student-knowledge-profiling

To generate student knowledge profiles from score data, provide your raw scores and optional question-tagging metadata to compute per-knowledge-point mastery levels. The skill supports total-score, section-based, and item-level formats to output structured CSV reports and class heatmaps.

Knowledge-point mastery estimation translates raw assessment scores into structured per-student profiles by mapping mastery levels and computing confidence intervals. This identifies specific learning gaps to enable targeted interventions and personalized learning plans.

Yes, you can analyze section-based and item-level scores to compute per-student mastery. The skill multi-format mastery estimation works with total-score, section scores, or per-question results to generate structured profiles and risk indices.

The best way to identify learning gaps from CSV assessment data is to compute per-knowledge-point mastery profiles with confidence intervals and risk indices. This generates per-student CSVs and class heatmaps to prioritize interventions for systemic weaknesses.

You do not need question-tagging metadata to generate class heatmaps and trend insights, but providing it improves per-knowledge-point mapping accuracy. The skill processes total-score, section-based, and item-level formats while documenting data-quality constraints and methodological assumptions.