hkdse-chinese-evaluation
CommunityEvaluate HKDSE Chinese AI grading vs ground truth
AuthorAKCqhzdy
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Evaluates HKDSE Chinese Language AI grading results for year 2025 against ground truth levels (1–5). Computes Spearman ρ, Kendall τ, exact/adjacent match rates, generates evaluation figures and DOCX reports for 10 students.
Core Features & Use Cases
- Automates evaluation workflow aligning AI grades with ground truth levels for HKDSE Chinese.
- Calculates rank-based metrics (Spearman ρ, Kendall τ) and per-student/class-level reports, plus visualization figures.
- Produces DOCX evaluation reports for class-wide assessment and audit trails.
Quick Start
Set YEAR to the target year and run the evaluation workflow to process grading outputs and ground-truth mappings.
Dependency Matrix
Required Modules
None requiredComponents
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-chinese-evaluation Download link: https://github.com/AKCqhzdy/dse-subject-grading/archive/main.zip#hkdse-chinese-evaluation 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.