skills.rest
AKCqhzdy
AKCqhzdyCOMMUNITY
Explore all skills by this author →
GitHub

lingliang-evaluation

Compare AI-generated Lingliang math grades against ground-truth scores using Spearman ρ, Pearson r, MAE, RMSE, and ±5-point accuracy.

Updated Aug 27, 2026
Search Tags:#education#metrics#evaluation#statistics#grading#ground-truth#lingliang
One-click install
npx skills add https://github.com/AKCqhzdy/dse-subject-grading --skill lingliang-evaluation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: lingliang-evaluation
Source: https://github.com/AKCqhzdy/dse-subject-grading/tree/main/skills/lingliang-evaluation
Command: npx skills add https://github.com/AKCqhzdy/dse-subject-grading --skill lingliang-evaluation

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Evaluates AI-generated Lingliang primary school math exam grades against ground-truth raw scores to measure accuracy and reliability using meaningful statistics.

Core Features & Use Cases

  • Compute Spearman ρ, Pearson r, MAE, RMSE, and ±5-point accuracy for 20 students.
  • Generate per-student reports and aggregate metrics, with data aligned to ground truth and grading outputs.
  • Use case: compare AI grading with ground-truth to validate model performance and calibrate thresholds.

Quick Start

Run the Lingliang evaluation workflow to compare AI grading outputs against ground-truth scores and generate the evaluation report.

Frequently Asked Questions about lingliang-evaluation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I evaluate AI grading accuracy against ground truth scores?▼

To evaluate AI grading accuracy against ground truth, compute statistical metrics like Spearman ρ, Pearson r, MAE, RMSE, and ±5-point accuracy. This Skill generates per-student and class-wide evaluation reports for 20 students.

What statistics are used for measuring AI exam grading reliability?▼

AI exam grading reliability is measured using Spearman ρ, Pearson r, MAE, RMSE, and ±5-point accuracy. These statistics validate model performance against ground-truth raw scores.

How do I compare AI-generated math grades with ground-truth raw scores?▼

Compare AI math grades with ground-truth raw scores by aligning per-student grading outputs with ground-truth mappings. The evaluation workflow outputs class-wide metrics and reports stored in evaluation/lingliang.

Do I need per-student grading outputs to run the evaluation?▼

Yes, running the evaluation requires per-student grading outputs and ground-truth mappings. The Skill aligns data, computes metrics, and generates reports for the 20-student Lingliang math exam dataset.

Where are the evaluation metrics and reports stored after running the grading comparison?▼

Evaluation metrics and reports are stored in the evaluation/lingliang directory, with aggregate metrics saved to evaluation/lingliang/metrics.json. The evaluation scripts are located in the scripts/ folder.

Related Skills

Explore More Education & Research Skills→
Ikram-AlamIkram-Alam

evaluation

Evaluate agent outputs against rubrics and ground truth with multi-dimensional scoring.

Community
Basic
michaeldubumichaeldubu

tech-report

Generate technical reports from performance analysis data in DOCX, PDF, and Markdown.

Community
Intermediate
paleoterrapaleoterra
2

code-metrics-analyzer

Compute code quality metrics and generate HTML reports.

Community
Intermediate
SamyakJhaveriSamyakJhaveri

eval-grader

Classify batch evaluation results and generate publication-ready markdown summary tables.

Community
Advanced