specweave 0.1.9 → 0.3.1

package/src/skills/hetzner-provisioner/test-results/README.md

@@ -1,259 +0,0 @@
-# Test Results: hetzner-provisioner
-
-This directory contains test execution results for the hetzner-provisioner skill.
-
-## How to Run Tests
-
-### Prerequisites
-1. Hetzner Cloud account (sign up at https://www.hetzner.com/cloud)
-2. Hetzner API token (create in Hetzner Cloud Console)
-3. Terraform installed (`brew install terraform` on macOS)
-4. Optional: Domain name for SSL test
-
-### Running Test 1: Basic Provision
-
-**Prompt to Claude Code**:
-```
-Deploy my NextJS app on Hetzner as cheaply as possible
-```
-
-**Expected Behavior**:
-1. hetzner-provisioner skill activates
-2. Generates Terraform files in `terraform/` directory
-3. Outputs cost estimate: ~$6-7/month
-4. Provides deployment guide
-
-**Verification Steps**:
-```bash
-# 1. Check generated files
-ls terraform/
-# Should see: main.tf, variables.tf, outputs.tf
-
-# 2. Validate Terraform
-cd terraform
-terraform init
-terraform validate
-# Should output: "Success! The configuration is valid."
-
-# 3. Check cost estimate
-terraform plan
-# Should show estimated costs
-
-# 4. (Optional) Apply infrastructure
-export TF_VAR_hcloud_token="your-hetzner-api-token"
-terraform apply
-# Review plan, type 'yes' to provision
-
-# 5. Verify server is running
-# Check Hetzner Cloud Console for new server
-```
-
-**Expected Output**:
-- `terraform validate` succeeds
-- Cost in `terraform plan` is under $10/month
-- Server provisions successfully (if applied)
-
----
-
-### Running Test 2: Postgres Provision
-
-**Prompt to Claude Code**:
-```
-Deploy my NextJS app on Hetzner with Postgres database
-```
-
-**Expected Behavior**:
-1. Generates Terraform with both server + database
-2. Cost estimate: ~$11-12/month
-3. Outputs database connection string
-
-**Verification Steps**:
-```bash
-# 1. Validate Terraform
-cd terraform
-terraform init
-terraform validate
-
-# 2. Check resources
-terraform plan | grep "hcloud_database"
-# Should see Postgres database resource
-
-# 3. Check cost
-terraform plan | grep "cost"
-# Should be under $15/month
-
-# 4. (Optional) Apply and test connection
-terraform apply
-# Wait for database to provision (~5-10 minutes)
-
-# 5. Test database connection
-psql "$(terraform output -raw database_url)"
-# Should connect successfully
-```
-
-**Expected Output**:
-- Database resource in Terraform plan
-- Connection string in `terraform output`
-- Can connect to database via psql
-
----
-
-### Running Test 3: SSL Configuration
-
-**Prompt to Claude Code**:
-```
-Deploy my NextJS app on Hetzner with Postgres and SSL for my-saas.com
-```
-
-**Prerequisites**:
-- Domain name (e.g., my-saas.com)
-- DNS access to create A records
-
-**Expected Behavior**:
-1. Generates Terraform with Nginx + Certbot
-2. Provides DNS configuration guide
-3. Outputs SSL setup commands
-
-**Verification Steps**:
-```bash
-# 1. Apply infrastructure
-cd terraform
-terraform apply
-
-# 2. Get server IP
-SERVER_IP=$(terraform output -raw server_ip)
