specweave 0.1.8 → 0.3.0

package/src/skills/cost-optimizer/test-cases/test-1-basic-comparison.yaml

@@ -1,75 +0,0 @@
----
-name: "Basic Platform Cost Comparison"
-description: "Compare platforms for small NextJS SaaS with 1000 users"
-skill: cost-optimizer
-priority: P1
-estimated_time: "2-3 minutes"
-
-input:
-  prompt: "What's the cheapest way to host my NextJS SaaS with Postgres for 1000 users?"
-  requirements:
-    app_type: nextjs
-    users: 1000
-    database: postgres
-    database_size: 2GB
-    storage: 20GB
-    traffic: "10k requests/day"
-
-expected_output:
-  platforms_compared:
-    - hetzner
-    - vercel
-    - aws
-    - railway
-    - fly_io
-    - digitalocean
-
-  recommendation:
-    platform: hetzner
-    monthly_cost: "$11-12"
-    confidence: "high"
-
-  cost_breakdown:
-    hetzner:
-      server: "$5.83"
-      database: "$5.00"
-      storage: "$0.50"
-      total: "$11.33"
-
-    vercel:
-      hosting: "$0 (hobby) or $60 (production)"
-      database: "$0 (planetscale hobby) or $39 (scaler)"
-      total: "$0 or $60-99"
-
-    aws:
-      ec2: "$10"
-      rds: "$15"
-      total: "$25"
-
-  savings_vs_alternatives:
-    vs_vercel: "$48.67/month (production)"
-    vs_aws: "$13.67/month"
-    annual_savings: "$584/year (vs Vercel)"
-
-  rationale:
-    pros:
-      - "Lowest cost"
-      - "Predictable pricing"
-      - "Managed database included"
-
-    cons:
-      - "EU-only"
-      - "No auto-scaling"
-
-validation:
-  - "Hetzner recommended for budget scenario"
-  - "Cost under $15/month"
-  - "At least 3 platforms compared"
-  - "Savings calculation accurate"
-  - "Pros and cons listed"
-
-success_criteria:
-  - "Recommendation matches requirements"
-  - "Cost estimate accurate within 10%"
-  - "Clear rationale provided"
----

package/src/skills/cost-optimizer/test-cases/test-2-budget-constraint.yaml

@@ -1,52 +0,0 @@
----
-name: "Budget Constraint Optimization"
-description: "Find platform that stays under $20/month budget"
-skill: cost-optimizer
-priority: P1
-
-input:
-  prompt: "I need to deploy my app with database, budget is max $20/month"
-  requirements:
-    budget_max: "$20/month"
-    app_type: fullstack
-    database: postgres
-    users: 2000
-    strict_budget: true
-
-expected_output:
-  recommendation:
-    platform: hetzner
-    monthly_cost: "$11.33"
-    within_budget: true
-    headroom: "$8.67"
-
-  alternatives_within_budget:
-    - platform: digitalocean
-      cost: "$18"
-      within_budget: true
-
-    - platform: railway
-      cost: "$20"
-      within_budget: true
-
-  excluded_platforms:
-    - platform: vercel_production
-      cost: "$60+"
-      reason: "Exceeds budget"
-
-  budget_analysis:
-    recommended_cost: "$11.33"
-    budget_limit: "$20"
-    utilization: "56.6%"
-    savings: "$8.67/month buffer"
-
-validation:
-  - "Recommendation under $20/month"
-  - "All alternatives under budget"
-  - "Excluded expensive options"
-  - "Budget utilization calculated"
-
-success_criteria:
-  - "Stays within budget"
-  - "Maximizes value for budget"
----

