🎁 Get the FREE AI Skills Starter Guide β€” Subscribe β†’
BytesAgainBytesAgain
BytesAgain β€Ί Skills β€Ί Paper Parse
πŸ¦€ ClawHub

Paper Parse

by @chen-li-17

Parse academic PDF papers into markdown with figure extraction.

Versionv1.0.0
Downloads752
#clawhub
TERMINAL
clawhub install paper-parse-figures

πŸ“– About This Skill

name: paper-parse description: Parse academic PDF papers into markdown with figure extraction. metadata: { "openclaw": { "emoji": "πŸ“„", "requires": { "bins": ["uv"] }, }, }

Paper Parse

Parse academic PDF papers into structured markdown with figure extraction using PyMuPDF.

Usage

uv run {baseDir}/scripts/parse_paper.py --pdf /path/to/paper.pdf [--output-dir ./output]

Output

The tool generates:

  • {paper_name}_content.md - Full paper content in markdown
  • {paper_name}_parsed.json - Structured metadata including:
    • - Paper title - Number of pages - Extracted figures with captions and paths
  • cover_title_authors.png - First-page snapshot focused on title + authors region
  • figures/ - Directory containing high-resolution figure screenshots

    • Example

    uv run scripts/parse_paper.py --pdf ~/papers/my-paper.pdf --output-dir ./parsed

    Output structure: 

    ./parsed/
β”œβ”€β”€ my-paper_content.md
β”œβ”€β”€ my-paper_parsed.json
└── figures/
    β”œβ”€β”€ figure_1.png
    β”œβ”€β”€ figure_2.png
    └── ...

    Dependencies

  • PyMuPDF (fitz) - PDF parsing and rendering
  • pymupdf4llm - Markdown conversion

    • These are automatically managed by uv via the inline script metadata.

    πŸ’‘ Examples

    uv run scripts/parse_paper.py --pdf ~/papers/my-paper.pdf --output-dir ./parsed

    Output structure: 

    ./parsed/
β”œβ”€β”€ my-paper_content.md
β”œβ”€β”€ my-paper_parsed.json
└── figures/
    β”œβ”€β”€ figure_1.png
    β”œβ”€β”€ figure_2.png
    └── ...