fulltext-retrieval

Batch-downloads open-access PDFs for listed DOIs from multiple sources.

243|60|Updated Apr 6, 2026
One-click install
npx skills add https://github.com/Aperivue/medsci-skills --skill fulltext-retrieval
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: fulltext-retrieval
Source: https://github.com/Aperivue/medsci-skills/tree/main/skills/fulltext-retrieval
Command: npx skills add https://github.com/Aperivue/medsci-skills --skill fulltext-retrieval

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf4llm.

What problem does it solve?

Batch-downloading open-access PDFs for a list of DOIs from multiple OA sources to enable rapid literature review and meta-analysis.

Core Features & Use Cases

  • Multi-source OA retrieval: Unpaywall, Europe PMC / PMC OA, OpenAlex, and Crossref are queried to locate OA PDFs.
  • Robust input handling and fallbacks: Accepts plain DOIs or TSV with DOI/PMID; creates a manual list for DOIs that could not be retrieved.
  • Optional MD conversion: After download, PDFs can be converted to Markdown for token-efficient NLP tasks.

Quick Start

Create a DOIs file (one per line or TSV with a DOI column) and run fetch_oa.py with your input file and email to download OA PDFs.

Frequently Asked Questions about fulltext-retrieval

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I batch-download open-access PDFs using a list of DOIs?▼

To batch-download open-access PDFs, you provide a plain DOI list or TSV input file. The tool queries Unpaywall, PMC, OpenAlex, and Crossref to locate and retrieve available PDFs automatically for your literature review.

What sources are used to find full-text PDFs for literature reviews?▼

Full-text PDFs are located by querying Unpaywall, Europe PMC, OpenAlex, and Crossref. This multi-source pipeline implements fallbacks and robust error handling to maximize retrieval success for open-access documents.

Can I convert downloaded PDFs to Markdown for NLP tasks?▼

Yes, downloaded PDFs can be converted to Markdown. This optional conversion uses the pymupdf4llm dependency to produce token-efficient text outputs optimized for downstream natural language processing tasks.

Does this tool handle PMIDs in addition to standard DOIs?▼

Yes, it handles PMIDs alongside DOIs. You can provide a TSV input containing DOI or PMID columns, and the tool will process these identifiers to retrieve the corresponding open-access PDFs.

What happens to DOIs that cannot be retrieved from open-access sources?▼

For DOIs that could not be retrieved, the tool writes a manual list file. This output identifies all DOIs requiring intervention so you can manually locate or request the remaining full-text PDFs.

What is the best way to automate meta-analysis literature downloads?▼

Automating meta-analysis literature downloads is best handled by running a batch-download script with a TSV DOI file and email. The tool attempts multi-source OA retrieval and logs any failed DOIs for manual review.