magnus919_agent-skills/mermaid-diagrams/evals/evals.json

{
  "schema_version": 1,
  "skill_name": "mermaid-diagrams",
  "evals": [
    {
      "id": "github-flowchart-review",
      "prompt": "Create a Mermaid architecture diagram for a GitHub README showing a user, the application, and two external services. Make it understandable to a new contributor and verify that the chosen syntax renders on GitHub.",
      "expected_output": "A GitHub-compatible flowchart with a stated audience/job, clear entry point and read order, labeled relationships, consistent representations, and a text fallback or summary.",
      "assertions": [
        "The output chooses standard GitHub-compatible Mermaid syntax rather than unsupported native C4 syntax",
        "The audience and contributor question are stated",
        "Nodes and relationships use consistent labels and meanings",
        "The diagram has an intentional read order and avoids unnecessary detail",
        "A text summary or equivalent accessible fallback is provided"
      ]
    },
    {
      "id": "pdf-rendering-and-communication",
      "prompt": "Turn a 16-node process flow into a PDF-ready Mermaid artifact. The current render is too wide, labels overlap, and the proposed status colors are the only distinction between states.",
      "expected_output": "A plan that splits or restructures the flow, uses the PDF rendering path and portrait constraints, resolves label overlap, and adds non-color status meaning while documenting the audience and review evidence.",
      "assertions": [
        "The output treats width, density, and overlap as communication defects rather than only renderer defects",
        "The PDF path pre-renders Mermaid and checks the rendered result",
        "The diagram is split or otherwise kept within a readable portrait scope",
        "Status meaning is redundant with labels, shapes, or line styles rather than color alone",
        "Target surface, renderer/version, and review evidence are recorded"
      ]
    },
    {
      "id": "sequence-read-order",
      "prompt": "Review a sequence diagram of an order flow with seven participants, retries, a timeout branch, and a reconciliation step. It is intended for support engineers diagnosing delayed orders.",
      "expected_output": "A support-oriented sequence diagram review that preserves temporal order, makes retry/timeout/reconciliation behavior legible, and splits or scopes the diagram if seven participants create noise.",
      "assertions": [
        "The support audience and diagnostic job are stated",
        "Temporal read order and timeout/reconciliation paths are explicit",
        "Participant or message density is reduced or split when it obscures the diagnostic path",
        "Retry and failure notation has a documented, consistent meaning",
        "The review distinguishes communication choices from backend behavior ownership"
      ]
    },
    {
      "id": "uncertainty-and-legend",
      "prompt": "A Mermaid flowchart documents a proposed migration. Solid arrows are confirmed, dotted arrows are inferred, and dashed arrows are future work, but the legend is incomplete and the render uses three colors with no labels.",
      "expected_output": "A review that completes or redesigns the legend, makes uncertainty understandable without color, preserves consistent line semantics, and identifies the evidence needed for inferred relationships.",
      "assertions": [
        "Confirmed, inferred, and future relationships are explicitly labeled or otherwise understandable without color",
        "The legend matches the actual line styles and does not substitute for a narrative",
        "The output identifies evidence gaps for inferred relationships",
        "Color is treated as supplementary rather than the sole semantic channel",
        "The output avoids claiming that a valid render proves the migration plan is correct"
      ]
    },
    {
      "id": "c4-and-accessibility-routing",
      "prompt": "The team asks for a Mermaid C4 container diagram, a system architecture decision, and a WCAG conformance statement for the published page. Explain the diagram work and handoffs without absorbing neighboring owners.",
      "expected_output": "A scoped response that routes C4 model level decisions to c4-diagramming, architecture decisions to software-architecture, and complete accessibility conformance to web-accessibility while retaining Mermaid authoring/rendering and diagram communication review here.",
      "assertions": [
        "C4 level and model ownership are routed to c4-diagramming",
        "Architecture drivers and decisions are routed to software-architecture",
        "Full WCAG/ARIA and assistive-technology evidence are routed to web-accessibility",
        "Mermaid syntax, renderer compatibility, target-surface rendering, and communication review remain in scope",
        "The response does not store this boundary test as a trigger-only claim or pretend one validator proves all three outcomes"
      ]
    }
  ]
}