Convert PDF literature to Markdown and extract embedded figures.
npx skills add https://github.com/InternScience/ChemClaw --skill literature-parsing
Please help me install this Agent Skill. Skill: literature-parsing Source: https://github.com/InternScience/ChemClaw/tree/main/skills/literature-parsing Command: npx skills add https://github.com/InternScience/ChemClaw --skill literature-parsing
PDF literature often exists as static documents that are difficult to edit or reuse. This Skill converts PDFs into clean, editable Markdown and automatically extracts embedded figures for reuse in notes and papers.
Ask the system to convert a PDF to Markdown with embedded figures to produce a document and an images folder.
High-intent search queries and answers about installing and using this skill.
To convert PDFs to Markdown with figures, the Skill parses literature using MinerU as the backend to produce structured Markdown, an images directory, and metadata. It automatically extracts embedded images and preserves the original document layout during conversion.
Yes, you can process multiple PDFs for a literature review at once using batch processing. This feature handles multiple PDF files in a single run, outputting structured Markdown and extracted figures for each document to streamline literature management.
Yes, MinerU preserves document formatting and layout when parsing PDFs. The conversion relies on MinerU as the parsing backend to maintain the original structure and formatting, ensuring the resulting editable Markdown accurately reflects the source literature.
To extract metadata like title and authors from PDF literature, the Skill automatically captures this information along with page details during the conversion process. This produces metadata outputs specifically structured for reference management.
The best way to extract embedded images from PDF files is using a parsing tool that isolates figures into a separate directory. This Skill pulls embedded images and stores them alongside the generated Markdown for easy reuse in notes and papers.
AstorYHExtract all text content from PDF files via local paths or URLs.
73aiOrganize references, notes, and collaboration data across Drive, Docs, and Sheets.
smilebank7Generate structured Markdown lecture notes with PDF conversion and cross-references.
JuanMS20Extract text from PDFs and scanned documents using pymupdf and marker-pdf.
