assessment-item-development
Create valid, reliable assessment items across formats (multiple choice, constructed response, performance tasks) following psychometric best practices
Profile →npx skills add a5c-ai/babysitter --skill assessment-item-development --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Assessment Item Development Create valid, reliable assessment items across formats including multiple choice, constructed response, and performance tasks following psychometric best practices. ## Overview This skill enables the development of high-quality assessment items that accurately measure learning outcomes. It encompasses item writing across formats, alignment with objectives, and application of psychometric principles to create valid and reliable assessments. ## Capabilities ### Multiple Choice Items - Write clear, unambiguous stems - Develop plausible distractors - Avoid item-writing flaws - Address various cognitive levels - Apply item analysis principles ### Constructed Response - Design short-answer items - Create essay prompts - Develop case-based questions - Write open-ended problems - Create scoring guidelines ### Performance Tasks - Design authentic tasks - Develop task specifications - Create rubrics and scoring guides - Plan administration conditions - Document task requirements ### Quality Assurance - Review for bias and sensitivity - Verify content alignment - Apply item statistics - Conduct item review - Document item metadata ## Usage Guidelines ### Item Dev
- Overview
- Capabilities
- Multiple Choice Items
- Constructed Response
- Performance Tasks
- Quality Assurance
- Usage Guidelines
- Item Development Process
- Multiple Choice Guidelines
- Constructed Response Guidelines
- Integration Points
- Related Processes
- Collaborating Skills
- References
What does the assessment-item-development skill do?
Create valid, reliable assessment items across formats (multiple choice, constructed response, performance tasks) following psychometric best practices
How do I install it?
Run `npx skills add a5c-ai/babysitter --skill assessment-item-development --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From a5c-ai/babysitter, a repository with 1,642 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.