CtrlK
BlogDocsLog inGet started
Tessl Logo

pantheon-ai/bdd-testing

Write and maintain Behavior-Driven Development tests with Gherkin and Cucumber. Use when defining acceptance scenarios, writing feature files, implementing step definitions, running Three Amigos sessions, or diagnosing BDD test quality issues. Keywords: bdd, gherkin, cucumber, given when then, feature files, step definitions, acceptance criteria, three amigos, example mapping.

Does it follow best practices?

Evaluation96%

1.04x

Agent success when using this tile

Validation for skill structure

Overview
Skills
Evals
Files

rubric.jsonevals/scenario-1/

{
  "context": "Tests whether the agent uses business-facing language, creates readable scenarios for non-developers, specifies observable behavior rather than implementation details, and structures scenarios with proper Given/When/Then format.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Business language usage",
      "description": "Feature file uses business-facing terminology that stakeholders would understand, avoiding technical jargon",
      "max_score": 15
    },
    {
      "name": "Non-developer readability",
      "description": "Scenarios are written in plain language that business stakeholders could review and understand",
      "max_score": 15
    },
    {
      "name": "Observable behavior focus",
      "description": "Scenarios specify user-visible outcomes rather than internal system behavior or implementation details",
      "max_score": 15
    },
    {
      "name": "Given/When/Then structure",
      "description": "Scenarios follow proper Gherkin Given/When/Then structure with clear context/action/outcome",
      "max_score": 10
    },
    {
      "name": "Avoids implementation details",
      "description": "Steps do NOT reference specific UI elements, APIs, database operations, or internal method calls",
      "max_score": 15
    },
    {
      "name": "Specific observable outcomes",
      "description": "Then steps specify concrete, verifiable outcomes like displayed text, visible elements, or user feedback",
      "max_score": 10
    },
    {
      "name": "Single behavior focus",
      "description": "Each scenario focuses on testing one specific behavior or user journey",
      "max_score": 10
    },
    {
      "name": "Deterministic scenarios",
      "description": "Scenarios are written to be repeatable and predictable without external dependencies",
      "max_score": 10
    }
  ]
}

Install with Tessl CLI

npx tessl i pantheon-ai/bdd-testing

evals

scenario-1

rubric.json

task.md

SKILL.md

tile.json