0,0 +1,44 @@
+## Codebase Analysis Report
+
+### Project: {name}
+- **Root**: `{root_path}`
+- **Primary Language**: {language}
+- **Detected Framework**: {framework}
+
+### Architecture Discovery
+
+#### Module Structure
+| Module | Path | Responsibility | Type |
+|--------|------|----------------|------|
+| {module} | `{path}` | {description} | {Domain/Application/Infrastructure/Interface} |
+
+#### Entity Inventory
+| Entity | Location | Relationships |
+|--------|----------|---------------|
+| {entity} | `{file}` | {related_entities} |
+
+#### Service Inventory
+| Service | Location | Dependencies | Methods |
+|---------|----------|--------------|---------|
+| {service} | `{file}` | {deps} | {methods} |
+
+### Dependency Analysis
+```mermaid
+graph TD
+    A[Module A] --> B[Module B]
+    B --> C[Module C]
+```
+
+### Key Findings
+| # | Finding | Type | Severity |
+|---|---------|------|----------|
+| 1 | {finding} | {architecture/code-quality/dependency} | {info/warning/concern} |
+
+### Workspace Updated
+- [x] project-context.yaml updated with discovered structure
+- [x] session.yaml updated
+
+---
+**Suggested Next Steps**:
+- `/mvt-analyze {requirements}` to add requirements on top of discovered structure
+- `/mvt-design` to design new features for existing architecture