-echo "Server IP: $SERVER_IP"
-
-# 3. Configure DNS (in your DNS provider)
-# Create A record: my-saas.com → $SERVER_IP
-# Create A record: www.my-saas.com → $SERVER_IP
-
-# 4. Wait for DNS propagation
-dig my-saas.com +short
-# Should return $SERVER_IP
-
-# 5. SSH into server
-ssh root@$SERVER_IP
-
-# 6. Run certbot (on server)
-certbot --nginx -d my-saas.com -d www.my-saas.com
-# Follow prompts, enter email
-
-# 7. Test HTTPS
-curl -I https://my-saas.com
-# Should return HTTP/2 200 with valid SSL
-
-# 8. Test HTTP redirect
-curl -I http://my-saas.com
-# Should return 301 redirect to HTTPS
-
-# 9. Check SSL certificate
-echo | openssl s_client -connect my-saas.com:443 | grep "Verify return code"
-# Should output: "Verify return code: 0 (ok)"
-```
-
-**Expected Output**:
-- SSL certificate obtained successfully
-- HTTPS works: `https://my-saas.com`
-- HTTP redirects to HTTPS
-- SSL Labs test: A or A+ rating
-
----
-
-## Test Execution Log
-
-### Test 1: Basic Provision
-**Date**: [When you run this]
-**Status**: ⏳ Pending | ✅ Passed | ❌ Failed
-**Result**:
-```
-[Paste terraform validate output here]
-[Paste cost estimate here]
-[Paste any errors encountered]
-```
-
-### Test 2: Postgres Provision
-**Date**: [When you run this]
-**Status**: ⏳ Pending | ✅ Passed | ❌ Failed
-**Result**:
-```
-[Paste terraform plan output showing database]
-[Paste database connection test result]
-```
-
-### Test 3: SSL Configuration
-**Date**: [When you run this]
-**Status**: ⏳ Pending | ✅ Passed | ❌ Failed
-**Result**:
-```
-[Paste certbot output]
-[Paste curl -I https://my-saas.com output]
-[Paste SSL test result]
-```
-
----
-
-## Screenshots
-
-### Successful Deployment
-(Add screenshot of Hetzner Cloud Console showing provisioned resources)
-
-### SSL Certificate
-(Add screenshot of browser showing valid HTTPS)
-
-### Cost Breakdown
-(Add screenshot of Hetzner billing showing monthly costs)
-
----
-
-## Troubleshooting
-
-### Issue: "terraform validate" fails
-**Solution**:
-```bash
-# Check Terraform syntax
-terraform fmt
-terraform validate
-# Review error messages and fix syntax
-```
-
-### Issue: Database won't connect
-**Solution**:
-```bash
-# Check database is running
-terraform output database_host
-# Verify firewall rules allow connection
-# Check DATABASE_URL format
-```
-
-### Issue: Certbot fails
-**Solutions**:
-- DNS not propagated: Wait 30 minutes, try again
-- Port 80 blocked: Check firewall allows port 80
-- Email required: Provide valid email to certbot
-
----
-
-## Cleanup
-
-To destroy test infrastructure and avoid charges:
-
-```bash
-cd terraform
-terraform destroy
-# Type 'yes' to confirm
-
-# Verify in Hetzner Cloud Console that resources are deleted
-```
-
-**Important**: Hetzner charges by the hour, so destroy resources when done testing.
-
----
-
-## Success Criteria Summary
-
-✅ Test 1: Terraform validates, cost <$10/month
-✅ Test 2: Database provisions, can connect
-✅ Test 3: SSL works, HTTPS redirects
-
-**All tests must pass before skill is considered production-ready.**

