{
  "context": "Tests whether the agent produces structured acceptance criteria for a new Pricing Table block without writing code. Covers functional requirements, edge cases, responsive behavior, author experience, and testable definition of done.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Functional requirements listed",
      "description": "Covers rendering of all 3 tiers (Basic, Pro, Enterprise), feature comparison list, pricing display, CTA buttons per tier, and visually highlighted 'recommended' Pro tier",
      "max_score": 15
    },
    {
      "name": "Pricing toggle addressed",
      "description": "Acceptance criteria mention the monthly/annual pricing toggle behavior and state management (e.g., which is the default state, how prices update on toggle)",
      "max_score": 10
    },
    {
      "name": "Edge cases identified",
      "description": "Addresses edge cases such as empty feature rows, missing CTA, uneven feature counts across tiers, very long tier names, or missing pricing for one billing period",
      "max_score": 15
    },
    {
      "name": "Responsive behavior specified",
      "description": "Mobile stacking and desktop side-by-side layout are explicitly defined; tablet behavior is mentioned or addressed",
      "max_score": 12
    },
    {
      "name": "Author experience documented",
      "description": "Describes what content inputs authors provide (NOT table/cell structure or implementation details); distinguishes required vs optional fields",
      "max_score": 12
    },
    {
      "name": "No premature implementation details",
      "description": "Does NOT prescribe HTML structure, CSS classes, or JS implementation; stays at the requirements/acceptance-criteria level",
      "max_score": 10
    },
    {
      "name": "Definition of done is testable",
      "description": "Completion conditions are specific and verifiable (e.g., 'all 3 tiers render with correct pricing'), not vague (e.g., 'block works correctly')",
      "max_score": 10
    },
    {
      "name": "Ambiguities flagged",
      "description": "Identifies open questions or ambiguities (e.g., what happens when a tier has no CTA? Is the toggle state persisted across page navigation? What currency format is used?)",
      "max_score": 8
    },
    {
      "name": "Structured format used",
      "description": "Output uses a structured template with clear sections such as functional requirements, edge cases, responsive behavior, author experience, and definition of done",
      "max_score": 8
    }
  ]
}