CtrlK
BlogDocsLog inGet started
Tessl Logo

haletothewood/behavioural-tdd

Execute a strict Red-Green-Refactor TDD cycle — one requirement at a time — in any language or framework.

97

1.11x

Quality

100%

Does it follow best practices?

Impact

94%

1.11x

Average score across 5 eval scenarios

Overview
Skills
Evals
Files

rubric.jsonevals/scenario-4/

{
  "context": "The agent is executing Phase 1 (RED) of a behavioral TDD cycle for a C#/xUnit PasswordValidator requirement. It should produce a failing test against the public interface only and stop before writing any implementation.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "xUnit test targets public interface",
      "description": "A test method is written using xUnit ([Fact] or [Theory]) that instantiates or calls the public PasswordValidator interface",
      "max_score": 2
    },
    {
      "name": "Assertion checks false for short password",
      "description": "The test asserts a return value of false (or equivalent) when given a password shorter than 8 characters",
      "max_score": 2
    },
    {
      "name": "No implementation code written",
      "description": "No implementation code is written — only the test",
      "max_score": 2
    },
    {
      "name": "Public interface only",
      "description": "The test uses only the public interface; no private methods are called or referenced",
      "max_score": 2
    },
    {
      "name": "Expected failure reason stated",
      "description": "The agent states the expected failure reason (e.g. PasswordValidator does not exist)",
      "max_score": 1
    },
    {
      "name": "Phase gating respected",
      "description": "The agent stops after Phase 1 and waits for user confirmation before proceeding to Phase 2",
      "max_score": 2
    }
  ]
}

Install with Tessl CLI

npx tessl i haletothewood/behavioural-tdd@1.8.0

evals

SKILL.md

tile.json