Paper Extract Style

Paper Style Extraction Skill

Goal: Reverse engineer academic style from PDF/TeX files and build the psmfiles/ knowledge base.

Workflow

1. Locate Source Files:

   • Look for PDF, TeX, or TXT files in the current directory or user-specified path.
   • If user requests new papers/datasets, use WebSearch to find them first.

2. Extract Text:

   • Execute the extraction script: python paper-extract-style/extract_text.py <file_path>
   • This creates ref_article/*_cleaned_body.md and ref_article/*_appendix.md.

3. Build Knowledge Base (Incremental Fusion):

   • Read: Process ref_article/*_cleaned_body.md.
   • Update psmfiles/lexicon_domain.md: