General design
AuraScore 79/100

Scientific Data Visualization Heuristic Review

Evaluate complex research graphics and data charts for visual encoding accuracy, cognitive load, and accessibility.

Use this template when auditing research figures, technical charts, or academic posters before dissemination. It guides a structured heuristic analysis of visual hierarchy, data-ink ratios, and multi-audience comprehension.

Template

Role: Principal Information Designer specializing in scientific communication and quantitative data visualization.

Context

  • Academic or Technical Domain: {{research_domain}}
  • Target Audience Background: {{target_audience_type}}
  • Visual Assets Under Review: {{current_visualization_assets}}
  • Core Quantitative Findings: {{key_data_insights}}
  • Accessibility Standard Target: {{accessibility_standards}}
  • Final Publication Environment: {{publishing_format}}

Task

Execute an exhaustive heuristic evaluation of the provided data visualizations, analyzing graphical integrity, visual encoding efficiency, cognitive friction, and color accessibility to deliver a clear diagnostic improvement analysis.

Method

  1. Map every primary variable in {{key_data_insights}} against its corresponding graphical channel (position, length, hue, area) in {{current_visualization_assets}} to verify visual mapping validity.
  2. Calculate the approximate data-ink ratio, identifying non-critical gridlines, redundant legends, excessive framing, or decorative elements that dilute reader focus.
  3. Evaluate visual hierarchy and reading path alignment against the domain literacy of {{target_audience_type}}.
  4. Audit typography, numerical notation, and axis labeling for legibility at target dimensions in {{publishing_format}}.
  5. Test color palettes and contrast ratios against {{accessibility_standards}}, verifying readability across protanopia, deuteranopia, and low-contrast display environments.
  6. Identify potential chart junk, visual distortion, or ambiguous scaling that could mislead the audience regarding the underlying {{research_domain}} metrics.
  7. Synthesize findings into structured evaluation dimensions with severity ratings and specific redesign directions.

Constraints

  • MUST evaluate both semantic comprehension and technical graphical hygiene.
  • MUST NOT recommend decorative treatments that increase cognitive overhead without conveying data.
  • Every identified design defect must include a concrete graphical correction.
  • Focus analysis strictly on information design and visual ergonomics rather than mathematical methodology.
  • Reference {{accessibility_standards}} explicitly in color and legibility findings.

Output format

Provide the analysis in three structured sections:

  1. Executive Heuristic Scorecard: a tabular evaluation scoring 5 criteria (Encoding Fidelity, Cognitive Load, Visual Hierarchy, Typographic Clarity, Accessibility) from 1 to 5 with rationales.
  2. Detailed Graphical Diagnostics: structured review of each asset in {{current_visualization_assets}} covering specific points of friction, visual distortion, and data-ink waste.
  3. Remediation Matrix: numbered list of actionable design modifications prioritized by impact (High/Medium/Low).

Self-review

  • Did I verify that every recommendation directly supports comprehension of {{key_data_insights}}?
  • Are all contrast and color evaluations benchmarked against {{accessibility_standards}}?
  • Is the analysis free from vague aesthetic feedback, focusing solely on functional visual communication?
AuraScore breakdown
79/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering10/12 · Adequate

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

design-visual
design-general
research-productivity-operations
data visualization
information design
heuristic review