package/src/skills/cost-optimizer/test-cases/test-3-scale-requirement.yaml

@@ -1,63 +0,0 @@
----
-name: "Scale Requirement - 10k Users"
-description: "Recommend platform for scaling to 10,000 users"
-skill: cost-optimizer
-priority: P2
-
-input:
-  prompt: "I need to host my SaaS for 10,000 users with high availability"
-  requirements:
-    users: 10000
-    traffic: "100k requests/day"
-    database: postgres
-    database_size: 8GB
-    high_availability: true
-    global_audience: false
-
-expected_output:
-  recommendation:
-    platform: hetzner
-    instance: cx21_or_cx31
-    monthly_cost: "$18-36"
-
-  cost_breakdown:
-    hetzner_cx21:
-      server: "$6.90"
-      database_8gb: "$20"
-      total: "$26.90"
-
-    hetzner_cx31:
-      server: "$14.28"
-      database_8gb: "$20"
-      total: "$34.28"
-
-  alternatives:
-    aws:
-      ec2_t3_medium: "$35"
-      rds_8gb: "$45"
-      total: "$80"
-
-    vercel:
-      pro_plan: "$120"
-
-  recommendation_rationale:
-    - "CX21 handles 10k users efficiently"
-    - "Can upgrade to CX31 if needed"
-    - "$53/month savings vs AWS"
-    - "$93/month savings vs Vercel"
-
-  scaling_path:
-    current: "CX21 ($27/mo)"
-    if_growth: "CX31 ($34/mo)"
-    enterprise: "Multiple instances + load balancer ($60/mo)"
-
-validation:
-  - "Handles 10k users"
-  - "High availability considered"
-  - "Scaling path provided"
-  - "Cost competitive"
-
-success_criteria:
-  - "Can handle stated scale"
-  - "Recommendation appropriate for load"
----

package/src/skills/cost-optimizer/test-results/README.md

@@ -1,46 +0,0 @@
-# Test Results: cost-optimizer
-
-## How to Run Tests
-
-### Test 1: Basic Comparison
-**Prompt**: "What's the cheapest way to host my NextJS SaaS with Postgres for 1000 users?"
-
-**Expected**: Hetzner recommended at ~$11/month
-
-**Verification**:
-- [ ] Hetzner recommended
-- [ ] Cost under $15/month
-- [ ] At least 3 platforms compared
-- [ ] Savings shown vs alternatives
-
-### Test 2: Budget Constraint
-**Prompt**: "I need to deploy my app with database, budget is max $20/month"
-
-**Expected**: Recommendation stays under $20
-
-**Verification**:
-- [ ] Recommended cost < $20
-- [ ] Budget utilization shown
-- [ ] Expensive options excluded
-
-### Test 3: Scale Requirement
-**Prompt**: "I need to host my SaaS for 10,000 users with high availability"
-
-**Expected**: Hetzner CX21/CX31 recommended at $27-34/month
-
-**Verification**:
-- [ ] Handles 10k users
-- [ ] Scaling path provided
-- [ ] Cost competitive with alternatives
-
-## Test Execution
-
-**Status**: ⏳ Pending
-
-Mark tests as ✅ Passed or ❌ Failed after execution.
-
-## Success Criteria
-
-✅ All 3 tests recommend appropriate platform
-✅ Cost estimates accurate within 10%
-✅ Savings calculations correct

package/src/skills/design-system-architect/test-cases/test-1-token-structure.yaml

@@ -1,23 +0,0 @@
----
-name: "Token Structure Validation"
-description: "Test validation of design token structure"
-input:
-  tokens:
-    colors:
-      primary:
-        500: "#3b82f6"
-    typography:
-      heading1:
-        fontSize: "2.25rem"
-expected_output:
-  type: "validation_result"
-  valid: true
-  issues: []
-validation:
-  - "Naming convention followed"
-  - "All required categories present"
-  - "Values in correct format"
-success_criteria:
-  - "Validation passes"
-  - "No issues reported"
----

package/src/skills/design-system-architect/test-cases/test-2-component-hierarchy.yaml

@@ -1,24 +0,0 @@
----
-name: "Component Hierarchy Validation"
-description: "Test validation of Atomic Design hierarchy"
-input:
-  components:
-    atoms:
-      - "Button"
-      - "Input"
-    molecules:
-      - "FormField"
-    organisms:
-      - "Navigation"
-expected_output:
-  type: "validation_result"
-  valid: true
-  hierarchy_correct: true
-validation:
-  - "Atoms are smallest components"
-  - "Molecules compose atoms"
-  - "Organisms compose molecules/atoms"
-success_criteria:
-  - "Hierarchy follows Atomic Design"
-  - "No circular dependencies"
----

package/src/skills/design-system-architect/test-cases/test-3-accessibility-checklist.yaml

