claude-skill-lord 1.5.0

package/skills/tier-2/e2e-testing/SKILL.md

@@ -0,0 +1,326 @@
+---
+name: e2e-testing
+description: Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.
+origin: ECC
+---
+
+# E2E Testing Patterns
+
+Comprehensive Playwright patterns for building stable, fast, and maintainable E2E test suites.
+
+## Test File Organization
+
+```
+tests/
+├── e2e/
+│   ├── auth/
+│   │   ├── login.spec.ts
+│   │   ├── logout.spec.ts
+│   │   └── register.spec.ts
+│   ├── features/
+│   │   ├── browse.spec.ts
+│   │   ├── search.spec.ts
+│   │   └── create.spec.ts
+│   └── api/
+│       └── endpoints.spec.ts
+├── fixtures/
+│   ├── auth.ts
+│   └── data.ts
+└── playwright.config.ts
+```
+
+## Page Object Model (POM)
+
+```typescript
+import { Page, Locator } from '@playwright/test'
+
+export class ItemsPage {
+  readonly page: Page
+  readonly searchInput: Locator
+  readonly itemCards: Locator
+  readonly createButton: Locator
+
+  constructor(page: Page) {
+    this.page = page
+    this.searchInput = page.locator('[data-testid="search-input"]')
+    this.itemCards = page.locator('[data-testid="item-card"]')
+    this.createButton = page.locator('[data-testid="create-btn"]')
+  }
+
+  async goto() {
+    await this.page.goto('/items')
+    await this.page.waitForLoadState('networkidle')
+  }
+
+  async search(query: string) {
+    await this.searchInput.fill(query)
+    await this.page.waitForResponse(resp => resp.url().includes('/api/search'))
+    await this.page.waitForLoadState('networkidle')
+  }
+
+  async getItemCount() {
+    return await this.itemCards.count()
+  }
+}
+```
+
+## Test Structure
+
+```typescript
+import { test, expect } from '@playwright/test'
+import { ItemsPage } from '../../pages/ItemsPage'
+
+test.describe('Item Search', () => {
+  let itemsPage: ItemsPage
+
+  test.beforeEach(async ({ page }) => {
+    itemsPage = new ItemsPage(page)
+    await itemsPage.goto()
+  })
+
+  test('should search by keyword', async ({ page }) => {
+    await itemsPage.search('test')
+
+    const count = await itemsPage.getItemCount()
+    expect(count).toBeGreaterThan(0)
+
+    await expect(itemsPage.itemCards.first()).toContainText(/test/i)
+    await page.screenshot({ path: 'artifacts/search-results.png' })
+  })
+
+  test('should handle no results', async ({ page }) => {
+    await itemsPage.search('xyznonexistent123')
+
+    await expect(page.locator('[data-testid="no-results"]')).toBeVisible()
+    expect(await itemsPage.getItemCount()).toBe(0)
+  })
+})
+```
+
+## Playwright Configuration
+
+```typescript
+import { defineConfig, devices } from '@playwright/test'
+
+export default defineConfig({
+  testDir: './tests/e2e',
+  fullyParallel: true,
+  forbidOnly: !!process.env.CI,
+  retries: process.env.CI ? 2 : 0,
+  workers: process.env.CI ? 1 : undefined,
+  reporter: [
+    ['html', { outputFolder: 'playwright-report' }],
+    ['junit', { outputFile: 'playwright-results.xml' }],
+    ['json', { outputFile: 'playwright-results.json' }]
+  ],
+  use: {
+    baseURL: process.env.BASE_URL || 'http://localhost:3000',
+    trace: 'on-first-retry',
+    screenshot: 'only-on-failure',
+    video: 'retain-on-failure',
+    actionTimeout: 10000,
+    navigationTimeout: 30000,
+  },
+  projects: [
+    { name: 'chromium', use: { ...devices['Desktop Chrome'] } },
+    { name: 'firefox', use: { ...devices['Desktop Firefox'] } },
+    { name: 'webkit', use: { ...devices['Desktop Safari'] } },
+    { name: 'mobile-chrome', use: { ...devices['Pixel 5'] } },
+  ],
+  webServer: {
+    command: 'npm run dev',
+    url: 'http://localhost:3000',
+    reuseExistingServer: !process.env.CI,
+    timeout: 120000,
+  },
+})
+```
+
+## Flaky Test Patterns
+
+### Quarantine
+
+```typescript
+test('flaky: complex search', async ({ page }) => {
+  test.fixme(true, 'Flaky - Issue #123')
+  // test code...