package/src/skills/increment-planner/test-cases/test-1-basic-feature.yaml

@@ -1,27 +0,0 @@
----
-name: "Basic Feature Planning"
-description: "Tests if increment-planner can create a basic feature from a simple description"
-input:
-  prompt: "Plan a feature for user authentication with email and password"
-  files: []
-expected_output:
-  type: "files_generated"
-  files:
-    - "features/001-user-authentication/spec.md"
-    - "features/001-user-authentication/plan.md"
-    - "features/001-user-authentication/tasks.md"
-    - "features/001-user-authentication/tests.md"
-    - "features/001-user-authentication/context-manifest.yaml"
-  contains:
-    - "User authentication"
-    - "P1"
-    - "Acceptance Criteria"
-    - "Test-First"
-validation:
-  - "All files exist in correct directory"
-  - "spec.md is technology-agnostic"
-  - "plan.md contains technical decisions"
-  - "tasks.md has test-first sequencing"
-  - "tests.md covers P1 user stories"
-  - "context-manifest.yaml has token budget"
----

package/src/skills/increment-planner/test-cases/test-2-complex-feature.yaml

@@ -1,30 +0,0 @@
----
-name: "Complex Feature with Multiple User Stories"
-description: "Tests feature planning for a complex feature with multiple priorities"
-input:
-  prompt: "Plan a feature for Stripe payment integration including subscriptions, one-time payments, and webhooks"
-  files: []
-expected_output:
-  type: "files_generated"
-  files:
-    - "features/002-stripe-payment-integration/spec.md"
-    - "features/002-stripe-payment-integration/plan.md"
-    - "features/002-stripe-payment-integration/tasks.md"
-    - "features/002-stripe-payment-integration/tests.md"
-    - "features/002-stripe-payment-integration/context-manifest.yaml"
-  contains:
-    - "US1"
-    - "US2"
-    - "US3"
-    - "P1"
-    - "P2"
-    - "Stripe"
-    - "subscriptions"
-    - "webhooks"
-validation:
-  - "Multiple user stories with different priorities"
-  - "P1/P2/P3 prioritization present"
-  - "tasks.md organized by user story"
-  - "tests.md has integration tests"
-  - "context-manifest.yaml references payment specs"
----

package/src/skills/increment-planner/test-cases/test-3-auto-numbering.yaml

@@ -1,24 +0,0 @@
----
-name: "Auto-Numbering Feature Test"
-description: "Tests that features are correctly auto-numbered when previous features exist"
-input:
-  prompt: "Plan a feature for email notifications"
-  files:
-    - "features/001-user-authentication/"
-    - "features/002-stripe-payment-integration/"
-expected_output:
-  type: "files_generated"
-  files:
-    - "features/003-email-notifications/spec.md"
-    - "features/003-email-notifications/plan.md"
-    - "features/003-email-notifications/tasks.md"
-    - "features/003-email-notifications/tests.md"
-    - "features/003-email-notifications/context-manifest.yaml"
-  contains:
-    - "feature: 003-email-notifications"
-    - "003"
-validation:
-  - "Feature number is 003 (incremented from 002)"
-  - "No conflicts with existing features"
-  - "features/README.md updated with new feature"
----

package/src/skills/increment-quality-judge/test-cases/test-1-good-spec.yaml

@@ -1,95 +0,0 @@
----
-name: "Basic Quality Assessment - Good Spec"
-description: "Evaluate a well-written specification with clear acceptance criteria"
-skill: increment-quality-judge
-priority: P1
-estimated_time: "2-3 minutes"
-
-input:
-  prompt: "Assess the quality of the authentication spec"
-  spec_content: |
-    # Authentication Feature
-
-    ## Overview
-    Implement JWT-based authentication with refresh tokens for secure user access.
-
-    ## Acceptance Criteria
-    - AC-001: User can log in with email/password, receiving JWT token within 2 seconds
-    - AC-002: JWT token expires after 1 hour, requires refresh
-    - AC-003: Failed login attempts (>5) lock account for 15 minutes
-    - AC-004: Password must be 8+ characters with uppercase, lowercase, number, special char
-
-    ## Security
-    - Passwords hashed with bcrypt (cost factor: 12)
-    - JWTs signed with RS256 (private key rotation every 90 days)
-    - Rate limiting: 5 login attempts per 15 minutes per IP
-
-    ## Performance
-    - Login latency: p95 < 500ms, p99 < 1000ms
-    - Concurrent logins: Support 100 logins/second
-
-    ## Error Handling
-    - Invalid credentials: Return 401 with error code AUTH_001
-    - Account locked: Return 403 with error code AUTH_002
-    - Rate limit exceeded: Return 429 with retry-after header
-
-expected_output:
-  overall_score: 0.85-0.95
-  score_range: "excellent"  # 85-100
-
-  dimension_scores:
-    clarity:
-      min: 0.90
-      rationale: "Clear problem statement, well-defined objectives"
-
-    testability:
-      min: 0.90
-      rationale: "All acceptance criteria measurable with specific metrics"
-
-    completeness:
-      min: 0.85
-      rationale: "Functional and non-functional requirements covered"
-
-    feasibility:
-      min: 0.85
-      rationale: "Realistic timeline and technical constraints"
-
-    maintainability:
-      min: 0.80
-      rationale: "Good structure, some room for modularity improvement"
-
-    edge_cases:
-      min: 0.85
-      rationale: "Error scenarios and rate limiting specified"
-
-  issues_found:
-    count: 0-2
-    severity_breakdown:
-      critical: 0
-      major: 0
-      minor: 0-2
-
-  suggestions:
-    count: 0-3
-    priority_breakdown:
-      high: 0-1
-      medium: 0-2
-      low: 0-1
-
-  confidence: 0.85-0.95
-
-validation:
-  - "Overall score >= 0.85"
-  - "Clarity dimension >= 0.90"
-  - "Testability dimension >= 0.90"
-  - "No critical or major issues"
-  - "Confidence >= 0.85"
-  - "All 6 dimensions evaluated"
-
-success_criteria:
-  - "Score reflects high-quality specification"
-  - "Detailed dimension breakdown provided"
-  - "Minimal or no issues found"
-  - "High confidence in assessment"
-  - "Clear rationale for each dimension"
----