@@ -1,23 +0,0 @@
----
-name: "Accessibility Checklist Validation"
-description: "Test validation of accessibility requirements"
-input:
-  component: "Button"
-  accessibility:
-    aria_label: true
-    keyboard_navigation: true
-    color_contrast: 4.6
-    touch_target: "44x44"
-expected_output:
-  type: "validation_result"
-  valid: true
-  wcag_compliant: true
-validation:
-  - "ARIA labels present"
-  - "Keyboard navigation supported"
-  - "Color contrast >= 4.5:1"
-  - "Touch targets >= 44x44px"
-success_criteria:
-  - "WCAG 2.1 AA compliance"
-  - "No accessibility violations"
----

package/src/skills/diagrams-architect/test-cases/test-1-c4-context.yaml

@@ -1,13 +0,0 @@
-name: "Create C4 Context Diagram"
-description: "Test creating a C4 Level 1 context diagram for a system"
-user_input: "Create a C4 context diagram for an e-commerce platform"
-expected_behavior:
-  - Generates valid Mermaid C4Context diagram
-  - Includes system boundary
-  - Shows external actors (users, external systems)
-  - Shows relationships and dependencies
-validation:
-  - Diagram starts with C4Context keyword
-  - Contains Person/System elements
-  - Includes Boundary definition
-  - Has BiRel or Rel relationship arrows

package/src/skills/diagrams-architect/test-cases/test-2-sequence-diagram.yaml

@@ -1,13 +0,0 @@
-name: "Create Sequence Diagram"
-description: "Test creating a sequence diagram for API authentication flow"
-user_input: "Create a sequence diagram for OAuth 2.0 authentication flow"
-expected_behavior:
-  - Generates valid Mermaid sequence diagram
-  - Shows participants (client, auth server, resource server)
-  - Includes authentication steps in correct order
-  - Shows token exchange flow
-validation:
-  - Diagram starts with sequenceDiagram keyword
-  - Contains participant declarations
-  - Has sequential messages (->>, -->)
-  - Includes notes for clarity

package/src/skills/diagrams-architect/test-cases/test-3-er-diagram.yaml

@@ -1,13 +0,0 @@
-name: "Create Entity Relationship Diagram"
-description: "Test creating an ER diagram for database schema"
-user_input: "Create an ER diagram for a multi-tenant SaaS database"
-expected_behavior:
-  - Generates valid Mermaid ER diagram
-  - Shows entities (tables)
-  - Shows relationships with cardinality
-  - Includes key attributes
-validation:
-  - Diagram starts with erDiagram keyword
-  - Contains entity definitions
-  - Has relationships (||--o{, etc.)
-  - Shows primary/foreign key fields

package/src/skills/diagrams-generator/test-cases/test-1.yaml

@@ -1,9 +0,0 @@
----
-name: "Detect Diagram Request"
-description: "Tests if diagrams-generator activates for diagram creation"
-input:
-  prompt: "Create C4 context diagram"
-expected_output:
-  skill_activated: true
-  agent_invoked: "diagrams-architect"
----

package/src/skills/diagrams-generator/test-cases/test-2.yaml

@@ -1,9 +0,0 @@
----
-name: "Detect C4 Level 3 (LLD)"
-description: "Tests if diagrams-generator correctly identifies LLD component diagrams"
-input:
-  prompt: "Create component diagram for Auth Service"
-expected_output:
-  diagram_type: "C4Component"
-  document_type: "LLD"
----

package/src/skills/diagrams-generator/test-cases/test-3.yaml

@@ -1,8 +0,0 @@
----
-name: "Save to Correct Location"
-description: "Tests if diagrams are saved to correct paths (HLD vs LLD)"
-input:
-  prompt: "Create component diagram for Payment Service"
-expected_output:
-  file_location: ".specweave/docs/internal/architecture/diagrams/payments/component-payment-service.mmd"
----

package/src/skills/docs-updater/test-cases/test-1-placeholder.yaml

@@ -1,12 +0,0 @@
----
-name: "Placeholder Test"
-description: "TODO: Add actual test case for this skill"
-input:
-  prompt: "Test prompt"
-expected_output:
-  type: "validation"
-validation:
-  - "Placeholder validation"
-success_criteria:
-  - "Test passes"
----

package/src/skills/docs-updater/test-cases/test-2-placeholder.yaml

@@ -1,12 +0,0 @@
----
-name: "Placeholder Test"
-description: "TODO: Add actual test case for this skill"
-input:
-  prompt: "Test prompt"
-expected_output:
-  type: "validation"
-validation:
-  - "Placeholder validation"
-success_criteria:
-  - "Test passes"
----