+})
+
+test('conditional skip', async ({ page }) => {
+  test.skip(process.env.CI, 'Flaky in CI - Issue #123')
+  // test code...
+})
+```
+
+### Identify Flakiness
+
+```bash
+npx playwright test tests/search.spec.ts --repeat-each=10
+npx playwright test tests/search.spec.ts --retries=3
+```
+
+### Common Causes & Fixes
+
+**Race conditions:**
+```typescript
+// Bad: assumes element is ready
+await page.click('[data-testid="button"]')
+
+// Good: auto-wait locator
+await page.locator('[data-testid="button"]').click()
+```
+
+**Network timing:**
+```typescript
+// Bad: arbitrary timeout
+await page.waitForTimeout(5000)
+
+// Good: wait for specific condition
+await page.waitForResponse(resp => resp.url().includes('/api/data'))
+```
+
+**Animation timing:**
+```typescript
+// Bad: click during animation
+await page.click('[data-testid="menu-item"]')
+
+// Good: wait for stability
+await page.locator('[data-testid="menu-item"]').waitFor({ state: 'visible' })
+await page.waitForLoadState('networkidle')
+await page.locator('[data-testid="menu-item"]').click()
+```
+
+## Artifact Management
+
+### Screenshots
+
+```typescript
+await page.screenshot({ path: 'artifacts/after-login.png' })
+await page.screenshot({ path: 'artifacts/full-page.png', fullPage: true })
+await page.locator('[data-testid="chart"]').screenshot({ path: 'artifacts/chart.png' })
+```
+
+### Traces
+
+```typescript
+await browser.startTracing(page, {
+  path: 'artifacts/trace.json',
+  screenshots: true,
+  snapshots: true,
+})
+// ... test actions ...
+await browser.stopTracing()
+```
+
+### Video
+
+```typescript
+// In playwright.config.ts
+use: {
+  video: 'retain-on-failure',
+  videosPath: 'artifacts/videos/'
+}
+```
+
+## CI/CD Integration
+
+```yaml
+# .github/workflows/e2e.yml
+name: E2E Tests
+on: [push, pull_request]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 20
+      - run: npm ci
+      - run: npx playwright install --with-deps
+      - run: npx playwright test
+        env:
+          BASE_URL: ${{ vars.STAGING_URL }}
+      - uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: playwright-report
+          path: playwright-report/
+          retention-days: 30
+```
+
+## Test Report Template
+
+```markdown
+# E2E Test Report
+
+**Date:** YYYY-MM-DD HH:MM
+**Duration:** Xm Ys
+**Status:** PASSING / FAILING
+
+## Summary
+- Total: X | Passed: Y (Z%) | Failed: A | Flaky: B | Skipped: C
+
+## Failed Tests
+
+### test-name
+**File:** `tests/e2e/feature.spec.ts:45`
+**Error:** Expected element to be visible
+**Screenshot:** artifacts/failed.png
+**Recommended Fix:** [description]
+
+## Artifacts
+- HTML Report: playwright-report/index.html
+- Screenshots: artifacts/*.png
+- Videos: artifacts/videos/*.webm
+- Traces: artifacts/*.zip
+```
+
+## Wallet / Web3 Testing
+
+```typescript
+test('wallet connection', async ({ page, context }) => {
+  // Mock wallet provider
+  await context.addInitScript(() => {
+    window.ethereum = {
+      isMetaMask: true,
+      request: async ({ method }) => {
+        if (method === 'eth_requestAccounts')
+          return ['0x1234567890123456789012345678901234567890']
+        if (method === 'eth_chainId') return '0x1'
+      }
+    }
+  })
+
+  await page.goto('/')
+  await page.locator('[data-testid="connect-wallet"]').click()
+  await expect(page.locator('[data-testid="wallet-address"]')).toContainText('0x1234')
+})
+```
+
+## Financial / Critical Flow Testing
+
+```typescript
+test('trade execution', async ({ page }) => {
+  // Skip on production — real money
+  test.skip(process.env.NODE_ENV === 'production', 'Skip on production')
+
+  await page.goto('/markets/test-market')
+  await page.locator('[data-testid="position-yes"]').click()
+  await page.locator('[data-testid="trade-amount"]').fill('1.0')
+
+  // Verify preview
+  const preview = page.locator('[data-testid="trade-preview"]')
+  await expect(preview).toContainText('1.0')
+
+  // Confirm and wait for blockchain
+  await page.locator('[data-testid="confirm-trade"]').click()
+  await page.waitForResponse(
+    resp => resp.url().includes('/api/trade') && resp.status() === 200,
+    { timeout: 30000 }
+  )
+
+  await expect(page.locator('[data-testid="trade-success"]')).toBeVisible()
+})
+```

package/skills/tier-2/eval-harness/SKILL.md

@@ -0,0 +1,270 @@
+---
+name: eval-harness
+description: Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
+origin: ECC
+tools: Read, Write, Edit, Bash, Grep, Glob
+---
+
+# Eval Harness Skill
+
+A formal evaluation framework for Claude Code sessions, implementing eval-driven development (EDD) principles.
