Portfolio of search evaluation, AI response grading, and dataset labeling artifacts

Bilingual (Malay + English) reasoning & governance dataset for evaluating LLM decision-making, stop-loss rules, and risk trade-offs.

Educational AI fluency self-assessment inspired by the 4D framework, with transcript scoring and guided challenge mode

[TEST REPO] PWA for task blocking that uses Rubric DSL for module constraints

Pytest plugin for semantic PASS/FAIL checks using LLM-as-a-Judge

Interactive dynamic rubric interface.

Tool for educators to generate formatted essay feedback reports

Bootcamp Rubric

Top-grade study prompt package focused on maximal score efficiency. Course-agnostic overlay + five core modules (Syllabus, Lectures, Assignments, Project, Exam) with strict rubric alignment and stepwise flows.

AI-powered course auditing for Canvas LMS. Ingest any course, build a dependency graph, and run multi-pass Claude reasoning to surface clarity issues, rubric mismatches, and curriculum gaps before students find them.

An Appscript to generate a Google Sheet that will allow you to import certain learning targets into a Google Classroom Assignment.

A sleek Streamlit-based auto-grader that lets instructors build a rubric in a simple table, upload student discussion files, and instantly generate final grades with downloadable reports.

a scoring guide used to assess the quality of feedback from communities

📊 Generate and access a comprehensive rubric dataset with RubricHub, enhancing your evaluation processes through automated data synthesis.

Universal quality evaluation plugin for Claude Code — 7-dimension scoring (correctness, completeness, adherence, efficiency, safety), configurable rubrics, threshold blocking, auto-hooks & /judge command.

Coders' creed

(Findings of ACL 2025) TabXEval: an exhaustive, explainable rubric + two-phase framework (TabAlign → TabCompare) for table evaluation with TabXBench.