package/src/skills/docs-updater/test-cases/test-3-placeholder.yaml

@@ -1,12 +0,0 @@
----
-name: "Placeholder Test"
-description: "TODO: Add actual test case for this skill"
-input:
-  prompt: "Test prompt"
-expected_output:
-  type: "validation"
-validation:
-  - "Placeholder validation"
-success_criteria:
-  - "Test passes"
----

package/src/skills/dotnet-backend/test-cases/test-1-rest-api.yaml

@@ -1,14 +0,0 @@
-name: "Create ASP.NET Core REST API"
-description: "Test creating a REST API controller with Entity Framework"
-user_input: "Create a REST API for managing products with CRUD operations"
-expected_behavior:
-  - Generates ASP.NET Core controller with appropriate attributes
-  - Includes Entity Framework DbContext integration
-  - Implements CRUD endpoints (GET, POST, PUT, DELETE)
-  - Includes async/await pattern
-  - Adds proper HTTP status codes
-validation:
-  - Uses [ApiController] and [Route] attributes
-  - Controller inherits from ControllerBase
-  - Methods use async Task<ActionResult> pattern
-  - Includes dependency injection for DbContext

package/src/skills/dotnet-backend/test-cases/test-2-authentication.yaml

@@ -1,13 +0,0 @@
-name: "Implement JWT Authentication"
-description: "Test implementing JWT authentication in ASP.NET Core"
-user_input: "Add JWT token-based authentication to my API"
-expected_behavior:
-  - Configures JWT authentication in Program.cs/Startup.cs
-  - Creates login endpoint that generates JWT tokens
-  - Includes claims-based authorization
-  - Protects endpoints with [Authorize] attribute
-validation:
-  - Uses Microsoft.AspNetCore.Authentication.JwtBearer
-  - Configures token validation parameters
-  - Generates tokens with claims
-  - Implements token refresh logic

package/src/skills/dotnet-backend/test-cases/test-3-minimal-api.yaml

@@ -1,13 +0,0 @@
-name: "Create Minimal API"
-description: "Test creating .NET 6+ minimal API endpoints"
-user_input: "Create a minimal API for user management"
-expected_behavior:
-  - Uses app.MapGet/MapPost/MapPut/MapDelete
-  - Implements endpoints in Program.cs
-  - Includes route parameters and query strings
-  - Uses dependency injection
-validation:
-  - No controller classes needed
-  - Uses lambda expressions for endpoints
-  - Implements proper HTTP verbs
-  - Includes validation and error handling

package/src/skills/e2e-playwright/test-cases/TC-001-basic-navigation.yaml

@@ -1,54 +0,0 @@
-id: TC-001
-name: Basic Navigation Test
-description: Verify that the skill can navigate to a webpage and capture a screenshot
-priority: high
-category: functional
-
-preconditions:
-  - Playwright is installed
-  - Chromium browser is available
-  - Development server is running on localhost:3000
-
-test_steps:
-  - step: 1
-    action: Create test script that navigates to localhost:3000
-    expected: Test script is created in /tmp/
-
-  - step: 2
-    action: Execute test script via execute.js
-    expected: Browser launches and navigates to homepage
-
-  - step: 3
-    action: Capture full-page screenshot
-    expected: Screenshot is saved to /tmp/ with timestamp
-
-  - step: 4
-    action: Verify page title
-    expected: Page title is captured and logged to console
-
-  - step: 5
-    action: Close browser
-    expected: Browser closes cleanly without errors
-
-acceptance_criteria:
-  - Browser launches in visible mode (headless: false)
-  - Navigation completes successfully
-  - Screenshot file is created with correct naming pattern
-  - Console output shows execution steps
-  - No errors are thrown during execution
-
-test_data:
-  url: http://localhost:3000
-  expected_title: SpecWeave
-  screenshot_pattern: /tmp/homepage-*.png
-
-expected_results:
-  - Browser opens visibly
-  - Page loads within 10 seconds
-  - Screenshot file exists and is valid PNG
-  - Console shows "✅ Test passed" message
-  - Process exits with code 0
-
-notes: |
-  This is the most basic test case to verify core functionality.
-  All other tests depend on this working correctly.