+
+## When to Activate
+
+- Setting up eval-driven development (EDD) for AI-assisted workflows
+- Defining pass/fail criteria for Claude Code task completion
+- Measuring agent reliability with pass@k metrics
+- Creating regression test suites for prompt or agent changes
+- Benchmarking agent performance across model versions
+
+## Philosophy
+
+Eval-Driven Development treats evals as the "unit tests of AI development":
+- Define expected behavior BEFORE implementation
+- Run evals continuously during development
+- Track regressions with each change
+- Use pass@k metrics for reliability measurement
+
+## Eval Types
+
+### Capability Evals
+Test if Claude can do something it couldn't before:
+```markdown
+[CAPABILITY EVAL: feature-name]
+Task: Description of what Claude should accomplish
+Success Criteria:
+  - [ ] Criterion 1
+  - [ ] Criterion 2
+  - [ ] Criterion 3
+Expected Output: Description of expected result
+```
+
+### Regression Evals
+Ensure changes don't break existing functionality:
+```markdown
+[REGRESSION EVAL: feature-name]
+Baseline: SHA or checkpoint name
+Tests:
+  - existing-test-1: PASS/FAIL
+  - existing-test-2: PASS/FAIL
+  - existing-test-3: PASS/FAIL
+Result: X/Y passed (previously Y/Y)
+```
+
+## Grader Types
+
+### 1. Code-Based Grader
+Deterministic checks using code:
+```bash
+# Check if file contains expected pattern
+grep -q "export function handleAuth" src/auth.ts && echo "PASS" || echo "FAIL"
+
+# Check if tests pass
+npm test -- --testPathPattern="auth" && echo "PASS" || echo "FAIL"
+
+# Check if build succeeds
+npm run build && echo "PASS" || echo "FAIL"
+```
+
+### 2. Model-Based Grader
+Use Claude to evaluate open-ended outputs:
+```markdown
+[MODEL GRADER PROMPT]
+Evaluate the following code change:
+1. Does it solve the stated problem?
+2. Is it well-structured?
+3. Are edge cases handled?
+4. Is error handling appropriate?
+
+Score: 1-5 (1=poor, 5=excellent)
+Reasoning: [explanation]
+```
+
+### 3. Human Grader
+Flag for manual review:
+```markdown
+[HUMAN REVIEW REQUIRED]
+Change: Description of what changed
+Reason: Why human review is needed
+Risk Level: LOW/MEDIUM/HIGH
+```
+
+## Metrics
+
+### pass@k
+"At least one success in k attempts"
+- pass@1: First attempt success rate
+- pass@3: Success within 3 attempts
+- Typical target: pass@3 > 90%
+
+### pass^k
+"All k trials succeed"
+- Higher bar for reliability
+- pass^3: 3 consecutive successes
+- Use for critical paths
+
+## Eval Workflow
+
+### 1. Define (Before Coding)
+```markdown
+## EVAL DEFINITION: feature-xyz
+
+### Capability Evals
+1. Can create new user account
+2. Can validate email format
+3. Can hash password securely
+
+### Regression Evals
+1. Existing login still works
+2. Session management unchanged
+3. Logout flow intact
+
+### Success Metrics
+- pass@3 > 90% for capability evals
+- pass^3 = 100% for regression evals
+```
+
+### 2. Implement
+Write code to pass the defined evals.
