grading-level-division-reference-calibrated
CommunityCalibrate grade boundaries from reference scores.
AuthorAKCqhzdy
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill computes a reference-calibrated level division for a grading regime. It uses the empirical score-to-level mapping from reference students, combined with rubric descriptors, and applies a reference-year bias prevention protocol before finalising the boundaries.
Core Features & Use Cases
- Determines initial level boundaries from reference score distributions and rubric means.
- Applies anti-bias adjustments to align the current cohort with reference-year expectations.
- Produces a deterministic level_division.json that records boundaries, the applied adjustments, and per-student final levels.
Quick Start
Run the reference-calibrated level division workflow to produce rubric/${SCOPE_GRADING_YEAR}/level_division.json.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: grading-level-division-reference-calibrated Download link: https://github.com/AKCqhzdy/dse-subject-grading/archive/main.zip#grading-level-division-reference-calibrated Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.