hkdse-subject-evaluation

Community

Evaluate AI grading against ground truth.

AuthorAKCqhzdy
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill evaluates HKDSE elective subject AI grading results against ground truth levels (1–5), enabling rigorous accuracy assessment and report generation.

Core Features & Use Cases

  • Ordinal evaluation: computes rank-based metrics (Spearman ρ, Kendall τ) to compare predicted levels with ground truth.
  • Ground-truth alignment: supports multiple data sources (per-student results, final scores, and optional rubric level divisions) to compute exact and adjacent match rates.
  • Comprehensive reports: generates visualization figures and DOCX evaluation reports across year scopes for subject-agnostic evaluation.

Quick Start

Execute the evaluation workflow for a given YEAR to compare grading outputs against the ground-truth mapping.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 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: hkdse-subject-evaluation
Download link: https://github.com/AKCqhzdy/dse-subject-grading/archive/main.zip#hkdse-subject-evaluation

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.