Master Test-Driven Development with deterministic red-green-refactor workflows, test-first feature delivery, bug reproduction through failing tests, behavior-focused assertions, and refactoring safety; use when implementing new functions, changing APIs, fixing regressions, or restructuring code under test.
Does it follow best practices?
Evaluation — 86%
↑ 1.05xAgent success when using this tile
Validation for skill structure
Distribute tests according to the pyramid: many unit tests at the base, fewer integration tests in the middle, and minimal E2E tests at the top.
Incorrect (inverted pyramid):
┌─────────────────────────────┐
│ E2E Tests (500) │ ← Slow, expensive, flaky
├─────────────────────────────┤
│ Integration Tests (100) │
├─────────────────────────────┤
│ Unit Tests (50) │ ← Fast, cheap, stable
└─────────────────────────────┘
Test run time: 45 minutes
Maintenance cost: HIGH
Flakiness: FREQUENT
Infrastructure cost: $10,000/monthCorrect (proper pyramid):
┌───────────┐
│ E2E (20) │ ← Critical user journeys only
┌───┴───────────┴───┐
│ Integration (100) │ ← Component boundaries
┌───┴───────────────────┴───┐
│ Unit Tests (500) │ ← Business logic
└───────────────────────────┘
Test run time: 5 minutes
Maintenance cost: LOW
Flakiness: RARE
Infrastructure cost: $100/monthDistribution guidelines:
| Layer | Count | Scope | Speed |
|---|---|---|---|
| Unit | 70-80% | Single function/class | <100ms |
| Integration | 15-25% | Multiple components | <5s |
| E2E | 5-10% | Full user journey | <30s |
What to test at each level:
Reference: The Practical Test Pyramid - Martin Fowler
Install with Tessl CLI
npx tessl i pantheon-ai/test-driven-developmentevals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
references