Run3 semantic subject classification

Maps documents to specific categories using a combination of keyword-based semantic matching and categorical hierarchy.From its SKILL.md

Install

npx -y skills add cxcscmu/SkillLearnBench --skill run3_semantic_subject_classification

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

0.9 KB, 172 tokens by cl100k_base, as published. Nobody here has run it

To ensure accurate classification:

Keyword/Thematic Set: Define a robust mapping dictionary including key terminology, common academic sub-fields, and potential core authors for each subject.
Standardized Mapping: Use a strict lookup dictionary where keys are subject categories and values are the exact folder names:
- LLM -> LLM
- Trapped Ion -> trapped_ion_and_qc
- Black Hole -> black_hole
- DNA -> DNA
- Default -> music_history
Logic Flow: Perform semantic evaluation for the first 4 subjects. If the similarity score falls below a defined threshold (e.g., 0.3) for all 4, assign the file to music_history as the absolute fallback.

Read from the repository

Just SKILL.md. No reference files, no scripts.