rubric-design-validation
Develop clear scoring rubrics with defined criteria, performance levels, and anchor examples ensuring inter-rater reliability
npx skills add a5c-ai/babysitter --skill rubric-design-validation --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.
# Rubric Design and Validation Develop clear scoring rubrics with defined criteria, performance levels, and anchor examples ensuring inter-rater reliability. ## Overview This skill enables the development and validation of scoring rubrics for educational assessment. It encompasses criteria definition, performance level articulation, anchor example selection, and reliability validation to ensure consistent and fair evaluation of student work. ## Capabilities ### Criteria Development - Identify essential performance dimensions - Define observable indicators - Weight criteria appropriately - Ensure comprehensiveness - Avoid overlap between criteria ### Performance Level Definition - Articulate distinct levels - Write clear descriptors - Ensure progressive differentiation - Define score points - Create level labels ### Anchor Examples - Select representative samples - Document exemplars for each level - Annotate scoring rationale - Create training materials - Validate with raters ### Reliability Validation - Conduct inter-rater reliability studies - Calculate agreement statistics - Identify scoring inconsistencies - Revise for clarity - Train and calibrate raters ## Usage Guidelines ##
- Overview
- Capabilities
- Criteria Development
- Performance Level Definition
- Anchor Examples
- Reliability Validation
- Usage Guidelines
- Rubric Development Process
- Descriptor Writing
- Validation Process
- Integration Points
- Related Processes
- Collaborating Skills
- References
What does the rubric-design-validation skill do?
Develop clear scoring rubrics with defined criteria, performance levels, and anchor examples ensuring inter-rater reliability
How do I install it?
Run `npx skills add a5c-ai/babysitter --skill rubric-design-validation --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.