package/src/skills/increment-quality-judge/test-cases/test-2-poor-spec.yaml

@@ -1,108 +0,0 @@
----
-name: "Quality Assessment - Poor Spec Needing Improvement"
-description: "Evaluate a vague specification with untestable criteria, triggering feedback loop"
-skill: increment-quality-judge
-priority: P1
-estimated_time: "2-3 minutes"
-
-input:
-  prompt: "Assess the quality of the payment processing spec"
-  spec_content: |
-    # Payment Processing
-
-    ## Overview
-    Add payment feature to the app.
-
-    ## Requirements
-    - Users can make payments
-    - System should be secure
-    - Payments should be fast
-    - Handle errors properly
-
-    ## Technical Details
-    - Use some payment provider
-    - Store payment info
-    - Send receipts
-
-expected_output:
-  overall_score: 0.50-0.70
-  score_range: "needs_work"  # Below 70
-
-  dimension_scores:
-    clarity:
-      max: 0.65
-      rationale: "Vague problem statement, objectives unclear"
-
-    testability:
-      max: 0.55
-      rationale: "Acceptance criteria not measurable (no metrics, thresholds)"
-
-    completeness:
-      max: 0.60
-      rationale: "Missing error handling details, security specs, performance targets"
-
-    feasibility:
-      max: 0.70
-      rationale: "No timeline, resource requirements unclear"
-
-    maintainability:
-      max: 0.65
-      rationale: "Lacks modularity, extension points undefined"
-
-    edge_cases:
-      max: 0.50
-      rationale: "No failure scenarios, retry logic, or edge case handling"
-
-  issues_found:
-    count: 5-8
-    severity_breakdown:
-      critical: 0-1
-      major: 3-5
-      minor: 2-3
-
-  typical_issues:
-    - severity: "major"
-      description: "Acceptance criteria not testable"
-      location: "Requirements section"
-      suggestion: "Add measurable metrics (e.g., 'Payment completes in <3s')"
-
-    - severity: "major"
-      description: "Security requirements too vague"
-      location: "Technical Details"
-      suggestion: "Specify: PCI-DSS compliance, encryption standards (TLS 1.3), tokenization"
-
-    - severity: "major"
-      description: "No error handling specification"
-      location: "Requirements"
-      suggestion: "Define error scenarios: payment declined, timeout, network failure"
-
-    - severity: "minor"
-      description: "Payment provider not specified"
-      location: "Technical Details"
-      suggestion: "Choose provider: Stripe, PayPal, or Square"
-
-  suggestions:
-    count: 5-8
-    priority_breakdown:
-      high: 3-5
-      medium: 2-3
-      low: 0-1
-
-  confidence: 0.85-0.95  # High confidence even for poor spec
-
-validation:
-  - "Overall score < 0.70"
-  - "Testability dimension < 0.60"
-  - "At least 5 issues found"
-  - "At least 3 major issues"
-  - "At least 5 suggestions provided"
-  - "High priority suggestions >= 3"
-  - "Confidence >= 0.85"
-
-success_criteria:
-  - "Score accurately reflects poor quality"
-  - "All 6 dimensions show low scores"
-  - "Issues clearly documented with locations"
-  - "Actionable suggestions with examples"
-  - "Would trigger feedback loop (score < 0.80)"
----

package/src/skills/increment-quality-judge/test-cases/test-3-export-suggestions.yaml

