Virtual STEM Laboratory Accessibility Testing Script
Develop a specialized think-aloud evaluation script for testing assistive technology interactions in digital science simulations.
Use this prompt when auditing screen reader navigation, keyboard traversal, and cognitive accessibility within interactive STEM learning tools and virtual experiment platforms.
Role: Principal Accessibility and Inclusive UX Architect for digital STEM learning environments.
Context
- Interactive simulation module: {{lab_simulation_title}}
- Target assistive technology: {{assistive_tech_modality}}
- Key interactive mechanic: {{complex_stem_interaction}}
- Cognitive or sensory challenge factor: {{cognitive_load_factor}}
- Target accessibility standard: {{wcag_conformance_target}}
- Evaluation session duration: {{session_timebox_minutes}}
Task
Author an accessible think-aloud evaluation script and testing protocol that systematically measures how students using {{assistive_tech_modality}} navigate {{complex_stem_interaction}} in the {{lab_simulation_title}} simulation.
Method
- Craft an accessibility-first briefing script confirming screen reader configurations, audio feeds, and keyboard-only preferences.
- Write pre-task baseline questions assessing the user's prior exposure to non-visual STEM data representations.
- Formulate three scenario tasks requiring non-visual manipulation of {{complex_stem_interaction}}.
- Define observer cues to audit ARIA live region announcements, focus trapping, and keyboard tab order efficiency.
- Draft non-directive verbal prompts to encourage verbalization of mental models without influencing tactile navigation.
- Integrate targeted probes for {{cognitive_load_factor}} during data collection and formula readout phases.
- Construct post-scenario debrief questions evaluating compliance with {{wcag_conformance_target}} criteria.
Constraints
- The script MUST contain explicit instructions for logging ARIA live region misfires.
- Facilitators MUST NOT prescribe specific keyboard shortcuts or navigation pathways during active tasks.
- Scenarios must account for the cognitive burden imposed by {{cognitive_load_factor}}.
- Timeboxing MUST account for assistive tech latency and keep total runtime within {{session_timebox_minutes}}.
Output format
Provide a 4-section evaluation protocol:
- Assistive Tech Setup & Calibration Script
- Scenario Flow (Task Description, Target Accessibility Pattern, Facilitator Script, Live-Region Observation Matrix)
- Think-Aloud Prompt Inventory (Neutral Interventions)
- WCAG & Usability Debrief Questionnaire
Self-review
- Does the script account for the unique communication cadence of {{assistive_tech_modality}}?
- Are observation checkpoints tuned to {{complex_stem_interaction}} rather than standard static web UI?
- Does the output verify conformance against {{wcag_conformance_target}}?
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.