+
+### 3. Evaluate
+```bash
+# Run capability evals
+[Run each capability eval, record PASS/FAIL]
+
+# Run regression evals
+npm test -- --testPathPattern="existing"
+
+# Generate report
+```
+
+### 4. Report
+```markdown
+EVAL REPORT: feature-xyz
+========================
+
+Capability Evals:
+  create-user:     PASS (pass@1)
+  validate-email:  PASS (pass@2)
+  hash-password:   PASS (pass@1)
+  Overall:         3/3 passed
+
+Regression Evals:
+  login-flow:      PASS
+  session-mgmt:    PASS
+  logout-flow:     PASS
+  Overall:         3/3 passed
+
+Metrics:
+  pass@1: 67% (2/3)
+  pass@3: 100% (3/3)
+
+Status: READY FOR REVIEW
+```
+
+## Integration Patterns
+
+### Pre-Implementation
+```
+/eval define feature-name
+```
+Creates eval definition file at `.claude/evals/feature-name.md`
+
+### During Implementation
+```
+/eval check feature-name
+```
+Runs current evals and reports status
+
+### Post-Implementation
+```
+/eval report feature-name
+```
+Generates full eval report
+
+## Eval Storage
+
+Store evals in project:
+```
+.claude/
+  evals/
+    feature-xyz.md      # Eval definition
+    feature-xyz.log     # Eval run history
+    baseline.json       # Regression baselines
+```
+
+## Best Practices
+
+1. **Define evals BEFORE coding** - Forces clear thinking about success criteria
+2. **Run evals frequently** - Catch regressions early
+3. **Track pass@k over time** - Monitor reliability trends
+4. **Use code graders when possible** - Deterministic > probabilistic
+5. **Human review for security** - Never fully automate security checks
+6. **Keep evals fast** - Slow evals don't get run
+7. **Version evals with code** - Evals are first-class artifacts
+
+## Example: Adding Authentication
+
+```markdown
+## EVAL: add-authentication
+
+### Phase 1: Define (10 min)
+Capability Evals:
+- [ ] User can register with email/password
+- [ ] User can login with valid credentials
+- [ ] Invalid credentials rejected with proper error
+- [ ] Sessions persist across page reloads
+- [ ] Logout clears session
+
+Regression Evals:
+- [ ] Public routes still accessible
+- [ ] API responses unchanged
+- [ ] Database schema compatible
+
+### Phase 2: Implement (varies)
+[Write code]
+
+### Phase 3: Evaluate
+Run: /eval check add-authentication
+
+### Phase 4: Report
+EVAL REPORT: add-authentication
+==============================
+Capability: 5/5 passed (pass@3: 100%)
+Regression: 3/3 passed (pass^3: 100%)
+Status: SHIP IT
+```
+
+## Product Evals (v1.8)
+
+Use product evals when behavior quality cannot be captured by unit tests alone.
+
+### Grader Types
+
+1. Code grader (deterministic assertions)
+2. Rule grader (regex/schema constraints)
+3. Model grader (LLM-as-judge rubric)
+4. Human grader (manual adjudication for ambiguous outputs)
+
+### pass@k Guidance
+
+- `pass@1`: direct reliability
+- `pass@3`: practical reliability under controlled retries
+- `pass^3`: stability test (all 3 runs must pass)
+
+Recommended thresholds:
+- Capability evals: pass@3 >= 0.90
+- Regression evals: pass^3 = 1.00 for release-critical paths
+
+### Eval Anti-Patterns
+
+- Overfitting prompts to known eval examples
+- Measuring only happy-path outputs
+- Ignoring cost and latency drift while chasing pass rates
+- Allowing flaky graders in release gates
+
+### Minimal Eval Artifact Layout
+
+- `.claude/evals/<feature>.md` definition
+- `.claude/evals/<feature>.log` run history
+- `docs/releases/<version>/eval-summary.md` release snapshot