Convert study PDFs into structured Markdown with frontmatter and IMRaD sections.
npx skills add https://github.com/NoiseMeldOrg/skills --skill extract-study
Please help me install this Agent Skill. Skill: extract-study Source: https://github.com/NoiseMeldOrg/skills/tree/main/skills/extract-study Command: npx skills add https://github.com/NoiseMeldOrg/skills --skill extract-study
Researchers often need consistent, searchable summaries of scientific papers, including IMRaD structure and clean metadata.
This Skill converts study PDFs into a structured Markdown representation with a frontmatter header, IMRaD sections, and preserved references, enabling easy archiving and discovery.
Provide a study PDF to the tool and it will generate a Markdown file with clean metadata and a structured body.
High-intent search queries and answers about installing and using this skill.
Yes, this tool converts study PDFs into structured Markdown with frontmatter and IMRaD sections. It detects Introduction, Methods, Results, and Discussion sections while preserving references for knowledge management.
Yes, you can extract metadata like DOI and PMID from PubMed papers. The tool identifies titles, years, DOI, PMID, and PMCID from the first page, and attempts to identify authors and journal names.
Yes, the tool uses pdfplumber to handle two-column PDF layouts common in academic papers. It accurately detects and reorganizes content from complex multi-column study PDFs into clean Markdown sections.
The best way to preview extraction is using the dry-run option. This allows you to preview the structured Markdown results and verify IMRaD section detection before finalizing the file.
You can structure references from a DOI study by applying the tool to the paper. It preserves references and outputs a Markdown file suitable for a literature review repository, including metadata and key findings.
A limitation is that metadata extraction relies on the first page of the PDF, meaning author and journal identification is attempted but may not always be perfect for non-standard PMC article formats.
wen-chenRetrieve full-text articles and metadata from PubMed Central and OA sources.
zengbaochengExtract text from PDFs and scanned documents using pymupdf or marker-pdf OCR.
cyhinverseGenerate consistent documentation templates for READMEs, API references, and ADRs.
takemi-ohamaExtract text, tables, sections, and metadata from PDF documents.
