Scientific Research Data Visualization Protocol
Develop a publication-ready data visualization standard for complex scientific and statistical research.
Use this template when preparing charts, multi-panel figures, and statistical graphs for peer-reviewed research papers or institutional reports. It standardizes colorblind-safe palettes, typography hierarchies, and figure export workflows.
Role: Senior Information Designer specializing in quantitative research communication and statistical visualization.
Context
- Research Field: {{research_domain}}
- Target Publications or Outlets: {{target_journals}}
- Underlying Data Types: {{primary_dataset_types}}
- Accessibility & Visual Constraints: {{palette_accessibility_needs}}
- Production Environment: {{tooling_environment}}
- Delivery Milestone: {{publication_deadline}}
Task
Author a comprehensive visual standard and figure production plan to transform raw quantitative analysis into accessible, high-density, publication-grade figures aligned with academic editorial standards.
Method
- Review visual dimension constraints, DPI requirements, and font specifications required by {{target_journals}}.
- Map {{primary_dataset_types}} to optimal visual chart encodings that prevent graphical distortion and data obscuration.
- Establish colorblind-safe categorical, sequential, and diverging palettes satisfying {{palette_accessibility_needs}}.
- Define typography hierarchy, axis notation, error bar formats, and micro-annotation rules.
- Construct multi-panel layout templates maximizing data-ink ratio while maintaining legible whitespace.
- Standardize reproducible vector generation workflows using {{tooling_environment}}.
- Detail a systematic peer-review critique checklist for statistical clarity before {{publication_deadline}}.
Constraints
- MUST ensure all color scales remain interpretable in greyscale printing and across common color vision deficiencies.
- MUST NOT include decorative visual elements, ungrounded 3D charts, or misleading axis truncations.
- Line weights and label sizes must maintain legibility when scaled down to journal column widths.
- All visual standards must be reproducible via code or templates in {{tooling_environment}}.
Output format
- Section 1: Visual Style Architecture (Typography, Color Scale Tokens, Grid Rules)
- Section 2: Chart Encoding Matrix (Mapping each item in {{primary_dataset_types}} to chart archetypes)
- Section 3: Figure Assembly & Vector Export Pipeline (Step-by-step workflow)
- Section 4: Pre-Submission Quality Assurance Checklist (6 concrete validation items)
Self-review
- Are palette recommendations compliant with {{palette_accessibility_needs}}?
- Are chart types precisely matched to the mathematical characteristics of {{primary_dataset_types}}?
- Do figure dimensions strictly adhere to {{target_journals}} specifications?
Explicit role, a named task, and discrete steps the model can follow.
Background, inputs and variables the model needs before it starts.
Hard boundaries — what the model must and must not do.
A named, field-level shape for the response.
Ordered work items that force analysis before an answer.
Length and structure that travel across frontier models.
Signal density — instruction weight without padding.
Documented variables so the scaffold adapts to new inputs.
Quality bar, assumptions and behaviour when inputs are thin.
How much real usage the template has behind it.