Converts complex research papers and technical PDFs into clean, GitHub-renderable Markdown with accurate LaTeX math and extracted figures.
This skill provides a specialized workflow for transforming academic PDFs into GitHub Flavored Markdown (GFM). It solves the common problem of garbled math equations on GitHub by intelligently selecting between standard LaTeX delimiters and code blocks based on specific rendering engine quirks. It includes logic for detecting PDF source types (Word-generated, LaTeX, or scanned), automated image extraction, and KaTeX validation to ensure documentation remains professional and readable across version control platforms like GitHub and GitLab.
主要功能
01Cross-platform compatibility mapping for rendering math on both GitHub.com and self-hosted GitLab instances.
02Automated figure and image extraction with size-based noise filtering to exclude icons and watermarks.
03Source-aware PDF analysis to determine optimal extraction methods for Word, LaTeX, or scanned sources.
04Integrated validation pipeline using KaTeX to verify mathematical syntax before pushing to a repository.
0540 GitHub stars
06Advanced LaTeX formatting logic that prevents GitHub's markdown pre-processor from breaking multiline equations.
使用场景
01Migrating math-heavy legacy documentation from PDF format to a version-controlled Markdown environment.
02Converting arXiv papers or technical reports for documentation sites hosted on GitHub Pages or Wikis.
03Building a searchable, collaborative knowledge base of research papers within a Git repository.
