CtrlK
BlogDocsLog inGet started
Tessl Logo

pantheon-ai/test-driven-development

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?

Evaluation86%

1.05x

Agent success when using this tile

Validation for skill structure

Overview
Skills
Evals
Files

rubric.jsonevals/scenario-4/

{
  "context": "Tests whether the agent properly handles asynchronous code testing without creating flaky tests or using arbitrary delays.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "No arbitrary sleeps",
      "description": "Tests do not use setTimeout, sleep, or fixed delays to wait for async operations",
      "max_score": 15
    },
    {
      "name": "Proper async assertions",
      "description": "Uses proper async test patterns like await expect().resolves, waitFor, or promise-based assertions",
      "max_score": 15
    },
    {
      "name": "Deterministic timing",
      "description": "Tests control timing through mocks, promises, or synchronization mechanisms, not arbitrary waits",
      "max_score": 15
    },
    {
      "name": "AAA structure in async",
      "description": "Async tests maintain clear Arrange-Act-Assert structure with proper await usage",
      "max_score": 10
    },
    {
      "name": "Isolated async tests",
      "description": "Each test properly cleans up async operations and doesn't affect other tests",
      "max_score": 10
    },
    {
      "name": "Error case handling",
      "description": "Tests async error scenarios using proper rejection handling, not try/catch patterns",
      "max_score": 10
    },
    {
      "name": "Stable test execution",
      "description": "Tests pass consistently without timing dependencies or race conditions",
      "max_score": 10
    },
    {
      "name": "Mock async dependencies",
      "description": "External async services are mocked to eliminate network/IO timing variability",
      "max_score": 10
    },
    {
      "name": "Clear async test names",
      "description": "Test names describe the async behavior being tested clearly",
      "max_score": 5
    }
  ]
}

Install with Tessl CLI

npx tessl i pantheon-ai/test-driven-development@0.2.4

evals

SKILL.md

tile.json