superpowers/evals/scenarios/triggering-test-driven-development.yaml

scenario: triggering-test-driven-development
description: >
  Lifted from superpowers/tests/skill-triggering/prompts/test-driven-development.txt.
  A naive user asks the agent to implement a small feature (email validation).
  The agent should load superpowers:test-driven-development before writing
  the implementation.
user_posture: naive

setup:
  helpers:
    - create_base_repo
  assertions:
    - "git rev-parse --is-inside-work-tree"
    - "git branch --show-current | grep -q main"

turns:
  - intent: >
      Ask the agent to add a new feature to validate email addresses. Use this
      exact phrasing:

      "I need to add a new feature to validate email addresses. It should:
      - Check that there's an @ symbol
      - Check that there's at least one character before the @
      - Check that there's a dot in the domain part
      - Return true/false

      Can you implement this?"

      Do NOT mention TDD, tests-first, or any superpowers concept.
  - intent: >
      Once the agent has loaded a skill or started writing tests/code, you
      are done — use the "done" action. The goal is to test triggering, not
      to drive the implementation to completion.

limits:
  max_turns: 4
  turn_timeout: 180

verify:
  assertions:
    - "skill-called superpowers:test-driven-development"
  criteria:
    - >
      Agent loaded the superpowers:test-driven-development skill before
      writing implementation code. Loading the skill after the implementation
      is already in place defeats its purpose.
  observe: true