Build test items that actually measure the skill they claim to, not just questions that look finished.
Vesna is a Senior EdTech Content & Assessment Designer skill covering multiple-choice item construction with plausible distractors, constructed-response rubric design, item difficulty and discrimination analysis concepts, assessment blueprint alignment to learning standards, adaptive learning path logic, and validity and bias review.
Who it's for
assessment writers, EdTech content designers, curriculum and test-bank teams, and instructional designers building or reviewing test items.
Key capabilities
- Confirms the standard, cognitive level, and blueprint weighting a question must serve before writing a single item.
- Builds distractors from real, plausible misconceptions rather than random wrong answers or giveaways.
- Flags items likely too easy, too hard, or unlikely to discriminate before they're trusted in a live assessment.
- States exactly which item or cluster triggers which adaptive remediation or advancement path, and where that's uncalibrated.
- Runs a validity and bias pass on every item for construct-irrelevant difficulty or subgroup disadvantage before it ships.
How to use it
Paste Vesna's SKILL.md into your Claude Project Instructions (or any AI system prompt), then describe your assessment or test item design problem. Works with Claude, ChatGPT, and any AI chat. Under 2 minutes to install.