package/src/skills/e2e-playwright/test-cases/TC-002-form-interaction.yaml

@@ -1,64 +0,0 @@
-id: TC-002
-name: Form Interaction Test
-description: Verify that the skill can interact with form elements using helper utilities
-priority: high
-category: functional
-
-preconditions:
-  - TC-001 passes
-  - Test page has a login form with email and password fields
-  - safeType and safeClick utilities are available
-
-test_steps:
-  - step: 1
-    action: Navigate to login page
-    expected: Login form is visible
-
-  - step: 2
-    action: Use safeType() to enter email address
-    expected: Email field is filled with test email
-
-  - step: 3
-    action: Use safeType() to enter password
-    expected: Password field is filled (masked)
-
-  - step: 4
-    action: Use safeClick() to submit form
-    expected: Form submission is triggered
-
-  - step: 5
-    action: Wait for navigation or success message
-    expected: User is redirected or sees success state
-
-  - step: 6
-    action: Capture screenshot of result
-    expected: Screenshot shows post-login state
-
-acceptance_criteria:
-  - safeType() handles focus and clearing automatically
-  - safeType() verifies text was entered correctly
-  - safeClick() waits for element to be visible
-  - Form submission completes without timeout
-  - Screenshots capture both pre and post submission states
-
-test_data:
-  email: test@example.com
-  password: testpassword123
-  login_url: http://localhost:3000/login
-  expected_redirect: /dashboard
-
-expected_results:
-  - Email field contains entered value
-  - Password field is masked
-  - Form submits successfully
-  - Navigation completes within 10 seconds
-  - Success state is reached
-
-error_scenarios:
-  - If email field not found: Error message with selector details
-  - If click times out: Retry up to 3 times
-  - If verification fails: Clear error about mismatch
-
-notes: |
-  Tests the core interaction utilities that make Playwright easier to use.
-  safeType() and safeClick() should handle common edge cases automatically.

package/src/skills/e2e-playwright/test-cases/TC-003-specweave-integration.yaml

@@ -1,74 +0,0 @@
-id: TC-003
-name: SpecWeave Integration Test
-description: Verify that the skill detects SpecWeave context and generates test reports in increment folders
-priority: medium
-category: integration
-
-preconditions:
-  - TC-001 and TC-002 pass
-  - Running in a SpecWeave project (.specweave/ directory exists)
-  - Active increment with in-progress status exists
-  - Increment has reports/ directory
-
-test_steps:
-  - step: 1
-    action: Execute test from within SpecWeave project
-    expected: Executor detects SpecWeave context
-
-  - step: 2
-    action: Check console output for SpecWeave detection message
-    expected: "🔷 SpecWeave project detected" is logged
-
-  - step: 3
-    action: Verify active increment detection
-    expected: "📦 Active increment: 0001-feature-name" is logged
-
-  - step: 4
-    action: Run test that generates results
-    expected: Test executes and collects results
-
-  - step: 5
-    action: Generate test report using generateTestReport()
-    expected: Markdown report is created
-
-  - step: 6
-    action: Save report using saveTestReport()
-    expected: Report is saved to .specweave/increments/{id}/reports/
-
-acceptance_criteria:
-  - detectSpecWeaveContext() correctly identifies SpecWeave projects
-  - Active increment is detected by checking tasks.md status
-  - Test reports follow SpecWeave format (see SKILL.md)
-  - Reports are saved to correct increment folder
-  - Report includes all sections (summary, results, performance, accessibility)
-
-test_data:
-  project_root: /path/to/specweave-project
-  increment_id: "0001-test-feature"
-  increment_status: in-progress
-  report_filename: e2e-test-report.md
-
-expected_results:
-  - isSpecweaveProject: true
-  - activeIncrement: "0001-test-feature"
-  - Report file exists at: .specweave/increments/0001-test-feature/reports/e2e-test-report.md
-  - Report contains proper Markdown formatting
-  - Report includes timestamp and test results
-
-report_sections_required:
-  - Test Summary (total, passed, failed, skipped)
-  - Test Results (individual test details)
-  - Performance Metrics (page load, interactions)
-  - Accessibility Issues (grouped by type)
-  - Recommendations (actionable items)
-
-edge_cases:
-  - No active increment: Should still work, just without increment context
-  - Multiple in-progress increments: Use the first one found
-  - reports/ directory missing: Create it automatically
-  - Running outside SpecWeave: Should work normally without SpecWeave features
-
-notes: |
-  This test verifies the SpecWeave-specific enhancements that differentiate
-  this skill from the original playwright-skill. The ability to automatically
-  detect context and generate reports in the right place is a key feature.