learning-adaptive-testing

majiayu000's avatarfrom majiayu000

adaptive-testing design for effective learning measurement.

5stars🔀1forks📁View on GitHub🕐Updated Jan 11, 2026

When & Why to Use This Skill

This Claude skill facilitates the design of advanced computer-adaptive tests (CAT) utilizing Item Response Theory (IRT) for precise and efficient learning measurement. By leveraging psychometric models like 2PL, it enables educators and developers to create assessments that dynamically adjust to a learner's proficiency level, ensuring accurate mastery determination with significantly fewer questions than traditional fixed-form tests.

Use Cases

  • Personalized Learning Platforms: Implementing dynamic assessments that adapt in real-time to a student's ability, providing a tailored educational experience.
  • Professional Certification: Designing high-stakes competency exams that use IRT to maintain rigorous standards while reducing testing fatigue for candidates.
  • Mastery-Based Curriculum Design: Mapping educational objectives to specific item banks to determine exactly when a student has reached the required knowledge threshold.
  • Educational Research: Utilizing the 2PL model to analyze item difficulty and discrimination, helping to refine question quality and assessment reliability.
namelearning-adaptive-testing
descriptionadaptive-testing design for effective learning measurement.

Learning adaptive testing

Design computer-adaptive tests using IRT for efficient mastery determination.

CLI: /learning.adaptive-testing --objectives objectives.json --irt-model 2PL

Exit Codes: 0=success, 1=invalid parameters, 2=insufficient items