name: terraform-policy-eval
description: Auto-generated eval for terraform-policy.
skill: terraform-policy
version: "1.0"

config:
  trials_per_task: 1
  timeout_seconds: 300
  parallel: false
  executor: copilot-sdk
  model: claude-sonnet-4.6
metrics:
  - name: task_completion
    weight: 0.7
    threshold: 0.8
    description: Did the skill complete trigger and anti-trigger checks?
  - name: efficiency
    weight: 0.3
    threshold: 0.7
    description: Did the skill stay within behavior limits?
graders:
  - type: behavior
    name: token-budget
    config:
      max_tokens: 35000
tasks:
  - "tasks/*.yaml"