@@ -1,87 +0,0 @@
----
-name: "Export Suggestions to Tasks"
-description: "Quality assessment with suggestions exported to tasks.md"
-skill: increment-quality-judge
-priority: P2
-estimated_time: "2-3 minutes"
-
-input:
-  prompt: "Assess quality and export suggestions to tasks"
-  spec_content: |
-    # User Profile Management
-
-    ## Overview
-    Allow users to manage their profile information.
-
-    ## Acceptance Criteria
-    - User can update profile (name, email, avatar)
-    - Changes saved successfully
-    - Validation for email format
-
-    ## Security
-    - Email verification required for email changes
-
-  export_to_tasks: true
-  increment_id: "0025-user-profile"
-
-expected_output:
-  overall_score: 0.70-0.80
-  score_range: "acceptable"  # 70-79
-
-  issues_found:
-    count: 3-5
-    typical_issues:
-      - "Performance requirements not specified"
-      - "Avatar upload constraints unclear (size, format)"
-      - "Concurrent edit conflict resolution not defined"
-
-  suggestions:
-    count: 3-5
-    typical_suggestions:
-      - priority: "high"
-        description: "Add performance requirements"
-        example: "Profile update completes in <1s, avatar upload <5s"
-
-      - priority: "high"
-        description: "Specify avatar constraints"
-        example: "Max size: 5MB, formats: JPG/PNG/WebP, dimensions: 512x512"
-
-      - priority: "medium"
-        description: "Define edit conflict resolution"
-        example: "Last-write-wins or optimistic locking with version field"
-
-  export_result:
-    file_path: ".specweave/increments/0025-user-profile/tasks.md"
-    tasks_added: 3-5
-    format: "markdown checklist"
-
-  tasks_content: |
-    ## Quality Improvements (from AI assessment)
-
-    - [ ] Add performance requirements (HIGH)
-      - Profile update: <1s
-      - Avatar upload: <5s
-
-    - [ ] Specify avatar upload constraints (HIGH)
-      - Max size: 5MB
-      - Formats: JPG, PNG, WebP
-      - Dimensions: 512x512
-
-    - [ ] Define edit conflict resolution (MEDIUM)
-      - Strategy: Last-write-wins or optimistic locking
-
-validation:
-  - "Suggestions exported to tasks.md"
-  - "Tasks in markdown checklist format"
-  - "Each task labeled with priority (HIGH/MEDIUM/LOW)"
-  - "Tasks include specific details, not vague"
-  - "File created at correct path"
-  - "At least 3 tasks added"
-
-success_criteria:
-  - "Export completes without errors"
-  - "Tasks are actionable with clear details"
-  - "Priority labels match suggestion priorities"
-  - "Tasks integrate cleanly with existing tasks.md"
-  - "Can check off tasks as they're completed"
----

package/src/skills/jira-sync/test-cases/test-1.yaml

@@ -1,9 +0,0 @@
----
-name: "Detect JIRA Sync Request"
-description: "Tests if jira-sync skill activates when user requests JIRA sync"
-input:
-  prompt: "Sync increment 0001 to JIRA"
-expected_output:
-  skill_activated: true
-  agent_invoked: "specweave-jira-mapper"
----

package/src/skills/jira-sync/test-cases/test-2.yaml

@@ -1,9 +0,0 @@
----
-name: "Coordinate with Agent"
-description: "Tests if jira-sync properly delegates to specweave-jira-mapper agent"
-input:
-  prompt: "Export increment 0001 to JIRA"
-expected_output:
-  agent_invoked: "specweave-jira-mapper"
-  parameters_passed: true
----

package/src/skills/jira-sync/test-cases/test-3.yaml

@@ -1,10 +0,0 @@
----
-name: "Handle Missing Credentials"
-description: "Tests error handling when JIRA credentials are missing"
-input:
-  prompt: "Sync to JIRA"
-  jira_configured: false
-expected_output:
-  error: "JIRA credentials not configured"
-  setup_instructions_provided: true
----

package/src/skills/nextjs/test-cases/test-1-app-router.yaml

@@ -1,13 +0,0 @@
-name: "Create Next.js App Router Page"
-description: "Test creating a page using Next.js 14+ App Router"
-user_input: "Create a products listing page using App Router"
-expected_behavior:
-  - Creates app/products/page.tsx
-  - Uses Server Components by default
-  - Implements async data fetching
-  - Includes proper metadata export
-validation:
-  - File located in app directory
-  - Uses default export function
-  - Implements async component if needed
-  - Exports metadata object

package/src/skills/nextjs/test-cases/test-2-server-actions.yaml

@@ -1,13 +0,0 @@
-name: "Implement Server Actions"
-description: "Test creating server actions for form handling"
-user_input: "Create a contact form using server actions"
-expected_behavior:
-  - Creates server action with 'use server' directive
-  - Implements form submission handler
-  - Uses FormData for input
-  - Includes validation with Zod
-validation:
-  - Uses 'use server' at top of action file
-  - Accepts FormData parameter
-  - Returns appropriate response
-  - Implements revalidatePath or redirect