From rubric-maker-skill
Review OSCE rubrics for clinical alignment, safety, observability, objectivity, feasibility, reliability, scoring clarity, missing Technique/Purpose fields, and Rubric Maker suggestion output. Use when an agent needs to audit an existing rubric, produce clarifying questions, or generate structured improvement suggestions. Use evaluate-dry-run instead when the critique is based on a trial grade sheet, and use content-validation when a specific concern or proposed fix needs clinical-validity adjudication, severity, consensus, or educator-guided tie-breaking.
How this skill is triggered — by the user, by Claude, or both
Slash command
/rubric-maker-skill:osce-rubric-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- Broad first-pass audits of existing OSCE rubrics.
content-validation.osce-rubric-transform.rubric-import.post-encounter-note-rubric.generate-student-artifact.grading-dry-run.evaluate-dry-run.Use osce-rubric-review to discover and frame rubric issues before dry-run testing.
Use evaluate-dry-run when the user already has a case, artifact, and trial grade sheet
and wants improvements based on how the rubric behaved in practice.
Escalate selected findings to content-validation when their clinical validity,
severity, fairness, safety impact, or best fix is contested or high-stakes.
Use osce-rubric-transform after review, validation, or dry-run evaluation when the
user wants the rubric content adapted or rewritten.
location,
current_value, suggested_value, reasoning, priority, row, field, and
optional sub.0:QuestionName or
2:ScoringLogic.Score3.current_value exact when editing existing text.critical, high, medium, low.references/rubric-schema.md for the shared schema, mode semantics, and
structured suggestion conventions.references/review-framework.md for the six-pillar audit and clarifying-question
workflow.references/suggestion-contracts.md when producing or validating structured
improvement suggestions.Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub jamiesonlabutsw/maples-toolkit --plugin rubric-maker-skill